diff --git "a/data/splits/test.jsonl" "b/data/splits/test.jsonl" new file mode 100644--- /dev/null +++ "b/data/splits/test.jsonl" @@ -0,0 +1,281 @@ +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a toleration program for this self-care / medical / caregiver-delivered skill.\n\nTarget: tolerating tooth brushing by caregiver\nCurriculum: AFLS Basic Living Skills\nLearner: School-Age Learner\nMastery Status: Generalization phase\n\nPlease include the toleration end goal, shaping progression, antecedent strategies, reinforcement plan, refusal / safety procedures, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating tooth brushing by caregiver\n- Curriculum: AFLS Basic Living Skills\n- Learner: School-Age Learner\n- Current mastery: Generalization phase\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for tooth brushing performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nfull 2-minute tooth-brushing routine completed by caregiver without refusal, crying, SIB, or aggression\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1-second toothbrush contact with teeth\n2. 3 seconds of brushing\n3. 5 seconds of brushing\n4. 15 seconds of brushing\n5. 30 seconds of brushing\n6. 60 seconds of brushing\n7. Full 2-minute brushing routine\n\nCurrent shaping step: At the generalization stage, begin at shaping step 6 (\"60 seconds of brushing\") and advance through step 7 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal activity tolerated with 2 different caregivers (primary caregiver + one other) across 2 consecutive weeks.\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 3 different settings and with 3 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "e3d789cfc2f4c909", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating tooth brushing by caregiver", "program_type": "toleration", "learner_profile": "school_age", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating tooth brushing by caregiver", "module": "basic_living", "mastery_criterion": "mc_toleration_caregivers", "shaping_n_steps": 7}, "teacher_model": null, "seed_tag": "39765"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: selects by single function from array of 3\nCurriculum Reference: LRFFC L1\nLearner Profile: Early Learner\nCurrent Mastery: Developing\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects by single function from array of 3\n- Curriculum: LRFFC L1\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: spoon, plate, jacket\nDistractor stimuli: shoe, car\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "ca08f6959493ae2a", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L1", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects by single function from array of 3", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "crf", "error_correction": "simple_correction", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "56565"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1860\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Mand + Reading + Writing\nDate range: Sessions 1\u20138 across 16 days (2026-06-10 to 2026-06-26)\n\nACCELERATION PROGRAMS\n1. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n2. selects items by feature (Listener Responding)\n Method: DTT\n3. copies simple words from model (Writing)\n Method: DTT\n4. reads 10\u201320 sight words (Reading)\n Method: DTT\n\nDECELERATION TARGETS\n1. Vocal stereotypy \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-10 \u2014 38 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/10 correct (38%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n selects items by feature: 5/12 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d77\n copies simple words from model: 4/13 correct (28%); latency 4.9s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d710\n reads 10\u201320 sight words: 3/8 correct (36%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n Vocal stereotypy: freq 0; PIR 0%\n\nSession 2 \u2014 2026-06-12 \u2014 38 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/14 correct (44%); latency 4.1s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d78\n selects items by feature: 4/9 correct (47%); latency 4.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n copies simple words from model: 3/10 correct (33%); latency 4.7s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n reads 10\u201320 sight words: 4/8 correct (46%); latency 4.2s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n Vocal stereotypy: freq 1; PIR 5%\n\nSession 3 \u2014 2026-06-14 \u2014 38 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/11 correct (53%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n selects items by feature: 8/15 correct (52%); latency 3.9s; prompts FP\u00d75, PP\u00d75, G\u00d70, I\u00d75\n copies simple words from model: 5/15 correct (36%); latency 4.3s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d713\n reads 10\u201320 sight words: 6/12 correct (53%); latency 3.4s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d75\n Vocal stereotypy: freq 0; PIR 10%\n\nSession 4 \u2014 2026-06-16 \u2014 38 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/13 correct (56%); latency 3.7s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d78\n selects items by feature: 8/12 correct (64%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d79\n copies simple words from model: 4/10 correct (43%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n reads 10\u201320 sight words: 4/8 correct (52%); latency 3.5s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n Vocal stereotypy: freq 0; PIR 0%\n\nSession 5 \u2014 2026-06-18 \u2014 38 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/10 correct (56%); latency 3.6s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n selects items by feature: 10/15 correct (65%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d75, I\u00d75\n copies simple words from model: 4/8 correct (45%); latency 4.3s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n reads 10\u201320 sight words: 6/11 correct (58%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n Vocal stereotypy: freq 0; PIR 8%\n\nSession 6 \u2014 2026-06-20 \u2014 38 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/11 correct (61%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d79\n selects items by feature: 11/15 correct (73%); latency 2.7s; prompts FP\u00d73, PP\u00d75, G\u00d75, I\u00d72\n copies simple words from model: 4/8 correct (50%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n reads 10\u201320 sight words: 10/15 correct (69%); latency 3.1s; prompts FP\u00d75, PP\u00d71, G\u00d70, I\u00d79\n Vocal stereotypy: freq 0; PIR 10%\n\nSession 7 \u2014 2026-06-22 \u2014 38 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/12 correct (66%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d711\n selects items by feature: 7/8 correct (88%); latency 1.8s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n copies simple words from model: 6/11 correct (57%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n reads 10\u201320 sight words: 6/8 correct (71%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n Vocal stereotypy: freq 0; PIR 4%\n\nSession 8 \u2014 2026-06-24 \u2014 38 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/12 correct (72%); latency 2.8s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d75\n selects items by feature: 14/15 correct (92%); latency 1.7s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d713\n copies simple words from model: 9/13 correct (68%); latency 2.9s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d78\n reads 10\u201320 sight words: 9/12 correct (72%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d712\n Vocal stereotypy: freq 0; PIR 3%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Requesting more trials verbally\n- Smiling during reinforcement delivery\n- Appropriate sitting posture maintained"}, {"role": "assistant", "content": "## Clinical Concerns\n- Steady improvement: accuracy rose from 38% to 72% across 8 sessions.\n- No clinical concerns at this time; mastery criteria should be reachable within a few additional sessions.\n\n## Pattern Classification\nmastery_progression\n\nAccuracy is ascending cleanly across sessions with no interfering behaviors, consistent with a mastery-progression trajectory.\n\n## Behavior Function Hypothesis\nVocal stereotypy: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Continue current teaching procedure \u2014 it is effective for this learner.\n- Maintain current stimulus arrangement; begin planning next skill in sequence.\n\n### Consequence strategies\n- Begin thinning reinforcement from CRF to FR-2 as accuracy stabilizes above 85%.\n- Continue differential reinforcement for independent responses.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 55.7%.\n- Trend direction: upward (first session: 38%, last session: 72%).\n- Vocal stereotypy: mean 0.1/session (early-window mean 0.5 -> late-window mean 0.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "1e4bd278d3ad9077", "gold_labels": {"pattern_class": "mastery_progression", "behavior_functions": {"Vocal stereotypy": "automatic"}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "mastery_progression", "learner_profile": "early", "n_sessions": 8, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["vocal_stereotypy"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "76532"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7364\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Listener Responding + Mand + Tolerating Denied Access + Writing\nDate range: Sessions 1\u201312 across 24 days (2026-07-25 to 2026-08-18)\n\nACCELERATION PROGRAMS\n1. copies simple words from model (Writing)\n Method: DTT\n2. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n3. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n4. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n5. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n6. selects items by feature (Listener Responding)\n Method: DTT\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-25 \u2014 49 min \u2014 1 observer\n copies simple words from model: 5/9 correct (57%); latency 3.3s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/12 correct (57%); latency 3.3s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d75\n wait calmly when access to preferred item is denied: 6/14 correct (41%); latency 4.3s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d74\n answers WH-questions about familiar topics: 5/9 correct (59%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n requesting a break ('break please' or AAC 'I need a break'): 9/14 correct (68%); latency 3.0s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n selects items by feature: 8/15 correct (53%); latency 3.8s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d711\n\nSession 2 \u2014 2026-07-27 \u2014 49 min \u2014 1 observer\n copies simple words from model: 7/10 correct (65%); latency 3.0s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/13 correct (51%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d79\n wait calmly when access to preferred item is denied: 4/10 correct (45%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d76\n answers WH-questions about familiar topics: 7/13 correct (55%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 5/8 correct (69%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n selects items by feature: 7/13 correct (52%); latency 3.6s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n\nSession 3 \u2014 2026-07-29 \u2014 49 min \u2014 1 observer\n copies simple words from model: 10/14 correct (69%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d710\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/9 correct (61%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d79\n wait calmly when access to preferred item is denied: 7/13 correct (54%); latency 3.3s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d75\n answers WH-questions about familiar topics: 8/14 correct (55%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 8/12 correct (63%); latency 3.2s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d76\n selects items by feature: 7/13 correct (54%); latency 3.3s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d77\n\nSession 4 \u2014 2026-07-31 \u2014 49 min \u2014 1 observer\n copies simple words from model: 9/13 correct (72%); latency 2.6s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/11 correct (56%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d711\n wait calmly when access to preferred item is denied: 7/13 correct (55%); latency 3.3s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d75\n answers WH-questions about familiar topics: 8/13 correct (62%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 8/11 correct (71%); latency 3.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d75\n selects items by feature: 6/11 correct (54%); latency 3.7s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d710\n\nSession 5 \u2014 2026-08-02 \u2014 49 min \u2014 1 observer\n copies simple words from model: 7/11 correct (65%); latency 3.2s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/11 correct (55%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n wait calmly when access to preferred item is denied: 6/10 correct (64%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n answers WH-questions about familiar topics: 4/8 correct (52%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 5/9 correct (58%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d75\n selects items by feature: 5/12 correct (41%); latency 4.3s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d75\n\nSession 6 \u2014 2026-08-04 \u2014 49 min \u2014 1 observer\n copies simple words from model: 11/15 correct (76%); latency 2.8s; prompts FP\u00d75, PP\u00d74, G\u00d74, I\u00d72\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/8 correct (63%); latency 3.2s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n wait calmly when access to preferred item is denied: 4/8 correct (56%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n answers WH-questions about familiar topics: 6/10 correct (56%); latency 3.3s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 6/10 correct (59%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d77\n selects items by feature: 8/15 correct (52%); latency 3.4s; prompts FP\u00d73, PP\u00d70, G\u00d75, I\u00d77\n\nSession 7 \u2014 2026-08-06 \u2014 49 min \u2014 1 observer\n copies simple words from model: 8/11 correct (73%); latency 3.0s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/11 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d79\n wait calmly when access to preferred item is denied: 6/10 correct (58%); latency 3.7s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n answers WH-questions about familiar topics: 9/15 correct (62%); latency 3.5s; prompts FP\u00d73, PP\u00d73, G\u00d75, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 8/13 correct (63%); latency 2.9s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d78\n selects items by feature: 7/15 correct (46%); latency 3.7s; prompts FP\u00d74, PP\u00d73, G\u00d75, I\u00d73\n\nSession 8 \u2014 2026-08-08 \u2014 49 min \u2014 1 observer\n copies simple words from model: 11/14 correct (75%); latency 2.8s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/14 correct (63%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d74\n wait calmly when access to preferred item is denied: 6/11 correct (55%); latency 3.6s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n answers WH-questions about familiar topics: 6/11 correct (59%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 6/9 correct (67%); latency 2.8s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n selects items by feature: 4/10 correct (41%); latency 4.0s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n\nSession 9 \u2014 2026-08-10 \u2014 49 min \u2014 1 observer\n copies simple words from model: 7/9 correct (74%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/13 correct (73%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d711\n wait calmly when access to preferred item is denied: 7/11 correct (59%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d78\n answers WH-questions about familiar topics: 5/8 correct (60%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 7/10 correct (74%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n selects items by feature: 5/11 correct (48%); latency 3.7s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n\nSession 10 \u2014 2026-08-12 \u2014 49 min \u2014 1 observer\n copies simple words from model: 11/15 correct (74%); latency 2.8s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d711\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/10 correct (63%); latency 3.3s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d76\n wait calmly when access to preferred item is denied: 7/12 correct (57%); latency 3.5s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d74\n answers WH-questions about familiar topics: 6/13 correct (50%); latency 3.9s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 9/15 correct (59%); latency 3.5s; prompts FP\u00d75, PP\u00d73, G\u00d71, I\u00d76\n selects items by feature: 5/15 correct (35%); latency 4.4s; prompts FP\u00d72, PP\u00d74, G\u00d75, I\u00d74\n\nSession 11 \u2014 2026-08-14 \u2014 49 min \u2014 1 observer\n copies simple words from model: 6/8 correct (72%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/13 correct (71%); latency 2.8s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d78\n wait calmly when access to preferred item is denied: 10/14 correct (73%); latency 2.9s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d76\n answers WH-questions about familiar topics: 9/14 correct (65%); latency 3.1s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 8/13 correct (64%); latency 3.0s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n selects items by feature: 6/13 correct (44%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d79\n\nSession 12 \u2014 2026-08-16 \u2014 49 min \u2014 1 observer\n copies simple words from model: 7/9 correct (80%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/12 correct (66%); latency 3.3s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n wait calmly when access to preferred item is denied: 8/12 correct (69%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d712\n answers WH-questions about familiar topics: 5/9 correct (53%); latency 3.7s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 9/12 correct (71%); latency 2.9s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d72\n selects items by feature: 7/15 correct (46%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d710\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Stereotypic behavior during inter-trial intervals\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Plateau**: accuracy has remained near 69% for 12 sessions without meaningful improvement.\n- Performance is below mastery criteria; current teaching procedure may not be effective for this learner.\n\n## Pattern Classification\nplateau\n\nResponding has stabilized below mastery criterion without meaningful movement, indicating the current procedure is limiting further acquisition.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Modify teaching procedure \u2014 switch prompt type (e.g., from most-to-least to time delay).\n- Conduct preference assessment and update reinforcer menu.\n- Break the current skill into smaller component steps if possible.\n- Increase practice opportunities by embedding targets in natural-environment training.\n\n### Consequence strategies\n- Check for inadvertent reinforcement of near-misses; tighten differential reinforcement.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 71.1%.\n- Trend direction: upward (first session: 57%, last session: 80%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "e9ee174e3677e968", "gold_labels": {"pattern_class": "plateau", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "plateau", "learner_profile": "early", "n_sessions": 12, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "12904"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6041\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Mand + Motor Imitation + Reading + Tact + Writing\nDate range: Sessions 1\u20136 across 12 days (2026-08-02 to 2026-08-14)\n\nACCELERATION PROGRAMS\n1. tacts colors of objects (Tact)\n Method: DTT\n2. reads 10\u201320 sight words (Reading)\n Method: DTT\n3. copies simple words from model (Writing)\n Method: DTT\n4. imitates 3-step motor sequences (Motor Imitation)\n Method: DTT variant\n5. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n6. selects items by feature (Listener Responding)\n Method: DTT\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-02 \u2014 31 min \u2014 1 observer\n tacts colors of objects: 3/13 correct (23%); latency 4.7s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d77\n reads 10\u201320 sight words: 3/11 correct (23%); latency 4.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n copies simple words from model: 2/9 correct (28%); latency 4.6s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n imitates 3-step motor sequences: 3/12 correct (27%); latency 4.5s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 2/12 correct (18%); latency 5.5s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d74\n selects items by feature: 2/10 correct (22%); latency 4.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n\nSession 2 \u2014 2026-08-04 \u2014 31 min \u2014 1 observer\n tacts colors of objects: 3/9 correct (34%); latency 4.5s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n reads 10\u201320 sight words: 4/13 correct (33%); latency 4.6s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d78\n copies simple words from model: 5/13 correct (36%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d79\n imitates 3-step motor sequences: 5/14 correct (34%); latency 4.3s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d712\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/10 correct (31%); latency 4.9s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n selects items by feature: 4/12 correct (32%); latency 4.4s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d74\n\nSession 3 \u2014 2026-08-06 \u2014 31 min \u2014 1 observer\n tacts colors of objects: 4/12 correct (37%); latency 4.2s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d78\n reads 10\u201320 sight words: 4/10 correct (42%); latency 4.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d78\n copies simple words from model: 6/12 correct (46%); latency 3.8s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d74\n imitates 3-step motor sequences: 4/10 correct (44%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/15 correct (38%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d712\n selects items by feature: 5/13 correct (41%); latency 4.0s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n\nSession 4 \u2014 2026-08-08 \u2014 31 min \u2014 1 observer\n tacts colors of objects: 4/8 correct (49%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n reads 10\u201320 sight words: 5/10 correct (53%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n copies simple words from model: 6/11 correct (55%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n imitates 3-step motor sequences: 5/9 correct (53%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/8 correct (52%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n selects items by feature: 5/9 correct (51%); latency 4.0s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n\nSession 5 \u2014 2026-08-10 \u2014 IOA SESSION \u2014 2 observers\n tacts colors of objects: 54% (primary); IOA 89% agreement\n reads 10\u201320 sight words: 57% (primary); IOA 89% agreement\n copies simple words from model: 62% (primary); IOA 89% agreement\n imitates 3-step motor sequences: 61% (primary); IOA 89% agreement\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 60% (primary); IOA 89% agreement\n selects items by feature: 60% (primary); IOA 89% agreement\n\nSession 6 \u2014 2026-08-12 \u2014 31 min \u2014 1 observer\n tacts colors of objects: 7/10 correct (65%); latency 3.2s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d76\n reads 10\u201320 sight words: 8/11 correct (68%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n copies simple words from model: 7/10 correct (70%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n imitates 3-step motor sequences: 10/14 correct (72%); latency 2.8s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/13 correct (71%); latency 3.0s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d77\n selects items by feature: 10/15 correct (70%); latency 2.8s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d713\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Quick response latency (within 2\u20133 seconds)\n- Appropriate sitting posture maintained"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 23% to 65% across 6 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 6 sessions of data with IOA evidence.\n\n## Data-Supported Rationale\n- Mean accuracy across 6 sessions: 43.5%.\n- Trend direction: upward (first session: 23%, last session: 65%).\n- IOA data: 89% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "522241129579b054", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "early", "n_sessions": 6, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "91206"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: spontaneously vocalizes during preferred activities\nCurriculum Reference: Spontaneous Vocal Behavior L1\nLearner Profile: Early Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously vocalizes during preferred activities\n- Curriculum: Spontaneous Vocal Behavior L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: room transition.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's room transition routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the approaching mastery stage, use time delay (0 s -> 2 s -> 4 s) before delivering any model prompt; reinforce independent responses differentially.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "0fe5d4b85ec54243", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously vocalizes during preferred activities", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "54871"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: matches non-identical items by category\nCurriculum: Visual Perceptual Skills & Matching-to-Sample L2\nLearner: Early Learner\nMastery Status: Emerging\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: matches non-identical items by category\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L2\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: hat, spoon, phone\nDistractor stimuli: cup, blanket, backpack, scissors\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "514d19a4d252abe7", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L2", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "matches non-identical items by category", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "5667"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: crossing a street safely\nCurriculum: AFLS Community Participation Skills\nLearner: Adolescent Learner\nMastery Status: Mastered at current level\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: crossing a street safely\n- Curriculum: AFLS Community Participation Skills\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Approach the crosswalk and stop at the curb.\n2. Look left, look right, look left again.\n3. Identify the walk signal or absence of traffic.\n4. Begin to cross while continuing to scan for vehicles.\n5. Cross directly to the opposite curb.\n6. Step up onto the sidewalk.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the mastered stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nToken economy \u2014 One token per correctly-completed step; token exchange at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 180s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "1cfc4bb1fafba7bc", "gold_labels": {"method": "task_analysis", "domain": "AFLS.community", "skill": "crossing a street safely", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "mastered", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "crossing a street safely", "module": "community", "mastery_criterion": "mc_fluent_chain", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "75542"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1781\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Social Behavior + Writing\nDate range: Sessions 1\u20138 across 16 days (2026-01-15 to 2026-01-31)\n\nACCELERATION PROGRAMS\n1. identifies numerals 1\u201320 (Math)\n Method: DTT\n2. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n3. takes turns during structured activities (Social Behavior)\n Method: PRT\n4. copies simple words from model (Writing)\n Method: DTT\n5. requesting a break during non-preferred tasks (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Vocal stereotypy \u2014 function hypothesized: automatic\n2. Motor stereotypy \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-15 \u2014 36 min \u2014 1 observer\n identifies numerals 1\u201320: 4/9 correct (47%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n indicating 'all done' when an activity is complete: 6/9 correct (65%); latency 3.2s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n takes turns during structured activities: 6/14 correct (44%); latency 4.1s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d76\n copies simple words from model: 11/15 correct (70%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d78\n requesting a break during non-preferred tasks: 9/15 correct (61%); latency 3.4s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d711\n Vocal stereotypy: freq 2; PIR 18%\n Motor stereotypy: freq 1; PIR 9%\n ABC (vocal stereotypy): A = quiet unstructured moment between trials; B = engaged in hand-flapping; C = no social consequence; self-terminated after 30s\n\nSession 2 \u2014 2026-01-17 \u2014 36 min \u2014 1 observer\n identifies numerals 1\u201320: 6/11 correct (51%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n indicating 'all done' when an activity is complete: 4/9 correct (42%); latency 4.2s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n takes turns during structured activities: 6/14 correct (40%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d79\n copies simple words from model: 5/15 correct (32%); latency 4.8s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d711\n requesting a break during non-preferred tasks: 3/9 correct (32%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n Vocal stereotypy: freq 1; PIR 11%\n Motor stereotypy: freq 3; PIR 20%\n\nSession 3 \u2014 2026-01-19 \u2014 IOA SESSION \u2014 2 observers\n identifies numerals 1\u201320: 60% (primary); IOA 96% agreement\n indicating 'all done' when an activity is complete: 44% (primary); IOA 96% agreement\n takes turns during structured activities: 27% (primary); IOA 96% agreement\n copies simple words from model: 47% (primary); IOA 96% agreement\n requesting a break during non-preferred tasks: 27% (primary); IOA 96% agreement\n Vocal stereotypy: freq 3; PIR 17%; IOA 96% agreement\n Motor stereotypy: freq 1; PIR 14%; IOA 96% agreement\n\nSession 4 \u2014 2026-01-21 \u2014 36 min \u2014 1 observer\n identifies numerals 1\u201320: 7/10 correct (66%); latency 3.0s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n indicating 'all done' when an activity is complete: 7/9 correct (81%); latency 2.5s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d75\n takes turns during structured activities: 4/9 correct (49%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n copies simple words from model: 3/8 correct (43%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n requesting a break during non-preferred tasks: 3/9 correct (34%); latency 4.7s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d72\n Vocal stereotypy: freq 3; PIR 16%\n Motor stereotypy: freq 1; PIR 13%\n\nSession 5 \u2014 2026-01-23 \u2014 36 min \u2014 1 observer\n identifies numerals 1\u201320: 6/11 correct (51%); latency 3.7s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n indicating 'all done' when an activity is complete: 7/14 correct (49%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d77\n takes turns during structured activities: 5/9 correct (61%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n copies simple words from model: 4/10 correct (41%); latency 4.0s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n requesting a break during non-preferred tasks: 5/10 correct (50%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n Vocal stereotypy: freq 2; PIR 12%\n Motor stereotypy: freq 2; PIR 16%\n\nSession 6 \u2014 2026-01-25 \u2014 36 min \u2014 1 observer\n identifies numerals 1\u201320: 6/12 correct (48%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d76\n indicating 'all done' when an activity is complete: 4/8 correct (50%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n takes turns during structured activities: 4/15 correct (30%); latency 4.9s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d710\n copies simple words from model: 3/9 correct (38%); latency 4.2s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n requesting a break during non-preferred tasks: 4/10 correct (35%); latency 4.4s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n Vocal stereotypy: freq 2; PIR 9%\n Motor stereotypy: freq 2; PIR 9%\n\nSession 7 \u2014 2026-01-27 \u2014 36 min \u2014 1 observer\n identifies numerals 1\u201320: 3/9 correct (32%); latency 4.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n indicating 'all done' when an activity is complete: 5/8 correct (60%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n takes turns during structured activities: 3/12 correct (23%); latency 4.9s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d77\n copies simple words from model: 4/12 correct (35%); latency 4.4s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d78\n requesting a break during non-preferred tasks: 7/13 correct (54%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d78\n Vocal stereotypy: freq 2; PIR 9%\n Motor stereotypy: freq 5; PIR 16%\n\nSession 8 \u2014 2026-01-29 \u2014 36 min \u2014 1 observer\n identifies numerals 1\u201320: 7/13 correct (56%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d78\n indicating 'all done' when an activity is complete: 6/10 correct (65%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n takes turns during structured activities: 3/8 correct (43%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n copies simple words from model: 7/13 correct (57%); latency 3.6s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n requesting a break during non-preferred tasks: 6/10 correct (58%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d76\n Vocal stereotypy: freq 2; PIR 19%\n Motor stereotypy: freq 3; PIR 10%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Leaving seat without permission\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 52% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Behavior Function Hypothesis\nVocal stereotypy: automatic\n Evidence: ABC events in the log support the automatic function; behavior persists across contexts without clear social mediation.\nMotor stereotypy: automatic\n Evidence: ABC events in the log support the automatic function; behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 8 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 51.5%.\n- Trend direction: upward (first session: 47%, last session: 56%).\n- Vocal stereotypy: mean 2.1/session (early-window mean 1.5 -> late-window mean 2.0).\n- Motor stereotypy: mean 2.2/session (early-window mean 2.0 -> late-window mean 4.0).\n- IOA data: 96% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "11b0878c10d829bd", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {"Vocal stereotypy": "automatic", "Motor stereotypy": "automatic"}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "school_age", "n_sessions": 8, "n_programs": 5, "n_behaviors": 2, "behavior_ids": ["vocal_stereotypy", "motor_stereotypy"], "behavior_functions": ["automatic", "automatic"], "has_abc_data": true, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "41084"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: identifies all lower-case letters\nCurriculum Reference: Reading L2\nLearner Profile: School-Age Learner\nCurrent Mastery: Near mastery\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies all lower-case letters\n- Curriculum: Reading L2\n- Learner: School-Age Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What letter is this?\"\nVariations: \"Read this letter\"; \"What does this say?\"\nPresentation: Present the letter flashcard.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: M, N, Z\nDistractor stimuli: K, C, V, E\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "23fa3255f35f0eff", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L2", "learner_profile": "school_age", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies all lower-case letters", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "vr3", "error_correction": "simple_correction", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "93657"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9955\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Mand + Self-Care\nDate range: Sessions 1\u201311 across 22 days (2026-02-02 to 2026-02-24)\n\nACCELERATION PROGRAMS\n1. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n2. requesting a break during non-preferred activities (Mand)\n Method: NET\n3. identifying community safety signs (Community)\n Method: DTT\n4. requesting preferred items using AAC device (Mand)\n Method: NET\n5. brushing teeth independently (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Non-compliance \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-02 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 7/8 correct (84%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n requesting a break during non-preferred activities: 8/10 correct (77%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n identifying community safety signs: 7/10 correct (72%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n requesting preferred items using AAC device: 7/10 correct (75%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n brushing teeth independently: 7/8 correct (87%); latency 1.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n Non-compliance: freq 2\n\nSession 2 \u2014 2026-02-04 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 6/9 correct (72%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n requesting a break during non-preferred activities: 11/15 correct (70%); latency 2.9s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d77\n identifying community safety signs: 9/14 correct (62%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d77\n requesting preferred items using AAC device: 10/15 correct (65%); latency 3.2s; prompts FP\u00d75, PP\u00d74, G\u00d70, I\u00d76\n brushing teeth independently: 10/12 correct (80%); latency 2.7s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d75\n Non-compliance: freq 3\n\nSession 3 \u2014 2026-02-06 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 6/9 correct (68%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n requesting a break during non-preferred activities: 5/9 correct (60%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n identifying community safety signs: 5/8 correct (64%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n requesting preferred items using AAC device: 9/15 correct (62%); latency 3.2s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d74\n brushing teeth independently: 9/14 correct (64%); latency 2.8s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d711\n Non-compliance: freq 4\n ABC (non-compliance): A = asked to finish dressing task; B = kicked at materials; C = task paused for 3 min\n\nSession 4 \u2014 2026-02-08 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 8/12 correct (67%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d79\n requesting a break during non-preferred activities: 8/15 correct (55%); latency 3.5s; prompts FP\u00d72, PP\u00d75, G\u00d71, I\u00d77\n identifying community safety signs: 5/11 correct (49%); latency 4.1s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n requesting preferred items using AAC device: 8/14 correct (60%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d710\n brushing teeth independently: 5/8 correct (63%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n Non-compliance: freq 5\n\nSession 5 \u2014 2026-02-10 \u2014 IOA SESSION \u2014 2 observers\n meal cleanup after eating: 63% (primary); IOA 86% agreement\n requesting a break during non-preferred activities: 53% (primary); IOA 86% agreement\n identifying community safety signs: 42% (primary); IOA 86% agreement\n requesting preferred items using AAC device: 50% (primary); IOA 86% agreement\n brushing teeth independently: 50% (primary); IOA 86% agreement\n Non-compliance: freq 5; IOA 86% agreement\n\nSession 6 \u2014 2026-02-12 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 6/12 correct (49%); latency 4.0s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d76\n requesting a break during non-preferred activities: 6/13 correct (47%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d76\n identifying community safety signs: 6/15 correct (39%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d75, I\u00d77\n requesting preferred items using AAC device: 8/15 correct (52%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d714\n brushing teeth independently: 6/12 correct (49%); latency 3.6s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d74\n Non-compliance: freq 6\n\nSession 7 \u2014 2026-02-14 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 5/11 correct (44%); latency 4.2s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n requesting a break during non-preferred activities: 5/14 correct (36%); latency 4.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d711\n identifying community safety signs: 3/11 correct (23%); latency 4.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n requesting preferred items using AAC device: 5/11 correct (45%); latency 4.0s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n brushing teeth independently: 5/12 correct (40%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d78\n Non-compliance: freq 6\n\nSession 8 \u2014 2026-02-16 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 4/10 correct (41%); latency 4.0s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n requesting a break during non-preferred activities: 4/12 correct (32%); latency 4.8s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n identifying community safety signs: 3/13 correct (23%); latency 4.7s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d79\n requesting preferred items using AAC device: 3/8 correct (38%); latency 4.3s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n brushing teeth independently: 4/15 correct (26%); latency 4.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d711\n Non-compliance: freq 7\n ABC (non-compliance): A = transition to non-preferred activity; B = dropped to floor, cried; C = transition delayed, preferred item offered\n\nSession 9 \u2014 2026-02-18 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 5/13 correct (36%); latency 4.5s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n requesting a break during non-preferred activities: 3/12 correct (24%); latency 4.8s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d75\n identifying community safety signs: 1/11 correct (12%); latency 5.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n requesting preferred items using AAC device: 3/10 correct (30%); latency 4.7s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n brushing teeth independently: 2/9 correct (17%); latency 5.0s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n Non-compliance: freq 8\n\nSession 10 \u2014 2026-02-20 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 3/12 correct (28%); latency 4.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d77\n requesting a break during non-preferred activities: 3/15 correct (19%); latency 5.0s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d711\n identifying community safety signs: 1/12 correct (10%); latency 5.6s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d76\n requesting preferred items using AAC device: 3/9 correct (32%); latency 4.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n brushing teeth independently: 1/11 correct (13%); latency 5.6s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d710\n Non-compliance: freq 8\n\nSession 11 \u2014 2026-02-22 \u2014 48 min \u2014 1 observer\n meal cleanup after eating: 4/15 correct (27%); latency 4.5s; prompts FP\u00d75, PP\u00d71, G\u00d74, I\u00d75\n requesting a break during non-preferred activities: 2/11 correct (21%); latency 5.3s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n identifying community safety signs: 1/11 correct (10%); latency 5.8s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n requesting preferred items using AAC device: 3/11 correct (24%); latency 5.0s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n brushing teeth independently: 1/12 correct (10%); latency 5.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d79\n Non-compliance: freq 9\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Peer aggression (hitting or pushing peers during group activities)\n- Turning away from task or staff\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (84% -> 27%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nNon-compliance: escape\n Evidence: ABC events in the log support the escape function; behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nhigh\n\nPattern is well-supported: 11 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 52.6%.\n- Trend direction: downward (first session: 84%, last session: 27%).\n- Non-compliance: mean 5.7/session (early-window mean 3.0 -> late-window mean 8.3).\n- IOA data: 86% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "8c52dd7133f4d1fe", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Non-compliance": "escape"}, "escalation_level": 3, "confidence": "high", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "adolescent", "n_sessions": 11, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["non_compliance"], "behavior_functions": ["escape"], "has_abc_data": true, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "5662"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: mands for others to stop an action\nCurriculum: Mand L2\nLearner Level: Early Learner\nBaseline: Developing\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands for others to stop an action\n- Curriculum: Mand L2\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nBriefly withhold or restrict access to the target preferred item/activity for 30\u201360 seconds to establish motivation before the teaching opportunity.\nPrimary natural context: snack time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's snack time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the developing stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: performance of the requested action.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "aaa9e8903eb01d6d", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L2", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands for others to stop an action", "mo_category": "mand_action", "mo_arrangement": "deprivation_preferred_item", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "70185"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: washing hands\nCurriculum Reference: AFLS Basic Living Skills\nLearner Profile: Adult Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: Task Analysis / Chaining\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: washing hands\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Approaching mastery\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Walk to the sink.\n2. Turn on the water.\n3. Wet hands under the water.\n4. Apply soap to hands.\n5. Rub hands together for 15\u201320 seconds, covering fronts, backs, and between fingers.\n6. Rinse hands thoroughly under the water.\n7. Turn off the water.\n8. Dry hands with a towel.\n\n## Prompt Strategy Per Step\nStrategy: Most-to-Least\nStart with full-physical prompt at each step; fade to partial physical, gestural, verbal, independent.\nCurrent prompt level: At the approaching mastery stage, use partial-physical or gestural prompts only at steps where errors occur; allow independence elsewhere.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\n100% of steps completed independently (no prompts) across 3 consecutive trials of the full chain.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "168c6707572c4655", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "washing hands", "program_type": "independence", "learner_profile": "adult", "mastery_state": "approaching", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "washing hands", "module": "basic_living", "mastery_criterion": "mc_all_steps_independent", "chain_type": "total_task", "prompt_strategy": "most_to_least", "reinforcement_schedule": "crf_per_step", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "97806"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a toleration program for this self-care / medical / caregiver-delivered skill.\n\nTarget: tolerating nail clipping\nCurriculum: AFLS Basic Living Skills\nLearner: Adolescent Learner\nMastery Status: Emerging\n\nPlease include the toleration end goal, shaping progression, antecedent strategies, reinforcement plan, refusal / safety procedures, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating nail clipping\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adolescent Learner\n- Current mastery: Emerging\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for nail clipping performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nall 10 fingernails (and optionally toenails) clipped by caregiver without refusal, pulling hand away, or safety behaviors\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1 fingernail clipped\n2. 2 fingernails clipped in one sitting\n3. 5 fingernails clipped (one hand)\n4. All 10 fingernails clipped\n5. All 10 fingernails + 10 toenails clipped\n\nCurrent shaping step: At the emerging stage, begin at shaping step 1 (\"1 fingernail clipped\") and advance through step 2 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal activity tolerated with 2 different caregivers (primary caregiver + one other) across 2 consecutive weeks.\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 2 different settings and with 3 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "dadc5d8b36a11468", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating nail clipping", "program_type": "toleration", "learner_profile": "adolescent", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating nail clipping", "module": "basic_living", "mastery_criterion": "mc_toleration_caregivers", "shaping_n_steps": 5}, "teacher_model": null, "seed_tag": "68917"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9164\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Mand + Reading + Self-Care + Tolerating Denied Access\nDate range: Sessions 1\u20138 across 16 days (2026-08-02 to 2026-08-18)\n\nACCELERATION PROGRAMS\n1. sounds out CVC words (Reading)\n Method: DTT\n2. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n3. requesting help when a task is difficult (Mand)\n Method: NET\n4. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n5. ordering in a restaurant (Community)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-02 \u2014 52 min \u2014 1 observer\n sounds out CVC words: 8/9 correct (89%); latency 1.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n dressing (pants, shirt): 8/9 correct (91%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n requesting help when a task is difficult: 13/15 correct (88%); latency 1.9s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d77\n wait calmly when access to preferred item is denied: 7/9 correct (81%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n ordering in a restaurant: 11/13 correct (81%); latency 2.4s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n Tantrum: freq 2, duration 10m total\n ABC (tantrum): A = transition to non-preferred activity; B = dropped to floor, cried; C = transition delayed, preferred item offered\n\nSession 2 \u2014 2026-08-04 \u2014 52 min \u2014 1 observer\n sounds out CVC words: 13/14 correct (95%); latency 1.4s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d78\n dressing (pants, shirt): 8/9 correct (90%); latency 1.9s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d79\n requesting help when a task is difficult: 13/15 correct (89%); latency 1.9s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d76\n wait calmly when access to preferred item is denied: 9/12 correct (75%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d710\n ordering in a restaurant: 13/15 correct (86%); latency 2.2s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d77\n Tantrum: freq 3, duration 6m total\n\nSession 3 \u2014 2026-08-06 \u2014 52 min \u2014 1 observer\n sounds out CVC words: 10/11 correct (95%); latency 1.4s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n dressing (pants, shirt): 12/13 correct (89%); latency 2.1s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n requesting help when a task is difficult: 11/13 correct (87%); latency 2.1s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d74\n wait calmly when access to preferred item is denied: 8/11 correct (72%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n ordering in a restaurant: 7/8 correct (89%); latency 2.2s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n Tantrum: freq 2, duration 8m total\n\nSession 4 \u2014 2026-08-08 \u2014 52 min \u2014 1 observer\n sounds out CVC words: 13/14 correct (94%); latency 1.9s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d74\n dressing (pants, shirt): 8/8 correct (96%); latency 1.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n requesting help when a task is difficult: 12/14 correct (83%); latency 1.9s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d73\n wait calmly when access to preferred item is denied: 6/8 correct (76%); latency 2.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n ordering in a restaurant: 13/15 correct (87%); latency 2.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d713\n Tantrum: freq 4, duration 12m total\n ABC (tantrum): A = worksheet task presented; B = refused + pushed materials away; C = task removed for 2 min\n\nSession 5 \u2014 2026-08-10 \u2014 52 min \u2014 1 observer\n sounds out CVC words: 11/11 correct (97%); latency 1.6s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d79\n dressing (pants, shirt): 11/11 correct (96%); latency 1.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n requesting help when a task is difficult: 7/8 correct (85%); latency 1.9s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n wait calmly when access to preferred item is denied: 10/15 correct (70%); latency 3.0s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d78\n ordering in a restaurant: 9/10 correct (87%); latency 2.3s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n Tantrum: freq 2, duration 6m total\n\nSession 6 \u2014 2026-08-12 \u2014 IOA SESSION \u2014 2 observers\n sounds out CVC words: 95% (primary); IOA 89% agreement\n dressing (pants, shirt): 91% (primary); IOA 89% agreement\n requesting help when a task is difficult: 88% (primary); IOA 89% agreement\n wait calmly when access to preferred item is denied: 72% (primary); IOA 89% agreement\n ordering in a restaurant: 88% (primary); IOA 89% agreement\n Tantrum: freq 2, duration 4m total; IOA 89% agreement\n\nSession 7 \u2014 2026-08-14 \u2014 52 min \u2014 1 observer\n sounds out CVC words: 8/8 correct (98%); latency 1.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n dressing (pants, shirt): 12/13 correct (90%); latency 2.2s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n requesting help when a task is difficult: 8/10 correct (82%); latency 2.2s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n wait calmly when access to preferred item is denied: 9/13 correct (68%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d710\n ordering in a restaurant: 12/13 correct (93%); latency 1.8s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d79\n Tantrum: freq 3, duration 6m total\n\nSession 8 \u2014 2026-08-16 \u2014 52 min \u2014 1 observer\n sounds out CVC words: 8/8 correct (98%); latency 1.4s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n dressing (pants, shirt): 9/10 correct (94%); latency 1.6s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n requesting help when a task is difficult: 8/10 correct (83%); latency 2.2s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d72\n wait calmly when access to preferred item is denied: 8/12 correct (67%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d77\n ordering in a restaurant: 13/14 correct (94%); latency 1.7s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n Tantrum: freq 3, duration 9m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Stereotypic behavior during inter-trial intervals\n- Playing with non-task materials\n- Delayed responding (>5 seconds consistently)\n- Looking away during SD presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (89%\u201398%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Behavior Function Hypothesis\nTantrum: escape\n Evidence: ABC events in the log support the escape function; behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 8 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 95.2%.\n- Trend direction: upward (first session: 89%, last session: 98%).\n- Tantrum: mean 2.6/session (early-window mean 2.5 -> late-window mean 3.0).\n- IOA data: 89% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "34677ea7e560603b", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {"Tantrum": "escape"}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "adolescent", "n_sessions": 8, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["tantrum"], "behavior_functions": ["escape"], "has_abc_data": true, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "52515"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a systematic desensitization / toleration program for the following.\n\nSkill: tolerating showering assistance\nCurriculum: AFLS Basic Living Skills\nLearner Level: Adult Learner\nBaseline: Mastered at current level\n\nThe learner currently refuses or exhibits safety behaviors during the activity; the program should build tolerance gradually."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating showering assistance\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Mastered at current level\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for showering / bathing performed with caregiver assistance through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nfull assisted shower routine completed without refusal, exiting the shower, or safety behaviors\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. Stand in shower for 30 seconds with water off\n2. Tolerate 10 seconds of water on body\n3. Tolerate 30 seconds of water on body\n4. Tolerate soap application to torso\n5. Tolerate full body wash by caregiver\n6. Full assisted shower routine\n\nCurrent shaping step: At the mastered stage, begin at shaping step 5 (\"Tolerate full body wash by caregiver\") and advance through step 6 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal activity tolerated across 2 different settings (e.g., home and clinic) across 2 consecutive weeks without safety behaviors.\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 2 different settings and with 3 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "31946abf0054cd39", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating showering assistance", "program_type": "toleration", "learner_profile": "adult", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating showering assistance", "module": "basic_living", "mastery_criterion": "mc_toleration_settings", "shaping_n_steps": 6}, "teacher_model": null, "seed_tag": "80658"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9497\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Reading + Social Behavior\nDate range: Sessions 1\u201310 across 20 days (2026-08-10 to 2026-08-30)\n\nACCELERATION PROGRAMS\n1. reads 10\u201320 sight words (Reading)\n Method: DTT\n2. identifies numerals 1\u201320 (Math)\n Method: DTT\n3. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n4. takes turns during structured activities (Social Behavior)\n Method: PRT\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-10 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 12/14 correct (83%); latency 2.0s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d710\n identifies numerals 1\u201320: 9/12 correct (78%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/12 correct (83%); latency 2.3s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d74\n takes turns during structured activities: 13/15 correct (87%); latency 2.3s; prompts FP\u00d71, PP\u00d74, G\u00d75, I\u00d75\n\nSession 2 \u2014 2026-08-12 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 5/13 correct (35%); latency 4.5s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d74\n identifies numerals 1\u201320: 4/8 correct (46%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (41%); latency 4.2s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d74\n takes turns during structured activities: 4/13 correct (33%); latency 4.3s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d79\n\nSession 3 \u2014 2026-08-14 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 7/9 correct (79%); latency 2.3s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n identifies numerals 1\u201320: 11/14 correct (78%); latency 2.3s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d710\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/9 correct (78%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n takes turns during structured activities: 12/15 correct (82%); latency 2.1s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d712\n\nSession 4 \u2014 2026-08-16 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 3/8 correct (41%); latency 4.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n identifies numerals 1\u201320: 6/15 correct (42%); latency 4.1s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/14 correct (44%); latency 3.7s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d710\n takes turns during structured activities: 5/13 correct (36%); latency 4.4s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d78\n\nSession 5 \u2014 2026-08-18 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 8/11 correct (77%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n identifies numerals 1\u201320: 11/15 correct (76%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d713\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/12 correct (81%); latency 2.2s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d71\n takes turns during structured activities: 9/11 correct (82%); latency 2.1s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n\nSession 6 \u2014 2026-08-20 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 3/9 correct (35%); latency 4.4s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n identifies numerals 1\u201320: 3/8 correct (37%); latency 4.4s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (40%); latency 4.5s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n takes turns during structured activities: 4/11 correct (35%); latency 4.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d710\n\nSession 7 \u2014 2026-08-22 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 10/12 correct (84%); latency 1.9s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n identifies numerals 1\u201320: 9/12 correct (73%); latency 2.8s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 11/14 correct (77%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d77\n takes turns during structured activities: 7/9 correct (80%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d72\n\nSession 8 \u2014 2026-08-24 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 5/13 correct (41%); latency 3.9s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d75\n identifies numerals 1\u201320: 5/13 correct (41%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/11 correct (47%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n takes turns during structured activities: 5/14 correct (34%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d79\n\nSession 9 \u2014 2026-08-26 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 11/15 correct (76%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d711\n identifies numerals 1\u201320: 6/8 correct (80%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 13/15 correct (84%); latency 2.1s; prompts FP\u00d71, PP\u00d74, G\u00d75, I\u00d75\n takes turns during structured activities: 10/12 correct (79%); latency 2.3s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d78\n\nSession 10 \u2014 2026-08-28 \u2014 41 min \u2014 1 observer\n reads 10\u201320 sight words: 6/14 correct (41%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d710\n identifies numerals 1\u201320: 4/9 correct (43%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/11 correct (39%); latency 4.0s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n takes turns during structured activities: 3/8 correct (41%); latency 4.1s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Stereotypic behavior during inter-trial intervals\n- Playing with non-task materials\n- Echolalic responding (repeating SD rather than answering)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 59.1%.\n- Trend direction: downward (first session: 83%, last session: 41%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "2897dfede0e9df01", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "school_age", "n_sessions": 10, "n_programs": 4, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "14320"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7060\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Mand + Tact + Writing\nDate range: Sessions 1\u20136 across 12 days (2026-06-23 to 2026-07-05)\n\nACCELERATION PROGRAMS\n1. copies simple words from model (Writing)\n Method: DTT\n2. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n3. indicating completion ('all done', 'finished') (Mand)\n Method: NET\n4. tacts colors of objects (Tact)\n Method: DTT\n5. tacts common objects (Tact)\n Method: DTT\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-23 \u2014 42 min \u2014 1 observer\n copies simple words from model: 3/10 correct (30%); latency 4.5s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 2/8 correct (24%); latency 4.7s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n indicating completion ('all done', 'finished'): 2/8 correct (29%); latency 4.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n tacts colors of objects: 3/9 correct (31%); latency 4.8s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n tacts common objects: 2/10 correct (25%); latency 4.7s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d78\n\nSession 2 \u2014 2026-06-25 \u2014 42 min \u2014 1 observer\n copies simple words from model: 3/9 correct (37%); latency 4.2s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 2/8 correct (31%); latency 4.6s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n indicating completion ('all done', 'finished'): 3/8 correct (39%); latency 4.5s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n tacts colors of objects: 6/14 correct (40%); latency 4.1s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d76\n tacts common objects: 3/9 correct (37%); latency 4.4s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d76\n\nSession 3 \u2014 2026-06-27 \u2014 42 min \u2014 1 observer\n copies simple words from model: 6/13 correct (44%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/14 correct (47%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d77\n indicating completion ('all done', 'finished'): 4/9 correct (46%); latency 4.0s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d73\n tacts colors of objects: 7/15 correct (49%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d78\n tacts common objects: 4/8 correct (45%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n\nSession 4 \u2014 2026-06-29 \u2014 42 min \u2014 1 observer\n copies simple words from model: 8/15 correct (54%); latency 3.3s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d713\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/9 correct (59%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n indicating completion ('all done', 'finished'): 9/15 correct (58%); latency 3.1s; prompts FP\u00d75, PP\u00d74, G\u00d72, I\u00d74\n tacts colors of objects: 4/8 correct (55%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n tacts common objects: 5/9 correct (54%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n\nSession 5 \u2014 2026-07-01 \u2014 42 min \u2014 1 observer\n copies simple words from model: 9/14 correct (66%); latency 2.9s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d79\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 10/14 correct (70%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d78\n indicating completion ('all done', 'finished'): 9/14 correct (68%); latency 3.0s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d77\n tacts colors of objects: 6/9 correct (64%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n tacts common objects: 6/10 correct (58%); latency 3.2s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d75\n\nSession 6 \u2014 2026-07-03 \u2014 42 min \u2014 1 observer\n copies simple words from model: 6/8 correct (73%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 11/13 correct (82%); latency 2.6s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n indicating completion ('all done', 'finished'): 7/9 correct (78%); latency 2.7s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n tacts colors of objects: 7/10 correct (72%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d74\n tacts common objects: 6/9 correct (71%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Reaching for materials proactively\n- Smiling during reinforcement delivery\n- Eye contact maintained throughout trials\n- Requesting more trials verbally"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 30% to 73% across 6 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nlow\n\nInsufficient data: only 6 sessions, high variance, and/or no IOA evidence. Recommend additional data collection before programming changes.\n\n## Data-Supported Rationale\n- Mean accuracy across 6 sessions: 50.8%.\n- Trend direction: upward (first session: 30%, last session: 73%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "c4bfb12d30859ea1", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "low", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "early", "n_sessions": 6, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "71683"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6315\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Reading + Tolerating Denied Access\nDate range: Sessions 1\u201311 across 22 days (2026-02-01 to 2026-02-23)\n\nACCELERATION PROGRAMS\n1. counts objects 1\u201320 (Math)\n Method: DTT\n2. requesting preferred items using AAC device (e.g., \"I want cookie please\") (Mand)\n Method: NET\n3. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n4. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n5. reads 10\u201320 sight words (Reading)\n Method: DTT\n\nDECELERATION TARGETS\n1. Fecal smearing (scatolia) \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-01 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 10/14 correct (73%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d710\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/12 correct (70%); latency 2.7s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d73\n wait calmly when access to preferred item is denied: 9/11 correct (78%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 12/14 correct (86%); latency 1.9s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n reads 10\u201320 sight words: 8/10 correct (81%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n Fecal smearing (scatolia): attempts 0\n\nSession 2 \u2014 2026-02-03 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 11/15 correct (73%); latency 2.7s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d710\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 9/13 correct (68%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d74\n wait calmly when access to preferred item is denied: 10/14 correct (72%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/9 correct (80%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n reads 10\u201320 sight words: 9/11 correct (81%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d76\n Fecal smearing (scatolia): attempts 2 (1 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 3 \u2014 2026-02-05 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 10/15 correct (65%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d78\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 6/10 correct (62%); latency 3.5s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d76\n wait calmly when access to preferred item is denied: 8/12 correct (70%); latency 2.6s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d72\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/8 correct (69%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 5/8 correct (66%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n Fecal smearing (scatolia): attempts 2 (0 intercepted \u2014 staff redirected before smearing; 2 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 4 \u2014 2026-02-07 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 5/8 correct (58%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/15 correct (51%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d712\n wait calmly when access to preferred item is denied: 8/13 correct (58%); latency 3.3s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/10 correct (65%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n reads 10\u201320 sight words: 9/15 correct (61%); latency 3.1s; prompts FP\u00d75, PP\u00d70, G\u00d72, I\u00d78\n Fecal smearing (scatolia): attempts 3 (2 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 5 \u2014 2026-02-09 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 8/14 correct (55%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d79\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 5/10 correct (52%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n wait calmly when access to preferred item is denied: 5/10 correct (54%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/9 correct (60%); latency 3.5s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d76\n reads 10\u201320 sight words: 8/14 correct (56%); latency 3.7s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d710\n Fecal smearing (scatolia): attempts 3 (3 intercepted \u2014 staff redirected before smearing; 0 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 6 \u2014 2026-02-11 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 5/10 correct (50%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d76\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 4/11 correct (37%); latency 4.6s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n wait calmly when access to preferred item is denied: 3/8 correct (43%); latency 4.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/10 correct (47%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n reads 10\u201320 sight words: 5/11 correct (43%); latency 4.1s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d78\n Fecal smearing (scatolia): attempts 4 (4 intercepted \u2014 staff redirected before smearing; 0 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 7 \u2014 2026-02-13 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 5/11 correct (41%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 4/13 correct (34%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d77\n wait calmly when access to preferred item is denied: 6/13 correct (44%); latency 4.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d712\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/10 correct (48%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n reads 10\u201320 sight words: 5/15 correct (36%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d78\n Fecal smearing (scatolia): attempts 4 (3 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 8 \u2014 2026-02-15 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 6/15 correct (43%); latency 4.0s; prompts FP\u00d75, PP\u00d72, G\u00d74, I\u00d74\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 3/9 correct (32%); latency 4.7s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n wait calmly when access to preferred item is denied: 3/12 correct (29%); latency 4.7s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/12 correct (39%); latency 4.4s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d77\n reads 10\u201320 sight words: 4/14 correct (27%); latency 4.6s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d78\n Fecal smearing (scatolia): attempts 6 (2 intercepted \u2014 staff redirected before smearing; 4 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 9 \u2014 2026-02-17 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 3/9 correct (32%); latency 4.7s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 3/11 correct (23%); latency 5.0s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d79\n wait calmly when access to preferred item is denied: 3/9 correct (30%); latency 4.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/13 correct (31%); latency 4.4s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d73\n reads 10\u201320 sight words: 3/10 correct (28%); latency 4.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n Fecal smearing (scatolia): attempts 6 (2 intercepted \u2014 staff redirected before smearing; 4 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 10 \u2014 2026-02-19 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 3/11 correct (30%); latency 4.7s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d75\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 2/14 correct (12%); latency 5.7s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d79\n wait calmly when access to preferred item is denied: 2/8 correct (21%); latency 5.0s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 3/9 correct (31%); latency 4.7s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n reads 10\u201320 sight words: 1/8 correct (14%); latency 5.6s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n Fecal smearing (scatolia): attempts 6 (4 intercepted \u2014 staff redirected before smearing; 2 completed \u2014 feces transferred to skin, clothing, or surface)\n\nSession 11 \u2014 2026-02-21 \u2014 47 min \u2014 1 observer\n counts objects 1\u201320: 3/10 correct (29%); latency 4.8s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d73\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 1/13 correct (10%); latency 5.7s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d710\n wait calmly when access to preferred item is denied: 1/12 correct (10%); latency 5.4s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 2/9 correct (17%); latency 5.4s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n reads 10\u201320 sight words: 1/9 correct (13%); latency 5.2s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n Fecal smearing (scatolia): attempts 8 (5 intercepted \u2014 staff redirected before smearing; 3 completed \u2014 feces transferred to skin, clothing, or surface)\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Self-stimulatory behavior increase during demand periods\n- Crying during demand presentation\n- Peer aggression (hitting or pushing peers during group activities)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (73% -> 29%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nFecal smearing (scatolia): attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 50.0%.\n- Trend direction: downward (first session: 73%, last session: 29%).\n- Fecal smearing (scatolia): mean 4.0/session (early-window mean 1.3 -> late-window mean 6.7).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "cb45405ddd8fc072", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Fecal smearing (scatolia)": "attention"}, "escalation_level": 4, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "school_age", "n_sessions": 11, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["fecal_smearing"], "behavior_functions": ["attention"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "7707"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6399\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math\nDate range: Sessions 1\u201310 across 20 days (2026-05-14 to 2026-06-03)\n\nACCELERATION PROGRAMS\n1. single-word requests for preferred items (Mand)\n Method: NET\n2. identifies numerals 1\u201320 (Math)\n Method: DTT\n3. mands for missing items needed to complete an activity (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Verbal aggression \u2014 function hypothesized: attention\n2. Property destruction \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-14 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 4/8 correct (55%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n identifies numerals 1\u201320: 10/15 correct (64%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d76\n mands for missing items needed to complete an activity: 9/13 correct (68%); latency 2.9s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d76\n Verbal aggression: freq 2\n Property destruction: freq 2\n\nSession 2 \u2014 2026-05-16 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 6/10 correct (56%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d76\n identifies numerals 1\u201320: 10/15 correct (67%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d75, I\u00d78\n mands for missing items needed to complete an activity: 8/10 correct (77%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d77\n Verbal aggression: freq 3\n Property destruction: freq 1\n ABC (property destruction): A = staff engaged in paperwork nearby; B = yelled name + tapped staff; C = staff attended and redirected\n\nSession 3 \u2014 2026-05-18 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 7/13 correct (58%); latency 3.2s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d76\n identifies numerals 1\u201320: 9/15 correct (63%); latency 2.9s; prompts FP\u00d74, PP\u00d75, G\u00d71, I\u00d75\n mands for missing items needed to complete an activity: 7/10 correct (74%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n Verbal aggression: freq 3\n Property destruction: freq 1\n\nSession 4 \u2014 2026-05-20 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 5/8 correct (60%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n identifies numerals 1\u201320: 9/13 correct (69%); latency 2.8s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d78\n mands for missing items needed to complete an activity: 10/13 correct (74%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d79\n Verbal aggression: freq 2\n Property destruction: freq 1\n\nSession 5 \u2014 2026-05-22 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 3/12 correct (24%); latency 5.2s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d77\n identifies numerals 1\u201320: 3/10 correct (29%); latency 4.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n mands for missing items needed to complete an activity: 4/10 correct (43%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n Verbal aggression: freq 7\n Property destruction: freq 3\n\nSession 6 \u2014 2026-05-24 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 4/11 correct (34%); latency 4.8s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d76\n identifies numerals 1\u201320: 3/9 correct (38%); latency 4.2s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n mands for missing items needed to complete an activity: 5/10 correct (50%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n Verbal aggression: freq 7\n Property destruction: freq 3\n\nSession 7 \u2014 2026-05-26 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 3/10 correct (34%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n identifies numerals 1\u201320: 5/11 correct (46%); latency 4.1s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d77\n mands for missing items needed to complete an activity: 8/15 correct (54%); latency 3.7s; prompts FP\u00d75, PP\u00d71, G\u00d70, I\u00d79\n Verbal aggression: freq 1\n Property destruction: freq 1\n\nSession 8 \u2014 2026-05-28 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 5/14 correct (35%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d710\n identifies numerals 1\u201320: 6/12 correct (54%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d79\n mands for missing items needed to complete an activity: 6/9 correct (64%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n Verbal aggression: freq 2\n Property destruction: freq 2\n\nSession 9 \u2014 2026-05-30 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 3/9 correct (36%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n identifies numerals 1\u201320: 6/10 correct (57%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n mands for missing items needed to complete an activity: 9/13 correct (69%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d72\n Verbal aggression: freq 2\n Property destruction: freq 1\n\nSession 10 \u2014 2026-06-01 \u2014 45 min \u2014 1 observer\n single-word requests for preferred items: 5/13 correct (38%); latency 4.4s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d75\n identifies numerals 1\u201320: 8/13 correct (65%); latency 2.8s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d73\n mands for missing items needed to complete an activity: 9/13 correct (71%); latency 2.8s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d79\n Verbal aggression: freq 3\n Property destruction: freq 1\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Stereotypic behavior during inter-trial intervals\n- Playing with non-task materials\n- Delayed responding (>5 seconds consistently)\n- Looking away during SD presentation\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Behavior Function Hypothesis\nVerbal aggression: attention\n Evidence: ABC events in the log support the attention function; behavior occurs during low-attention periods and results in social attention contingently.\nProperty destruction: attention\n Evidence: ABC events in the log support the attention function; behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 43.0%.\n- Trend direction: downward (first session: 55%, last session: 38%).\n- Verbal aggression: mean 3.2/session (early-window mean 2.7 -> late-window mean 2.3).\n- Property destruction: mean 1.6/session (early-window mean 1.3 -> late-window mean 1.3).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "809984a13faeceb2", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {"Verbal aggression": "attention", "Property destruction": "attention"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "school_age", "n_sessions": 10, "n_programs": 3, "n_behaviors": 2, "behavior_ids": ["verbal_aggression", "property_destruction"], "behavior_functions": ["attention", "attention"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "70412"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: selects items by function from array of 5\u20138\nCurriculum: LRFFC L2\nLearner: Early Learner\nMastery Status: Approaching mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by function from array of 5\u20138\n- Curriculum: LRFFC L2\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: pencil, toothbrush, sock\nDistractor stimuli: car, hat, blanket, phone\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy at independent prompt level across 3 sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "ce083a6f263a2b97", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L2", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by function from array of 5\u20138", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "crf", "error_correction": "four_step", "mastery_criterion": "mc_80_independent"}, "teacher_model": null, "seed_tag": "68189"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: using public transportation\nCurriculum Reference: AFLS Community Participation Skills\nLearner Profile: Adolescent Learner\nCurrent Mastery: Emerging\nTeaching Method: Task Analysis / Chaining\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: using public transportation\n- Curriculum: AFLS Community Participation Skills\n- Learner: Adolescent Learner\n- Current mastery: Emerging\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Confirm the correct stop or station. <- Learner-taught step (forward chaining starts here)\n2. Purchase or have the fare ready.\n3. Wait at the designated boarding area.\n4. Board the vehicle when it arrives.\n5. Pay the fare or present the pass.\n6. Sit or stand safely.\n7. Monitor the route for the correct stop.\n8. Exit at the correct stop.\n\n## Prompt Strategy Per Step\nStrategy: Most-to-Least\nStart with full-physical prompt at each step; fade to partial physical, gestural, verbal, independent.\nCurrent prompt level: At the emerging stage, use full-physical or partial-physical prompts at each step; fade systematically.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "c43b29c3d4774850", "gold_labels": {"method": "task_analysis", "domain": "AFLS.community", "skill": "using public transportation", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "emerging", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "using public transportation", "module": "community", "mastery_criterion": "mc_self_initiation", "chain_type": "forward", "prompt_strategy": "most_to_least", "reinforcement_schedule": "crf_per_step", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "44637"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a chaining program for the following.\n\nSkill: clocking in at start of shift\nCurriculum: AFLS Vocational Skills\nLearner Level: Adolescent Learner\nBaseline: Developing\n\nInclude the full Task Analysis structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: clocking in at start of shift\n- Curriculum: AFLS Vocational Skills\n- Learner: Adolescent Learner\n- Current mastery: Developing\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Arrive at the workplace by the scheduled time.\n2. Locate the time clock or digital system.\n3. Enter identification (ID card / badge / code).\n4. Confirm the clock-in timestamp.\n5. Notify the supervisor or check the day's task list.\n6. Proceed to the assigned workstation.\n\n## Prompt Strategy Per Step\nStrategy: Graduated Guidance\nHand-over-hand physical guidance with fading pressure; move to shadow, then independent.\nCurrent prompt level: At the developing stage, provide hand-over-hand guidance at each step; reduce physical pressure across sessions.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "3b6c16bcd5e4e7ea", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "clocking in at start of shift", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "developing", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "clocking in at start of shift", "module": "vocational", "mastery_criterion": "mc_self_initiation", "chain_type": "total_task", "prompt_strategy": "graduated_guidance", "reinforcement_schedule": "crf_per_step", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "98892"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: answers social questions (How are you?)\nCurriculum: Intraverbal L2\nLearner: School-Age Learner\nMastery Status: Near mastery\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: answers social questions (How are you?)\n- Curriculum: Intraverbal L2\n- Learner: School-Age Learner\n- Current mastery: Near mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: transition conversation.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's transition conversation routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the near mastery stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "7d7a50e3c6fd4134", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L2", "learner_profile": "school_age", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "answers social questions (How are you?)", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "83467"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: tracks print left to right\nCurriculum: Reading L1\nLearner: Early Learner\nMastery Status: Near mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tracks print left to right\n- Curriculum: Reading L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What letter is this?\"\nVariations: \"Read this letter\"; \"What does this say?\"\nPresentation: Present the letter or word on a flashcard.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: spoon, apple, pencil\nDistractor stimuli: ball, block\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy across 2 consecutive sessions with at least 10 trials each.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "421660d3a275008b", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tracks print left to right", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "fr2", "error_correction": "simple_correction", "mastery_criterion": "mc_80_2sessions"}, "teacher_model": null, "seed_tag": "36112"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5742\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Home Skills + Mand + Self-Care + Writing\nDate range: Sessions 1\u201312 across 24 days (2026-01-01 to 2026-01-25)\n\nACCELERATION PROGRAMS\n1. brushing teeth independently (Self-Care)\n Method: Task Analysis\n2. washing hands independently (Self-Care)\n Method: Task Analysis\n3. requesting preferred items using AAC device (Mand)\n Method: NET\n4. making the bed (Home Skills)\n Method: Task Analysis\n5. copies simple words from model (Writing)\n Method: DTT\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: escape\n2. Motor stereotypy \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-01 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 7/13 correct (57%); latency 3.5s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d79\n washing hands independently: 4/9 correct (49%); latency 4.0s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n requesting preferred items using AAC device: 6/9 correct (65%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n making the bed: 4/12 correct (37%); latency 4.5s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d77\n copies simple words from model: 4/10 correct (45%); latency 3.7s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n Self-injurious behavior (SIB): freq 4\n Motor stereotypy: freq 5; PIR 34%\n\nSession 2 \u2014 2026-01-03 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 4/9 correct (48%); latency 3.9s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d73\n washing hands independently: 7/9 correct (77%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d72\n requesting preferred items using AAC device: 5/10 correct (53%); latency 3.6s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n making the bed: 5/8 correct (68%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n copies simple words from model: 10/14 correct (73%); latency 2.6s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d710\n Self-injurious behavior (SIB): freq 5\n Motor stereotypy: freq 4; PIR 27%\n\nSession 3 \u2014 2026-01-05 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 6/11 correct (52%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n washing hands independently: 4/11 correct (40%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n requesting preferred items using AAC device: 10/13 correct (74%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d78\n making the bed: 3/8 correct (42%); latency 4.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n copies simple words from model: 5/8 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n Self-injurious behavior (SIB): freq 3\n Motor stereotypy: freq 4; PIR 20%\n\nSession 4 \u2014 2026-01-07 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 5/8 correct (66%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n washing hands independently: 7/9 correct (75%); latency 2.6s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n requesting preferred items using AAC device: 5/8 correct (61%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n making the bed: 8/13 correct (62%); latency 3.5s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d76\n copies simple words from model: 7/12 correct (61%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d711\n Self-injurious behavior (SIB): freq 6\n Motor stereotypy: freq 6; PIR 36%\n\nSession 5 \u2014 2026-01-09 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 5/11 correct (45%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n washing hands independently: 10/15 correct (69%); latency 3.1s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d78\n requesting preferred items using AAC device: 12/15 correct (78%); latency 2.7s; prompts FP\u00d75, PP\u00d74, G\u00d71, I\u00d75\n making the bed: 6/8 correct (76%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n copies simple words from model: 5/9 correct (60%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n Self-injurious behavior (SIB): freq 3\n Motor stereotypy: freq 2; PIR 15%\n\nSession 6 \u2014 2026-01-11 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 9/15 correct (63%); latency 3.0s; prompts FP\u00d74, PP\u00d75, G\u00d75, I\u00d71\n washing hands independently: 11/14 correct (79%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d77\n requesting preferred items using AAC device: 6/12 correct (50%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d77\n making the bed: 4/9 correct (49%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n copies simple words from model: 6/15 correct (41%); latency 4.3s; prompts FP\u00d75, PP\u00d74, G\u00d70, I\u00d76\n Self-injurious behavior (SIB): freq 4\n Motor stereotypy: freq 5; PIR 29%\n\nSession 7 \u2014 2026-01-13 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 6/11 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n washing hands independently: 6/11 correct (56%); latency 3.7s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n requesting preferred items using AAC device: 7/15 correct (50%); latency 3.7s; prompts FP\u00d70, PP\u00d75, G\u00d71, I\u00d79\n making the bed: 5/8 correct (57%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n copies simple words from model: 6/9 correct (61%); latency 3.1s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n Self-injurious behavior (SIB): freq 7\n Motor stereotypy: freq 1; PIR 10%\n\nSession 8 \u2014 2026-01-15 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 6/8 correct (74%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n washing hands independently: 4/8 correct (52%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n requesting preferred items using AAC device: 10/13 correct (73%); latency 2.7s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d711\n making the bed: 10/13 correct (74%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d76\n copies simple words from model: 5/14 correct (36%); latency 4.4s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d79\n Self-injurious behavior (SIB): freq 7\n Motor stereotypy: freq 3; PIR 15%\n\nSession 9 \u2014 2026-01-17 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 8/10 correct (77%); latency 2.6s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n washing hands independently: 6/9 correct (71%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n requesting preferred items using AAC device: 12/15 correct (81%); latency 2.3s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d78\n making the bed: 7/11 correct (66%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n copies simple words from model: 9/13 correct (68%); latency 3.1s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d79\n Self-injurious behavior (SIB): freq 4\n Motor stereotypy: freq 3; PIR 21%\n\nSession 10 \u2014 2026-01-19 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 8/15 correct (54%); latency 3.3s; prompts FP\u00d70, PP\u00d75, G\u00d72, I\u00d78\n washing hands independently: 6/14 correct (40%); latency 4.5s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d710\n requesting preferred items using AAC device: 8/12 correct (70%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d711\n making the bed: 8/12 correct (68%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d75\n copies simple words from model: 6/10 correct (64%); latency 3.1s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n Self-injurious behavior (SIB): freq 6\n Motor stereotypy: freq 1; PIR 12%\n\nSession 11 \u2014 2026-01-21 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 8/14 correct (56%); latency 3.6s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d78\n washing hands independently: 8/13 correct (60%); latency 3.5s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n requesting preferred items using AAC device: 9/15 correct (57%); latency 3.4s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d75\n making the bed: 5/11 correct (48%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n copies simple words from model: 7/11 correct (64%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d76\n Self-injurious behavior (SIB): freq 4\n Motor stereotypy: freq 6; PIR 32%\n\nSession 12 \u2014 2026-01-23 \u2014 36 min \u2014 1 observer\n brushing teeth independently: 9/12 correct (76%); latency 2.7s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d77\n washing hands independently: 8/13 correct (59%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d77\n requesting preferred items using AAC device: 6/11 correct (52%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n making the bed: 7/14 correct (51%); latency 4.0s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d75\n copies simple words from model: 8/13 correct (60%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d712\n Self-injurious behavior (SIB): freq 6\n Motor stereotypy: freq 7; PIR 23%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Stereotypic behavior during inter-trial intervals\n- Delayed responding (>5 seconds consistently)\n- Echolalic responding (repeating SD rather than answering)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 67% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\nMotor stereotypy: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 60.1%.\n- Trend direction: upward (first session: 57%, last session: 76%).\n- Self-injurious behavior (SIB): mean 4.9/session (early-window mean 4.5 -> late-window mean 5.0).\n- Motor stereotypy: mean 3.9/session (early-window mean 4.8 -> late-window mean 4.2).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "2355d4a3a0e38e8e", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {"Self-injurious behavior (SIB)": "escape", "Motor stereotypy": "automatic"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "adolescent", "n_sessions": 12, "n_programs": 5, "n_behaviors": 2, "behavior_ids": ["sib", "motor_stereotypy"], "behavior_functions": ["escape", "automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "90253"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: clocking in at start of shift\nCurriculum: AFLS Vocational Skills\nLearner: Adolescent Learner\nMastery Status: Approaching mastery\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: clocking in at start of shift\n- Curriculum: AFLS Vocational Skills\n- Learner: Adolescent Learner\n- Current mastery: Approaching mastery\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Arrive at the workplace by the scheduled time.\n2. Locate the time clock or digital system.\n3. Enter identification (ID card / badge / code).\n4. Confirm the clock-in timestamp.\n5. Notify the supervisor or check the day's task list.\n6. Proceed to the assigned workstation.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the approaching mastery stage, use partial-physical or gestural prompts only at steps where errors occur; allow independence elsewhere.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 60s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "5495eb32df5b6db1", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "clocking in at start of shift", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "approaching", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "clocking in at start of shift", "module": "vocational", "mastery_criterion": "mc_fluent_chain", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "crf_per_step", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "80658"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a systematic desensitization / toleration program for the following.\n\nSkill: tolerating nail clipping\nCurriculum: AFLS Basic Living Skills\nLearner Level: Adolescent Learner\nBaseline: Emerging\n\nThe learner currently refuses or exhibits safety behaviors during the activity; the program should build tolerance gradually."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating nail clipping\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adolescent Learner\n- Current mastery: Emerging\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for nail clipping performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nall 10 fingernails (and optionally toenails) clipped by caregiver without refusal, pulling hand away, or safety behaviors\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1 fingernail clipped\n2. 2 fingernails clipped in one sitting\n3. 5 fingernails clipped (one hand)\n4. All 10 fingernails clipped\n5. All 10 fingernails + 10 toenails clipped\n\nCurrent shaping step: At the emerging stage, begin at shaping step 1 (\"1 fingernail clipped\") and advance through step 2 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal activity tolerated across 2 different settings (e.g., home and clinic) across 2 consecutive weeks without safety behaviors.\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 2 different settings and with 2 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "7172ec34fc2688b2", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating nail clipping", "program_type": "toleration", "learner_profile": "adolescent", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating nail clipping", "module": "basic_living", "mastery_criterion": "mc_toleration_settings", "shaping_n_steps": 5}, "teacher_model": null, "seed_tag": "68917"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9345\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Mand + Self-Care + Vocational\nDate range: Sessions 1\u20138 across 16 days (2026-10-20 to 2026-11-05)\n\nACCELERATION PROGRAMS\n1. brushing teeth independently (Self-Care)\n Method: Task Analysis\n2. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n3. doing laundry (Home Skills)\n Method: Task Analysis\n4. requesting assistance using AAC device (Mand)\n Method: NET\n5. washing hands independently (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Non-compliance \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-20 \u2014 55 min \u2014 1 observer\n brushing teeth independently: 7/15 correct (50%); latency 4.0s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d710\n completing assigned tasks in order: 9/15 correct (61%); latency 3.3s; prompts FP\u00d75, PP\u00d74, G\u00d75, I\u00d71\n doing laundry: 7/15 correct (49%); latency 3.9s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d79\n requesting assistance using AAC device: 6/9 correct (65%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n washing hands independently: 6/9 correct (72%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n Non-compliance: freq 2\n\nSession 2 \u2014 2026-10-22 \u2014 55 min \u2014 1 observer\n brushing teeth independently: 4/8 correct (53%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n completing assigned tasks in order: 9/13 correct (70%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d74\n doing laundry: 7/13 correct (51%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d75\n requesting assistance using AAC device: 7/10 correct (66%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n washing hands independently: 7/10 correct (72%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d77\n Non-compliance: freq 2\n\nSession 3 \u2014 2026-10-24 \u2014 55 min \u2014 1 observer\n brushing teeth independently: 8/14 correct (59%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d78\n completing assigned tasks in order: 10/13 correct (74%); latency 2.8s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d73\n doing laundry: 7/12 correct (58%); latency 3.2s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d74\n requesting assistance using AAC device: 9/13 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d76\n washing hands independently: 9/13 correct (71%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n Non-compliance: freq 11\n\nSession 4 \u2014 2026-10-26 \u2014 55 min \u2014 1 observer\n brushing teeth independently: 8/15 correct (55%); latency 3.8s; prompts FP\u00d75, PP\u00d75, G\u00d72, I\u00d73\n completing assigned tasks in order: 10/13 correct (75%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d73\n doing laundry: 9/15 correct (63%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d79\n requesting assistance using AAC device: 6/10 correct (62%); latency 3.5s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n washing hands independently: 9/13 correct (69%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d710\n Non-compliance: freq 11\n\nSession 5 \u2014 2026-10-28 \u2014 55 min \u2014 1 observer\n brushing teeth independently: 8/13 correct (64%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d77\n completing assigned tasks in order: 7/9 correct (74%); latency 2.4s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n doing laundry: 6/9 correct (66%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n requesting assistance using AAC device: 10/15 correct (66%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d710\n washing hands independently: 10/14 correct (74%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d710\n Non-compliance: freq 3\n\nSession 6 \u2014 2026-10-30 \u2014 55 min \u2014 1 observer\n brushing teeth independently: 7/11 correct (64%); latency 3.2s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n completing assigned tasks in order: 10/14 correct (74%); latency 2.9s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d77\n doing laundry: 5/8 correct (60%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n requesting assistance using AAC device: 10/14 correct (73%); latency 2.5s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n washing hands independently: 9/14 correct (66%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n Non-compliance: freq 3\n\nSession 7 \u2014 2026-11-01 \u2014 55 min \u2014 1 observer\n brushing teeth independently: 7/11 correct (65%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n completing assigned tasks in order: 11/13 correct (82%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d710\n doing laundry: 8/11 correct (70%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n requesting assistance using AAC device: 10/14 correct (71%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d78\n washing hands independently: 8/11 correct (68%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d79\n Non-compliance: freq 2\n\nSession 8 \u2014 2026-11-03 \u2014 55 min \u2014 1 observer\n brushing teeth independently: 10/15 correct (68%); latency 2.8s; prompts FP\u00d75, PP\u00d73, G\u00d74, I\u00d73\n completing assigned tasks in order: 9/11 correct (79%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n doing laundry: 8/11 correct (74%); latency 2.6s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n requesting assistance using AAC device: 10/14 correct (69%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d79\n washing hands independently: 10/14 correct (68%); latency 2.7s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d75\n Non-compliance: freq 4\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Turning away from task or staff\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Peer aggression (hitting or pushing peers during group activities)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nNon-compliance: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 59.7%.\n- Trend direction: upward (first session: 50%, last session: 68%).\n- Non-compliance: mean 4.8/session (early-window mean 2.0 -> late-window mean 3.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "1dd2723d41c62b51", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Non-compliance": "escape"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "adult", "n_sessions": 8, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["non_compliance"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "44994"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: follows conditional instructions (if X, then Y)\nCurriculum Reference: Listener Responding L3\nLearner Profile: School-Age Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: follows conditional instructions (if X, then Y)\n- Curriculum: Listener Responding L3\n- Learner: School-Age Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: plate, brush, glue\nDistractor stimuli: cup, sock, pencil, block, apple\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nToken economy \u2014 Tokens delivered per correct response; exchanged at session end for a back-up reinforcer appropriate to the learner (for children: candy, cookies, brief leisure-time access, preferred activity, screen time, or a favorite sensory item). Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "fbbd06b71b7c164e", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L3", "learner_profile": "school_age", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "follows conditional instructions (if X, then Y)", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "token_economy", "error_correction": "backstep", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "92219"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: spontaneously requests desired items without prompts\nCurriculum: Spontaneous Vocal Behavior L1\nLearner: Early Learner\nMastery Status: Emerging\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously requests desired items without prompts\n- Curriculum: Spontaneous Vocal Behavior L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: room transition.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's room transition routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the emerging stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "7483c51436980328", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously requests desired items without prompts", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "46838"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: matches colors (identical chips)\nCurriculum Reference: Visual Perceptual Skills & Matching-to-Sample L1\nLearner Profile: Early Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: matches colors (identical chips)\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: red, blue, orange\nDistractor stimuli: green, white\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "44e8d61847443e95", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "matches colors (identical chips)", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "crf", "error_correction": "backstep", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "35263"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6948\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Listener Responding + Mand + Tolerating Denied Access\nDate range: Sessions 1\u201311 across 22 days (2026-02-13 to 2026-03-07)\n\nACCELERATION PROGRAMS\n1. selects items by feature (Listener Responding)\n Method: DTT\n2. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n3. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n4. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n5. indicating completion ('all done', 'finished') (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-13 \u2014 35 min \u2014 1 observer\n selects items by feature: 8/10 correct (82%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/10 correct (91%); latency 1.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n answers WH-questions about familiar topics: 10/12 correct (80%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n wait calmly when access to preferred item is denied: 8/11 correct (74%); latency 2.4s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n indicating completion ('all done', 'finished'): 7/9 correct (82%); latency 2.3s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n\nSession 2 \u2014 2026-02-15 \u2014 35 min \u2014 1 observer\n selects items by feature: 5/14 correct (36%); latency 4.3s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (42%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n answers WH-questions about familiar topics: 6/15 correct (42%); latency 3.9s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d77\n wait calmly when access to preferred item is denied: 4/11 correct (37%); latency 4.5s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d78\n indicating completion ('all done', 'finished'): 5/15 correct (31%); latency 4.6s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d79\n\nSession 3 \u2014 2026-02-17 \u2014 35 min \u2014 1 observer\n selects items by feature: 9/11 correct (81%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/9 correct (87%); latency 2.2s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n answers WH-questions about familiar topics: 8/10 correct (78%); latency 2.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n wait calmly when access to preferred item is denied: 11/15 correct (75%); latency 2.8s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d712\n indicating completion ('all done', 'finished'): 8/10 correct (77%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n\nSession 4 \u2014 2026-02-19 \u2014 35 min \u2014 1 observer\n selects items by feature: 6/13 correct (45%); latency 4.3s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/12 correct (36%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d78\n answers WH-questions about familiar topics: 4/11 correct (40%); latency 4.1s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n wait calmly when access to preferred item is denied: 6/14 correct (41%); latency 4.5s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d77\n indicating completion ('all done', 'finished'): 3/11 correct (31%); latency 4.5s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n\nSession 5 \u2014 2026-02-21 \u2014 IOA SESSION \u2014 2 observers\n selects items by feature: 83% (primary); IOA 89% agreement\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 88% (primary); IOA 89% agreement\n answers WH-questions about familiar topics: 82% (primary); IOA 89% agreement\n wait calmly when access to preferred item is denied: 81% (primary); IOA 89% agreement\n indicating completion ('all done', 'finished'): 78% (primary); IOA 89% agreement\n\nSession 6 \u2014 2026-02-23 \u2014 35 min \u2014 1 observer\n selects items by feature: 4/9 correct (44%); latency 3.9s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d72\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/15 correct (34%); latency 4.3s; prompts FP\u00d70, PP\u00d73, G\u00d75, I\u00d77\n answers WH-questions about familiar topics: 4/9 correct (42%); latency 4.0s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n wait calmly when access to preferred item is denied: 4/9 correct (44%); latency 4.3s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n indicating completion ('all done', 'finished'): 3/10 correct (27%); latency 4.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d78\n\nSession 7 \u2014 2026-02-25 \u2014 35 min \u2014 1 observer\n selects items by feature: 6/8 correct (81%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 11/14 correct (82%); latency 2.6s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d78\n answers WH-questions about familiar topics: 10/13 correct (75%); latency 2.9s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d75\n wait calmly when access to preferred item is denied: 9/12 correct (79%); latency 2.6s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d78\n indicating completion ('all done', 'finished'): 8/11 correct (74%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n\nSession 8 \u2014 2026-02-27 \u2014 35 min \u2014 1 observer\n selects items by feature: 5/13 correct (37%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d710\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/15 correct (38%); latency 4.1s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d710\n answers WH-questions about familiar topics: 5/10 correct (49%); latency 3.9s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n wait calmly when access to preferred item is denied: 5/14 correct (35%); latency 4.3s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d78\n indicating completion ('all done', 'finished'): 3/10 correct (29%); latency 4.5s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n\nSession 9 \u2014 2026-03-01 \u2014 35 min \u2014 1 observer\n selects items by feature: 13/15 correct (85%); latency 1.9s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/10 correct (91%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n answers WH-questions about familiar topics: 7/9 correct (78%); latency 2.4s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d75\n wait calmly when access to preferred item is denied: 9/11 correct (78%); latency 2.3s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d74\n indicating completion ('all done', 'finished'): 7/10 correct (75%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d74\n\nSession 10 \u2014 2026-03-03 \u2014 35 min \u2014 1 observer\n selects items by feature: 4/10 correct (41%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (37%); latency 4.5s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d74\n answers WH-questions about familiar topics: 7/14 correct (47%); latency 4.0s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d74\n wait calmly when access to preferred item is denied: 6/15 correct (43%); latency 4.2s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d79\n indicating completion ('all done', 'finished'): 3/9 correct (31%); latency 4.3s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d77\n\nSession 11 \u2014 2026-03-05 \u2014 35 min \u2014 1 observer\n selects items by feature: 7/9 correct (82%); latency 2.1s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/12 correct (84%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d74\n answers WH-questions about familiar topics: 10/13 correct (77%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n wait calmly when access to preferred item is denied: 7/9 correct (73%); latency 2.6s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n indicating completion ('all done', 'finished'): 10/13 correct (79%); latency 2.3s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d72\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 11 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 63.2%.\n- Trend direction: downward (first session: 82%, last session: 82%).\n- IOA data: 89% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "c1877f5521ca22e8", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "early", "n_sessions": 11, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "82365"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3217\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Mand + Tact + Tolerating Denied Access\nDate range: Sessions 1\u201310 across 20 days (2026-04-12 to 2026-05-02)\n\nACCELERATION PROGRAMS\n1. indicating completion ('all done', 'finished') (Mand)\n Method: NET\n2. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n3. tacts common objects (Tact)\n Method: DTT\n4. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-12 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 5/8 correct (60%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/11 correct (59%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d78\n tacts common objects: 8/12 correct (66%); latency 3.1s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n wait calmly when access to preferred item is denied: 9/14 correct (63%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n\nSession 2 \u2014 2026-04-14 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 6/12 correct (53%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/11 correct (60%); latency 3.5s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n tacts common objects: 9/13 correct (68%); latency 2.9s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d76\n wait calmly when access to preferred item is denied: 5/8 correct (58%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n\nSession 3 \u2014 2026-04-16 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 6/11 correct (55%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/13 correct (59%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d78\n tacts common objects: 9/13 correct (69%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d78\n wait calmly when access to preferred item is denied: 5/8 correct (60%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n\nSession 4 \u2014 2026-04-18 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 7/12 correct (58%); latency 3.3s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/10 correct (58%); latency 3.2s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n tacts common objects: 6/10 correct (65%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n wait calmly when access to preferred item is denied: 7/11 correct (67%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n\nSession 5 \u2014 2026-04-20 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 4/14 correct (30%); latency 4.9s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/10 correct (30%); latency 4.9s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d74\n tacts common objects: 5/14 correct (33%); latency 4.4s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d710\n wait calmly when access to preferred item is denied: 4/15 correct (27%); latency 4.8s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d78\n\nSession 6 \u2014 2026-04-22 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 5/15 correct (34%); latency 4.7s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/8 correct (32%); latency 4.7s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n tacts common objects: 4/11 correct (37%); latency 4.4s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d74\n wait calmly when access to preferred item is denied: 5/15 correct (32%); latency 4.6s; prompts FP\u00d70, PP\u00d75, G\u00d71, I\u00d79\n\nSession 7 \u2014 2026-04-24 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 5/10 correct (46%); latency 4.1s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (39%); latency 4.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n tacts common objects: 5/13 correct (40%); latency 4.1s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d76\n wait calmly when access to preferred item is denied: 5/15 correct (35%); latency 4.2s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d710\n\nSession 8 \u2014 2026-04-26 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 5/11 correct (49%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/12 correct (47%); latency 3.6s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d74\n tacts common objects: 4/8 correct (51%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n wait calmly when access to preferred item is denied: 6/15 correct (37%); latency 4.6s; prompts FP\u00d75, PP\u00d70, G\u00d70, I\u00d710\n\nSession 9 \u2014 2026-04-28 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 6/12 correct (54%); latency 3.8s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/10 correct (54%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n tacts common objects: 6/11 correct (57%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n wait calmly when access to preferred item is denied: 5/11 correct (42%); latency 4.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n\nSession 10 \u2014 2026-04-30 \u2014 55 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 5/9 correct (58%); latency 3.6s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/12 correct (56%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d710\n tacts common objects: 8/12 correct (65%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d77\n wait calmly when access to preferred item is denied: 8/15 correct (51%); latency 3.6s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d75\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Playing with non-task materials\n- Delayed responding (>5 seconds consistently)\n- Stereotypic behavior during inter-trial intervals"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 49.6%.\n- Trend direction: downward (first session: 60%, last session: 58%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "18156c9ea7eced13", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "early", "n_sessions": 10, "n_programs": 4, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "74200"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8979\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Mand + Reading + Self-Care\nDate range: Sessions 1\u201312 across 24 days (2026-06-02 to 2026-06-26)\n\nACCELERATION PROGRAMS\n1. brushing teeth independently (Self-Care)\n Method: Task Analysis\n2. tolerating haircut (Self-Care)\n Method: Task Analysis\n3. requesting preferred items using AAC device (Mand)\n Method: NET\n4. reads 10\u201320 sight words (Reading)\n Method: DTT\n5. requesting help when a task is difficult (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Non-compliance \u2014 function hypothesized: escape\n2. Motor stereotypy \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-02 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 5/9 correct (60%); latency 3.1s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n tolerating haircut: 6/8 correct (71%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n requesting preferred items using AAC device: 5/8 correct (60%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 9/14 correct (62%); latency 3.2s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d76\n requesting help when a task is difficult: 9/15 correct (62%); latency 3.0s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d78\n Non-compliance: freq 1\n Motor stereotypy: freq 2; PIR 9%\n\nSession 2 \u2014 2026-06-04 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 9/15 correct (60%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d712\n tolerating haircut: 10/15 correct (66%); latency 2.7s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d75\n requesting preferred items using AAC device: 6/10 correct (57%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d79\n reads 10\u201320 sight words: 7/11 correct (68%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n requesting help when a task is difficult: 7/12 correct (58%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d74\n Non-compliance: freq 1\n Motor stereotypy: freq 1; PIR 8%\n\nSession 3 \u2014 2026-06-06 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 8/12 correct (64%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d78\n tolerating haircut: 8/11 correct (69%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d77\n requesting preferred items using AAC device: 8/15 correct (56%); latency 3.7s; prompts FP\u00d72, PP\u00d75, G\u00d70, I\u00d78\n reads 10\u201320 sight words: 9/13 correct (69%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d78\n requesting help when a task is difficult: 5/8 correct (59%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n Non-compliance: freq 2\n Motor stereotypy: freq 2; PIR 19%\n\nSession 4 \u2014 2026-06-08 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 9/13 correct (69%); latency 2.9s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d73\n tolerating haircut: 10/14 correct (71%); latency 3.0s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d76\n requesting preferred items using AAC device: 6/10 correct (62%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n reads 10\u201320 sight words: 5/8 correct (66%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n requesting help when a task is difficult: 5/8 correct (64%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n Non-compliance: freq 0\n Motor stereotypy: freq 1; PIR 14%\n\nSession 5 \u2014 2026-06-10 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 4/12 correct (34%); latency 4.4s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d78\n tolerating haircut: 4/11 correct (40%); latency 4.3s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n requesting preferred items using AAC device: 3/9 correct (28%); latency 4.5s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d73\n reads 10\u201320 sight words: 4/12 correct (32%); latency 4.4s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d77\n requesting help when a task is difficult: 2/9 correct (25%); latency 5.2s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n Non-compliance: freq 3\n Motor stereotypy: freq 4; PIR 22%\n\nSession 6 \u2014 2026-06-12 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 3/9 correct (38%); latency 4.2s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d74\n tolerating haircut: 7/15 correct (48%); latency 3.7s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d79\n requesting preferred items using AAC device: 5/14 correct (32%); latency 4.8s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d78\n reads 10\u201320 sight words: 5/14 correct (39%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d712\n requesting help when a task is difficult: 4/12 correct (34%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d711\n Non-compliance: freq 4\n Motor stereotypy: freq 3; PIR 9%\n\nSession 7 \u2014 2026-06-14 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 5/11 correct (44%); latency 3.9s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n tolerating haircut: 7/12 correct (56%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d76\n requesting preferred items using AAC device: 4/10 correct (36%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n reads 10\u201320 sight words: 6/13 correct (47%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d77\n requesting help when a task is difficult: 4/11 correct (37%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d75\n Non-compliance: freq 1\n Motor stereotypy: freq 1; PIR 6%\n\nSession 8 \u2014 2026-06-16 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 6/12 correct (50%); latency 4.0s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d75\n tolerating haircut: 7/11 correct (60%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n requesting preferred items using AAC device: 6/14 correct (45%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d79\n reads 10\u201320 sight words: 5/8 correct (58%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n requesting help when a task is difficult: 4/10 correct (40%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d74\n Non-compliance: freq 0\n Motor stereotypy: freq 1; PIR 6%\n\nSession 9 \u2014 2026-06-18 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 5/8 correct (63%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n tolerating haircut: 8/12 correct (67%); latency 3.2s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d74\n requesting preferred items using AAC device: 6/10 correct (55%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n reads 10\u201320 sight words: 9/14 correct (66%); latency 3.1s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d76\n requesting help when a task is difficult: 4/9 correct (44%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n Non-compliance: freq 1\n Motor stereotypy: freq 2; PIR 19%\n\nSession 10 \u2014 2026-06-20 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 5/8 correct (64%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n tolerating haircut: 8/12 correct (67%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d74\n requesting preferred items using AAC device: 5/8 correct (60%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 9/14 correct (66%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d710\n requesting help when a task is difficult: 7/15 correct (47%); latency 4.1s; prompts FP\u00d70, PP\u00d75, G\u00d73, I\u00d77\n Non-compliance: freq 1\n Motor stereotypy: freq 1; PIR 14%\n\nSession 11 \u2014 2026-06-22 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 6/10 correct (64%); latency 2.9s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n tolerating haircut: 9/13 correct (67%); latency 3.0s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d79\n requesting preferred items using AAC device: 8/13 correct (60%); latency 3.1s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d76\n reads 10\u201320 sight words: 6/9 correct (66%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n requesting help when a task is difficult: 8/14 correct (56%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d711\n Non-compliance: freq 2\n Motor stereotypy: freq 2; PIR 11%\n\nSession 12 \u2014 2026-06-24 \u2014 31 min \u2014 1 observer\n brushing teeth independently: 10/15 correct (64%); latency 2.8s; prompts FP\u00d71, PP\u00d75, G\u00d75, I\u00d74\n tolerating haircut: 5/8 correct (67%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n requesting preferred items using AAC device: 5/9 correct (60%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 9/14 correct (66%); latency 3.1s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n requesting help when a task is difficult: 7/12 correct (58%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d79\n Non-compliance: freq 1\n Motor stereotypy: freq 2; PIR 11%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Stereotypic behavior during inter-trial intervals\n- Looking away during SD presentation\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Behavior Function Hypothesis\nNon-compliance: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\nMotor stereotypy: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 56.2%.\n- Trend direction: upward (first session: 60%, last session: 64%).\n- Non-compliance: mean 1.4/session (early-window mean 1.0 -> late-window mean 1.2).\n- Motor stereotypy: mean 1.8/session (early-window mean 1.5 -> late-window mean 1.8).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "c8444262e057668a", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {"Non-compliance": "escape", "Motor stereotypy": "automatic"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "adolescent", "n_sessions": 12, "n_programs": 5, "n_behaviors": 2, "behavior_ids": ["non_compliance", "motor_stereotypy"], "behavior_functions": ["escape", "automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "76456"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7908\nProfile: Adult Learner (18+ years)\nCurricula: Independent Living + Self-Care + Vocational\nDate range: Sessions 1\u20139 across 18 days (2026-06-16 to 2026-07-04)\n\nACCELERATION PROGRAMS\n1. brushing teeth independently (Self-Care)\n Method: Task Analysis\n2. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n3. managing a budget (Independent Living)\n Method: Task Analysis\n4. clocking in at start of shift (Vocational)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-16 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 11/15 correct (74%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d78\n dressing (pants, shirt): 10/13 correct (79%); latency 2.3s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d76\n managing a budget: 9/11 correct (81%); latency 2.4s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n clocking in at start of shift: 12/15 correct (82%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d75, I\u00d78\n\nSession 2 \u2014 2026-06-18 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 8/11 correct (75%); latency 2.6s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d77\n dressing (pants, shirt): 8/10 correct (79%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n managing a budget: 10/12 correct (82%); latency 2.6s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d75\n clocking in at start of shift: 9/11 correct (86%); latency 2.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n\nSession 3 \u2014 2026-06-20 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 11/15 correct (71%); latency 2.7s; prompts FP\u00d72, PP\u00d75, G\u00d72, I\u00d76\n dressing (pants, shirt): 6/8 correct (75%); latency 2.5s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n managing a budget: 11/13 correct (81%); latency 2.1s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n clocking in at start of shift: 13/15 correct (86%); latency 1.8s; prompts FP\u00d72, PP\u00d74, G\u00d75, I\u00d74\n\nSession 4 \u2014 2026-06-22 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 3/9 correct (35%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n dressing (pants, shirt): 4/9 correct (44%); latency 4.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n managing a budget: 7/13 correct (55%); latency 3.7s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d78\n clocking in at start of shift: 6/15 correct (41%); latency 4.0s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d73\n\nSession 5 \u2014 2026-06-24 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 3/8 correct (34%); latency 4.5s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n dressing (pants, shirt): 6/15 correct (41%); latency 4.4s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d710\n managing a budget: 4/8 correct (54%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n clocking in at start of shift: 6/15 correct (41%); latency 4.3s; prompts FP\u00d75, PP\u00d73, G\u00d71, I\u00d76\n\nSession 6 \u2014 2026-06-26 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 5/12 correct (38%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d78\n dressing (pants, shirt): 4/8 correct (45%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n managing a budget: 8/14 correct (58%); latency 3.4s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d73\n clocking in at start of shift: 5/12 correct (43%); latency 3.9s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d71\n\nSession 7 \u2014 2026-06-28 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 5/10 correct (47%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n dressing (pants, shirt): 5/11 correct (48%); latency 3.9s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n managing a budget: 7/14 correct (53%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d710\n clocking in at start of shift: 6/13 correct (48%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d79\n\nSession 8 \u2014 2026-06-30 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 7/13 correct (57%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n dressing (pants, shirt): 6/11 correct (59%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n managing a budget: 5/9 correct (58%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d77\n clocking in at start of shift: 8/14 correct (56%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d77\n\nSession 9 \u2014 2026-07-02 \u2014 52 min \u2014 1 observer\n brushing teeth independently: 8/12 correct (63%); latency 3.5s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d710\n dressing (pants, shirt): 9/15 correct (62%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d710\n managing a budget: 9/14 correct (61%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n clocking in at start of shift: 7/12 correct (62%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d76\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Playing with non-task materials\n- Leaving seat without permission\n- Stereotypic behavior during inter-trial intervals\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 54.7%.\n- Trend direction: downward (first session: 74%, last session: 63%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "e8880784e0be88e1", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "adult", "n_sessions": 9, "n_programs": 4, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "39857"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: identifies 5\u201310 upper-case letters\nCurriculum: Reading L1\nLearner: Early Learner\nMastery Status: Approaching mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies 5\u201310 upper-case letters\n- Curriculum: Reading L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What letter is this?\"\nVariations: \"Read this letter\"; \"What does this say?\"\nPresentation: Present the letter flashcard.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: C, F, D\nDistractor stimuli: I, B\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy across 2 consecutive sessions with at least 10 trials each.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "7026d711a01dbc3b", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies 5\u201310 upper-case letters", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "fr2", "error_correction": "simple_correction", "mastery_criterion": "mc_80_2sessions"}, "teacher_model": null, "seed_tag": "46080"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8319\nProfile: Adult Learner (18+ years)\nCurricula: Independent Living + Mand + Self-Care + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u20139 across 18 days (2026-08-19 to 2026-09-06)\n\nACCELERATION PROGRAMS\n1. requesting a break during extended tasks (Mand)\n Method: NET\n2. scheduling medical appointments (Independent Living)\n Method: Task Analysis\n3. brushing teeth independently (Self-Care)\n Method: Task Analysis\n4. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n5. clocking in at start of shift (Vocational)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-19 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 7/10 correct (70%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n scheduling medical appointments: 4/8 correct (45%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n brushing teeth independently: 5/10 correct (47%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n wait calmly when a preferred activity is denied: 10/15 correct (69%); latency 2.9s; prompts FP\u00d75, PP\u00d72, G\u00d70, I\u00d78\n clocking in at start of shift: 4/8 correct (50%); latency 3.7s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n\nSession 2 \u2014 2026-08-21 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 6/9 correct (67%); latency 3.2s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n scheduling medical appointments: 5/10 correct (55%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d79\n brushing teeth independently: 5/12 correct (46%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d79\n wait calmly when a preferred activity is denied: 6/9 correct (66%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n clocking in at start of shift: 6/12 correct (48%); latency 3.7s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d73\n\nSession 3 \u2014 2026-08-23 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 10/15 correct (65%); latency 3.3s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d75\n scheduling medical appointments: 4/8 correct (49%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n brushing teeth independently: 5/11 correct (44%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n wait calmly when a preferred activity is denied: 8/12 correct (65%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d72\n clocking in at start of shift: 4/9 correct (46%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d76\n\nSession 4 \u2014 2026-08-25 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 8/12 correct (66%); latency 3.2s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d76\n scheduling medical appointments: 6/14 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d712\n brushing teeth independently: 7/13 correct (51%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d76\n wait calmly when a preferred activity is denied: 8/15 correct (56%); latency 3.2s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d78\n clocking in at start of shift: 5/10 correct (50%); latency 3.9s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n\nSession 5 \u2014 2026-08-27 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 5/8 correct (66%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n scheduling medical appointments: 5/12 correct (44%); latency 3.8s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d75\n brushing teeth independently: 7/14 correct (51%); latency 3.6s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d79\n wait calmly when a preferred activity is denied: 6/9 correct (64%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n clocking in at start of shift: 4/8 correct (51%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n\nSession 6 \u2014 2026-08-29 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 5/8 correct (62%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n scheduling medical appointments: 4/8 correct (52%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n brushing teeth independently: 4/10 correct (43%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d79\n wait calmly when a preferred activity is denied: 8/13 correct (65%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d78\n clocking in at start of shift: 4/9 correct (43%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n\nSession 7 \u2014 2026-08-31 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 7/9 correct (73%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n scheduling medical appointments: 4/9 correct (40%); latency 4.3s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n brushing teeth independently: 4/9 correct (42%); latency 4.3s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n wait calmly when a preferred activity is denied: 6/9 correct (67%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n clocking in at start of shift: 6/15 correct (42%); latency 4.3s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d710\n\nSession 8 \u2014 2026-09-02 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 9/12 correct (73%); latency 2.7s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d710\n scheduling medical appointments: 4/8 correct (53%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n brushing teeth independently: 4/10 correct (35%); latency 4.2s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n wait calmly when a preferred activity is denied: 8/14 correct (57%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d77\n clocking in at start of shift: 7/15 correct (43%); latency 4.0s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d74\n\nSession 9 \u2014 2026-09-04 \u2014 43 min \u2014 1 observer\n requesting a break during extended tasks: 9/14 correct (66%); latency 2.9s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d77\n scheduling medical appointments: 4/11 correct (38%); latency 4.6s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d711\n brushing teeth independently: 6/14 correct (44%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d79\n wait calmly when a preferred activity is denied: 7/10 correct (67%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d75\n clocking in at start of shift: 5/13 correct (41%); latency 4.0s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d73\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Stereotypic behavior during inter-trial intervals"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Plateau**: accuracy has remained near 68% for 9 sessions without meaningful improvement.\n- Performance is below mastery criteria; current teaching procedure may not be effective for this learner.\n\n## Pattern Classification\nplateau\n\nResponding has stabilized below mastery criterion without meaningful movement, indicating the current procedure is limiting further acquisition.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Modify teaching procedure \u2014 switch prompt type (e.g., from most-to-least to time delay).\n- Conduct preference assessment and update reinforcer menu.\n- Break the current skill into smaller component steps if possible.\n- Increase practice opportunities by embedding targets in natural-environment training.\n\n### Consequence strategies\n- Check for inadvertent reinforcement of near-misses; tighten differential reinforcement.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 67.4%.\n- Trend direction: downward (first session: 70%, last session: 66%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "02c0ef3e43de42ad", "gold_labels": {"pattern_class": "plateau", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "plateau", "learner_profile": "adult", "n_sessions": 9, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "15263"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: spontaneously uses humor appropriately\nCurriculum Reference: Spontaneous Vocal Behavior L3\nLearner Profile: Adolescent Learner\nCurrent Mastery: Developing\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously uses humor appropriately\n- Curriculum: Spontaneous Vocal Behavior L3\n- Learner: Adolescent Learner\n- Current mastery: Developing\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: morning greeting.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's morning greeting routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the developing stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "dce5203c3082f7d9", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L3", "learner_profile": "adolescent", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously uses humor appropriately", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "76914"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: selects items by feature (What is round?)\nCurriculum: LRFFC L1\nLearner: Early Learner\nMastery Status: Developing\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by feature (What is round?)\n- Curriculum: LRFFC L1\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: towel, jacket, ball\nDistractor stimuli: book, blanket\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nPrevent errors by using high prompts from the start; fade gradually. Paired with most-to-least prompt hierarchy.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy at independent prompt level across 3 sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "665a1d982f3291a6", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L1", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by feature (What is round?)", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "crf", "error_correction": "errorless", "mastery_criterion": "mc_80_independent"}, "teacher_model": null, "seed_tag": "97173"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1664\nProfile: Adult Learner (18+ years)\nCurricula: Mand + Self-Care + Vocational\nDate range: Sessions 1\u201312 across 24 days (2026-04-02 to 2026-04-26)\n\nACCELERATION PROGRAMS\n1. indicating 'all done' at task completion (Mand)\n Method: NET\n2. requesting a break during extended tasks (Mand)\n Method: NET\n3. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n4. requesting assistance using AAC device (Mand)\n Method: NET\n5. brushing teeth independently (Self-Care)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-02 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 7/12 correct (56%); latency 3.3s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d73\n requesting a break during extended tasks: 5/8 correct (65%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n completing assigned tasks in order: 4/9 correct (44%); latency 4.2s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d74\n requesting assistance using AAC device: 5/9 correct (60%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d76\n brushing teeth independently: 4/8 correct (48%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n\nSession 2 \u2014 2026-04-04 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 5/8 correct (63%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n requesting a break during extended tasks: 7/10 correct (72%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n completing assigned tasks in order: 6/12 correct (47%); latency 4.2s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d78\n requesting assistance using AAC device: 4/9 correct (49%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n brushing teeth independently: 6/12 correct (46%); latency 4.1s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d75\n\nSession 3 \u2014 2026-04-06 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 5/8 correct (63%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n requesting a break during extended tasks: 9/15 correct (59%); latency 3.2s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d77\n completing assigned tasks in order: 7/15 correct (46%); latency 4.2s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d78\n requesting assistance using AAC device: 4/8 correct (46%); latency 4.0s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n brushing teeth independently: 6/12 correct (49%); latency 3.6s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d73\n\nSession 4 \u2014 2026-04-08 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 9/14 correct (66%); latency 2.8s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d78\n requesting a break during extended tasks: 9/15 correct (62%); latency 3.4s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d78\n completing assigned tasks in order: 5/10 correct (51%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n requesting assistance using AAC device: 6/13 correct (45%); latency 4.0s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n brushing teeth independently: 4/8 correct (54%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n\nSession 5 \u2014 2026-04-10 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 4/8 correct (50%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n requesting a break during extended tasks: 8/14 correct (59%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d79\n completing assigned tasks in order: 3/8 correct (42%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n requesting assistance using AAC device: 7/13 correct (53%); latency 3.7s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d78\n brushing teeth independently: 5/10 correct (49%); latency 3.9s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d72\n\nSession 6 \u2014 2026-04-12 \u2014 IOA SESSION \u2014 2 observers\n indicating 'all done' at task completion: 49% (primary); IOA 93% agreement\n requesting a break during extended tasks: 67% (primary); IOA 93% agreement\n completing assigned tasks in order: 43% (primary); IOA 93% agreement\n requesting assistance using AAC device: 53% (primary); IOA 93% agreement\n brushing teeth independently: 51% (primary); IOA 93% agreement\n\nSession 7 \u2014 2026-04-14 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 4/8 correct (48%); latency 4.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n requesting a break during extended tasks: 9/13 correct (68%); latency 3.1s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n completing assigned tasks in order: 3/8 correct (34%); latency 4.4s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n requesting assistance using AAC device: 4/11 correct (40%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d79\n brushing teeth independently: 8/15 correct (56%); latency 3.4s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d711\n\nSession 8 \u2014 2026-04-16 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 6/11 correct (58%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n requesting a break during extended tasks: 6/10 correct (63%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d74\n completing assigned tasks in order: 4/10 correct (37%); latency 4.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n requesting assistance using AAC device: 3/8 correct (39%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n brushing teeth independently: 4/10 correct (44%); latency 4.1s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n\nSession 9 \u2014 2026-04-18 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 6/14 correct (43%); latency 4.1s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d79\n requesting a break during extended tasks: 7/11 correct (63%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n completing assigned tasks in order: 5/13 correct (39%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d77\n requesting assistance using AAC device: 6/11 correct (50%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n brushing teeth independently: 4/8 correct (51%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n\nSession 10 \u2014 2026-04-20 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 4/9 correct (43%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n requesting a break during extended tasks: 5/8 correct (60%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n completing assigned tasks in order: 4/9 correct (39%); latency 4.4s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n requesting assistance using AAC device: 4/10 correct (42%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n brushing teeth independently: 5/10 correct (49%); latency 3.7s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n\nSession 11 \u2014 2026-04-22 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 5/10 correct (47%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n requesting a break during extended tasks: 6/10 correct (63%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n completing assigned tasks in order: 4/13 correct (31%); latency 4.5s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d75\n requesting assistance using AAC device: 5/13 correct (35%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d711\n brushing teeth independently: 7/14 correct (51%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d78\n\nSession 12 \u2014 2026-04-24 \u2014 54 min \u2014 1 observer\n indicating 'all done' at task completion: 6/12 correct (50%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d78\n requesting a break during extended tasks: 6/9 correct (67%); latency 2.8s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n completing assigned tasks in order: 4/15 correct (28%); latency 4.6s; prompts FP\u00d71, PP\u00d75, G\u00d71, I\u00d78\n requesting assistance using AAC device: 3/8 correct (42%); latency 4.3s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n brushing teeth independently: 8/15 correct (54%); latency 3.6s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d710\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Looking away during SD presentation\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Plateau**: accuracy has remained near 53% for 12 sessions without meaningful improvement.\n- Performance is below mastery criteria; current teaching procedure may not be effective for this learner.\n\n## Pattern Classification\nplateau\n\nResponding has stabilized below mastery criterion without meaningful movement, indicating the current procedure is limiting further acquisition.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Modify teaching procedure \u2014 switch prompt type (e.g., from most-to-least to time delay).\n- Conduct preference assessment and update reinforcer menu.\n- Break the current skill into smaller component steps if possible.\n- Increase practice opportunities by embedding targets in natural-environment training.\n\n### Consequence strategies\n- Check for inadvertent reinforcement of near-misses; tighten differential reinforcement.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 12 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 53.0%.\n- Trend direction: downward (first session: 56%, last session: 50%).\n- IOA data: 93% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "17b13ac4da2b3f04", "gold_labels": {"pattern_class": "plateau", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "plateau", "learner_profile": "adult", "n_sessions": 12, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "28229"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: compares quantities (more/less/same)\nCurriculum Reference: Math L2\nLearner Profile: School-Age Learner\nCurrent Mastery: Emerging\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: compares quantities (more/less/same)\n- Curriculum: Math L2\n- Learner: School-Age Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"How many?\"\nVariations: \"Count these\"; \"What number is this?\"\nPresentation: Present the numeral card or a set of objects to count.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: napkin, scissors, apple\nDistractor stimuli: spoon, shoe, plate, cup\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nPrevent errors by using high prompts from the start; fade gradually. Paired with most-to-least prompt hierarchy.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "7b9eacb92a8bc7db", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L2", "learner_profile": "school_age", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "compares quantities (more/less/same)", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "crf", "error_correction": "errorless", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "27367"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: identifies 5\u201310 upper-case letters\nCurriculum: Reading L1\nLearner: Early Learner\nMastery Status: Mastered at current level\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies 5\u201310 upper-case letters\n- Curriculum: Reading L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What letter is this?\"\nVariations: \"Read this letter\"; \"What does this say?\"\nPresentation: Present the letter flashcard.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: C, J, G\nDistractor stimuli: H, F\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "bb19268ca0ca039a", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies 5\u201310 upper-case letters", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "fr2", "error_correction": "simple_correction", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "93978"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: simple meal preparation (sandwich)\nCurriculum: AFLS Home Skills\nLearner: Adolescent Learner\nMastery Status: Mastered at current level\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: simple meal preparation (sandwich)\n- Curriculum: AFLS Home Skills\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Collect all ingredients (bread, filling, spread).\n2. Place two slices of bread on the plate.\n3. Apply spread to one slice.\n4. Place filling on the spread slice.\n5. Place the second slice on top.\n6. Cut the sandwich in half if desired.\n7. Place on a plate to serve.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the mastered stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "7ebf1484022cb6be", "gold_labels": {"method": "task_analysis", "domain": "AFLS.home", "skill": "simple meal preparation (sandwich)", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "mastered", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "simple meal preparation (sandwich)", "module": "home", "mastery_criterion": "mc_self_initiation", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "42817"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: using public transportation\nCurriculum: AFLS Community Participation Skills\nLearner: Adolescent Learner\nMastery Status: Developing\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: using public transportation\n- Curriculum: AFLS Community Participation Skills\n- Learner: Adolescent Learner\n- Current mastery: Developing\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Confirm the correct stop or station. <- Learner-taught step (forward chaining starts here)\n2. Purchase or have the fare ready.\n3. Wait at the designated boarding area.\n4. Board the vehicle when it arrives.\n5. Pay the fare or present the pass.\n6. Sit or stand safely.\n7. Monitor the route for the correct stop.\n8. Exit at the correct stop.\n\n## Prompt Strategy Per Step\nStrategy: Most-to-Least\nStart with full-physical prompt at each step; fade to partial physical, gestural, verbal, independent.\nCurrent prompt level: At the developing stage, use full-physical or partial-physical prompts at each step; fade systematically.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "12eaa878425b5645", "gold_labels": {"method": "task_analysis", "domain": "AFLS.community", "skill": "using public transportation", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "developing", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "using public transportation", "module": "community", "mastery_criterion": "mc_self_initiation", "chain_type": "forward", "prompt_strategy": "most_to_least", "reinforcement_schedule": "crf_per_step", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "92010"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a systematic desensitization / toleration program for the following.\n\nSkill: tolerating tooth brushing by caregiver\nCurriculum: AFLS Basic Living Skills\nLearner Level: Adolescent Learner\nBaseline: Developing\n\nThe learner currently refuses or exhibits safety behaviors during the activity; the program should build tolerance gradually."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating tooth brushing by caregiver\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adolescent Learner\n- Current mastery: Developing\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for tooth brushing performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nfull 2-minute tooth-brushing routine completed by caregiver without refusal, crying, SIB, or aggression\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1-second toothbrush contact with teeth\n2. 3 seconds of brushing\n3. 5 seconds of brushing\n4. 15 seconds of brushing\n5. 30 seconds of brushing\n6. 60 seconds of brushing\n7. Full 2-minute brushing routine\n\nCurrent shaping step: At the developing stage, begin at shaping step 2 (\"3 seconds of brushing\") and advance through step 3 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal duration tolerated across 3 consecutive sessions with no safety behaviors (refusal, crying, SIB, aggression, property destruction).\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 3 different settings and with 3 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "21072f6b55e579d2", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating tooth brushing by caregiver", "program_type": "toleration", "learner_profile": "adolescent", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating tooth brushing by caregiver", "module": "basic_living", "mastery_criterion": "mc_toleration_full_duration", "shaping_n_steps": 7}, "teacher_model": null, "seed_tag": "98892"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: tacts familiar people by name\nCurriculum: Tact L1\nLearner Level: Early Learner\nBaseline: Mastered at current level\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts familiar people by name\n- Curriculum: Tact L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What is this?\"\nVariations: \"Tell me what you see\"; \"What's that?\"; \"Name this\"\nPresentation: Present the target stimulus within visual field and ask while pointing to it.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: scissors, crayon, brush\nDistractor stimuli: car, apple\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nToken economy \u2014 Tokens delivered per correct response; exchanged at session end for a back-up reinforcer appropriate to the learner (for children: candy, cookies, brief leisure-time access, preferred activity, screen time, or a favorite sensory item). Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "9c364ca007b1a2ad", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts familiar people by name", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "token_economy", "error_correction": "backstep", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "69141"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: identifies coins by name\nCurriculum Reference: Math L2\nLearner Profile: Early Learner\nCurrent Mastery: Near mastery\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies coins by name\n- Curriculum: Math L2\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What number is this?\"\nVariations: \"Which number?\"; \"Tell me the number\"\nPresentation: Present the numeral card.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: ball, towel, glue\nDistractor stimuli: book, blanket, apple, plate\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "bb30021e20265be7", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L2", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies coins by name", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "vr3", "error_correction": "backstep", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "85854"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5737\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Self-Care + Tolerating Denied Access\nDate range: Sessions 1\u201311 across 22 days (2026-08-07 to 2026-08-29)\n\nACCELERATION PROGRAMS\n1. ordering in a restaurant (Community)\n Method: Task Analysis\n2. washing hands independently (Self-Care)\n Method: Task Analysis\n3. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n\nDECELERATION TARGETS\n1. Non-compliance \u2014 function hypothesized: escape\n2. Property destruction \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-07 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 12/15 correct (77%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d79\n washing hands independently: 7/9 correct (81%); latency 2.5s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d75\n wait calmly when access to preferred item is denied: 12/15 correct (82%); latency 2.1s; prompts FP\u00d73, PP\u00d72, G\u00d75, I\u00d75\n Non-compliance: freq 2\n Property destruction: freq 3\n\nSession 2 \u2014 2026-08-09 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 7/10 correct (72%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n washing hands independently: 8/10 correct (76%); latency 2.3s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n wait calmly when access to preferred item is denied: 6/8 correct (78%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n Non-compliance: freq 2\n Property destruction: freq 4\n\nSession 3 \u2014 2026-08-11 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 6/10 correct (62%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d72\n washing hands independently: 5/8 correct (62%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n wait calmly when access to preferred item is denied: 8/11 correct (70%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n Non-compliance: freq 2\n Property destruction: freq 3\n\nSession 4 \u2014 2026-08-13 \u2014 IOA SESSION \u2014 2 observers\n ordering in a restaurant: 58% (primary); IOA 97% agreement\n washing hands independently: 59% (primary); IOA 97% agreement\n wait calmly when access to preferred item is denied: 61% (primary); IOA 97% agreement\n Non-compliance: freq 2; IOA 97% agreement\n Property destruction: freq 5; IOA 97% agreement\n\nSession 5 \u2014 2026-08-15 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 6/13 correct (43%); latency 3.9s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d73\n washing hands independently: 7/15 correct (50%); latency 3.7s; prompts FP\u00d71, PP\u00d71, G\u00d75, I\u00d78\n wait calmly when access to preferred item is denied: 5/8 correct (58%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n Non-compliance: freq 3\n Property destruction: freq 4\n\nSession 6 \u2014 2026-08-17 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 6/15 correct (39%); latency 4.2s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d77\n washing hands independently: 3/8 correct (41%); latency 4.0s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n wait calmly when access to preferred item is denied: 9/15 correct (57%); latency 3.2s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d710\n Non-compliance: freq 3\n Property destruction: freq 5\n\nSession 7 \u2014 2026-08-19 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 3/10 correct (28%); latency 4.6s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n washing hands independently: 3/10 correct (34%); latency 4.2s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d77\n wait calmly when access to preferred item is denied: 4/9 correct (43%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n Non-compliance: freq 3\n Property destruction: freq 4\n\nSession 8 \u2014 2026-08-21 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 4/15 correct (23%); latency 5.2s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d74\n washing hands independently: 3/10 correct (30%); latency 4.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d78\n wait calmly when access to preferred item is denied: 3/8 correct (43%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n Non-compliance: freq 3\n Property destruction: freq 4\n\nSession 9 \u2014 2026-08-23 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 1/8 correct (15%); latency 5.6s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n washing hands independently: 4/13 correct (27%); latency 4.6s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d77\n wait calmly when access to preferred item is denied: 5/13 correct (40%); latency 4.2s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d76\n Non-compliance: freq 4\n Property destruction: freq 6\n\nSession 10 \u2014 2026-08-25 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 2/15 correct (10%); latency 5.5s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d76\n washing hands independently: 2/12 correct (18%); latency 5.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d78\n wait calmly when access to preferred item is denied: 4/13 correct (32%); latency 4.3s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d78\n Non-compliance: freq 4\n Property destruction: freq 7\n\nSession 11 \u2014 2026-08-27 \u2014 51 min \u2014 1 observer\n ordering in a restaurant: 1/9 correct (10%); latency 5.4s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d76\n washing hands independently: 1/12 correct (10%); latency 5.7s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d76\n wait calmly when access to preferred item is denied: 3/11 correct (31%); latency 4.5s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n Non-compliance: freq 5\n Property destruction: freq 7\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Elopement from the work area\n- Vocal refusal ('no', 'I don't want to')"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 77% to 10% across 11 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nNon-compliance: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\nProperty destruction: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nhigh\n\nPattern is well-supported: 11 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 39.7%.\n- Trend direction: downward (first session: 77%, last session: 10%).\n- Non-compliance: mean 3.0/session (early-window mean 2.0 -> late-window mean 4.3).\n- Property destruction: mean 4.7/session (early-window mean 3.3 -> late-window mean 6.7).\n- IOA data: 97% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "75afaba36c518978", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Non-compliance": "escape", "Property destruction": "escape"}, "escalation_level": 3, "confidence": "high", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "adolescent", "n_sessions": 11, "n_programs": 3, "n_behaviors": 2, "behavior_ids": ["non_compliance", "property_destruction"], "behavior_functions": ["escape", "escape"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "46501"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: traces basic shapes (circle, cross)\nCurriculum Reference: Writing L1\nLearner Profile: Early Learner\nCurrent Mastery: Emerging\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: traces basic shapes (circle, cross)\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: oval, rectangle, triangle\nDistractor stimuli: square, star\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "3d5f7dbadda34951", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "traces basic shapes (circle, cross)", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "68189"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: matches upper-case letters\nCurriculum Reference: Visual Perceptual Skills & Matching-to-Sample L2\nLearner Profile: Early Learner\nCurrent Mastery: Generalization phase\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: matches upper-case letters\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L2\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: Z, O, W\nDistractor stimuli: K, P, R, A\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "454315aea6f54820", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L2", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "matches upper-case letters", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "vr3", "error_correction": "simple_correction", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "97173"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: matches words to identical words\nCurriculum: Reading L1\nLearner: Early Learner\nMastery Status: Mastered at current level\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: matches words to identical words\n- Curriculum: Reading L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What word?\"\nVariations: \"Read this word\"; \"What does it say?\"\nPresentation: Present the sight-word card and deliver the SD.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: key, apple, car\nDistractor stimuli: book, brush\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "d84978d45bb8ebfa", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "matches words to identical words", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "fr2", "error_correction": "backstep", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "93657"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: spontaneously uses social phrases appropriately\nCurriculum: Spontaneous Vocal Behavior L2\nLearner: School-Age Learner\nMastery Status: Approaching mastery\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously uses social phrases appropriately\n- Curriculum: Spontaneous Vocal Behavior L2\n- Learner: School-Age Learner\n- Current mastery: Approaching mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: activity setup.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's activity setup routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the approaching mastery stage, use time delay (0 s -> 2 s -> 4 s) before delivering any model prompt; reinforce independent responses differentially.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "3ce46eef40257ece", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L2", "learner_profile": "school_age", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously uses social phrases appropriately", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "time_delay", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "54871"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: describes recent events in sequence\nCurriculum Reference: Intraverbal L2\nLearner Profile: School-Age Learner\nCurrent Mastery: Near mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: describes recent events in sequence\n- Curriculum: Intraverbal L2\n- Learner: School-Age Learner\n- Current mastery: Near mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: transition conversation.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's transition conversation routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the near mastery stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "ab4e819b342f5828", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L2", "learner_profile": "school_age", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "describes recent events in sequence", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "5962"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: engages in social games (peek-a-boo, tickle)\nCurriculum: Social Behavior & Social Play L1\nLearner Level: Early Learner\nBaseline: Developing\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: engages in social games (peek-a-boo, tickle)\n- Curriculum: Social Behavior & Social Play L1\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: circle time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's circle time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the developing stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "c42d6dd38cae0351", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L1", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "engages in social games (peek-a-boo, tickle)", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "70185"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-2769\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Home Skills + Mand + Reading + Self-Care\nDate range: Sessions 1\u20138 across 16 days (2026-10-11 to 2026-10-27)\n\nACCELERATION PROGRAMS\n1. requesting preferred items using AAC device (Mand)\n Method: NET\n2. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n3. reads 10\u201320 sight words (Reading)\n Method: DTT\n4. indicating 'all done' with a step or activity (Mand)\n Method: NET\n5. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Aggression \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-11 \u2014 60 min \u2014 1 observer\n requesting preferred items using AAC device: 11/15 correct (76%); latency 2.8s; prompts FP\u00d72, PP\u00d73, G\u00d75, I\u00d75\n meal cleanup after eating: 10/15 correct (70%); latency 2.9s; prompts FP\u00d75, PP\u00d71, G\u00d75, I\u00d74\n reads 10\u201320 sight words: 6/8 correct (75%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n indicating 'all done' with a step or activity: 6/8 correct (73%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n dressing (pants, shirt): 7/9 correct (77%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n Aggression: freq 2\n\nSession 2 \u2014 2026-10-13 \u2014 60 min \u2014 1 observer\n requesting preferred items using AAC device: 9/13 correct (72%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d711\n meal cleanup after eating: 7/12 correct (62%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d75\n reads 10\u201320 sight words: 7/9 correct (76%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n indicating 'all done' with a step or activity: 8/11 correct (73%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d75\n dressing (pants, shirt): 7/10 correct (69%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n Aggression: freq 3\n\nSession 3 \u2014 2026-10-15 \u2014 60 min \u2014 1 observer\n requesting preferred items using AAC device: 9/13 correct (71%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d78\n meal cleanup after eating: 5/10 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n reads 10\u201320 sight words: 7/10 correct (69%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n indicating 'all done' with a step or activity: 6/10 correct (60%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n dressing (pants, shirt): 6/10 correct (65%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n Aggression: freq 4\n\nSession 4 \u2014 2026-10-17 \u2014 60 min \u2014 1 observer\n requesting preferred items using AAC device: 6/11 correct (57%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n meal cleanup after eating: 5/10 correct (45%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n reads 10\u201320 sight words: 6/8 correct (70%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n indicating 'all done' with a step or activity: 4/8 correct (53%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n dressing (pants, shirt): 7/11 correct (62%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d710\n Aggression: freq 3\n\nSession 5 \u2014 2026-10-19 \u2014 60 min \u2014 1 observer\n requesting preferred items using AAC device: 8/15 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d75, G\u00d75, I\u00d72\n meal cleanup after eating: 5/15 correct (34%); latency 4.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d711\n reads 10\u201320 sight words: 5/8 correct (56%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n indicating 'all done' with a step or activity: 4/8 correct (52%); latency 3.5s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n dressing (pants, shirt): 5/9 correct (58%); latency 3.4s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n Aggression: freq 4\n\nSession 6 \u2014 2026-10-21 \u2014 60 min \u2014 1 observer\n requesting preferred items using AAC device: 4/10 correct (43%); latency 4.3s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n meal cleanup after eating: 4/15 correct (26%); latency 4.6s; prompts FP\u00d74, PP\u00d75, G\u00d73, I\u00d73\n reads 10\u201320 sight words: 4/8 correct (54%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n indicating 'all done' with a step or activity: 3/8 correct (38%); latency 4.3s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n dressing (pants, shirt): 5/10 correct (55%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d78\n Aggression: freq 5\n\nSession 7 \u2014 2026-10-23 \u2014 60 min \u2014 1 observer\n requesting preferred items using AAC device: 6/13 correct (42%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d79\n meal cleanup after eating: 3/13 correct (27%); latency 5.1s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d710\n reads 10\u201320 sight words: 4/8 correct (51%); latency 4.0s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n indicating 'all done' with a step or activity: 4/11 correct (39%); latency 4.5s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n dressing (pants, shirt): 6/13 correct (49%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n Aggression: freq 5\n\nSession 8 \u2014 2026-10-25 \u2014 60 min \u2014 1 observer\n requesting preferred items using AAC device: 4/13 correct (30%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d79\n meal cleanup after eating: 2/14 correct (11%); latency 5.6s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d79\n reads 10\u201320 sight words: 5/9 correct (51%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d76\n indicating 'all done' with a step or activity: 4/13 correct (33%); latency 4.3s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n dressing (pants, shirt): 7/14 correct (47%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d79\n Aggression: freq 6\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Self-stimulatory behavior increase during demand periods\n- Vocal refusal ('no', 'I don't want to')\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n- Attempts at property destruction (throwing materials, swiping items off the surface)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (76% -> 30%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nAggression: attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 55.6%.\n- Trend direction: downward (first session: 76%, last session: 30%).\n- Aggression: mean 4.0/session (early-window mean 2.5 -> late-window mean 5.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "ebee1bea6bf1e832", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Aggression": "attention"}, "escalation_level": 4, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "adolescent", "n_sessions": 8, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["aggression"], "behavior_functions": ["attention"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "61520"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: tracks print left to right\nCurriculum Reference: Reading L1\nLearner Profile: Early Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tracks print left to right\n- Curriculum: Reading L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What letter is this?\"\nVariations: \"Read this letter\"; \"What does this say?\"\nPresentation: Present the letter or word on a flashcard.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: towel, shoe, toothbrush\nDistractor stimuli: hat, phone\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy at independent prompt level across 3 sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "da2ef8be0d1b5601", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tracks print left to right", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "fr2", "error_correction": "four_step", "mastery_criterion": "mc_80_independent"}, "teacher_model": null, "seed_tag": "47307"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1818\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Mand + Writing\nDate range: Sessions 1\u20137 across 14 days (2026-03-17 to 2026-03-31)\n\nACCELERATION PROGRAMS\n1. ordering in a restaurant (Community)\n Method: Task Analysis\n2. making the bed (Home Skills)\n Method: Task Analysis\n3. requesting preferred items using AAC device (Mand)\n Method: NET\n4. copies simple words from model (Writing)\n Method: DTT\n5. identifying community safety signs (Community)\n Method: DTT\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: tangible\n\nSESSION DATA\n\nSession 1 \u2014 2026-03-17 \u2014 36 min \u2014 1 observer\n ordering in a restaurant: 8/15 correct (52%); latency 3.5s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d77\n making the bed: 5/8 correct (60%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n requesting preferred items using AAC device: 8/13 correct (62%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d79\n copies simple words from model: 6/12 correct (53%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d710\n identifying community safety signs: 10/15 correct (64%); latency 3.0s; prompts FP\u00d73, PP\u00d75, G\u00d71, I\u00d76\n Tantrum: freq 2, duration 8m total\n\nSession 2 \u2014 2026-03-19 \u2014 36 min \u2014 1 observer\n ordering in a restaurant: 8/14 correct (56%); latency 3.5s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d74\n making the bed: 8/15 correct (55%); latency 3.7s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d78\n requesting preferred items using AAC device: 7/11 correct (63%); latency 3.4s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d77\n copies simple words from model: 7/13 correct (54%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d75\n identifying community safety signs: 7/12 correct (62%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d77\n Tantrum: freq 2, duration 4m total\n\nSession 3 \u2014 2026-03-21 \u2014 IOA SESSION \u2014 2 observers\n ordering in a restaurant: 56% (primary); IOA 97% agreement\n making the bed: 55% (primary); IOA 97% agreement\n requesting preferred items using AAC device: 69% (primary); IOA 97% agreement\n copies simple words from model: 48% (primary); IOA 97% agreement\n identifying community safety signs: 65% (primary); IOA 97% agreement\n Tantrum: freq 7, duration 14m total; IOA 97% agreement\n\nSession 4 \u2014 2026-03-23 \u2014 36 min \u2014 1 observer\n ordering in a restaurant: 6/10 correct (57%); latency 3.4s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n making the bed: 7/11 correct (61%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d75\n requesting preferred items using AAC device: 8/11 correct (73%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n copies simple words from model: 8/13 correct (58%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d78\n identifying community safety signs: 7/10 correct (73%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n Tantrum: freq 7, duration 28m total\n\nSession 5 \u2014 2026-03-25 \u2014 36 min \u2014 1 observer\n ordering in a restaurant: 8/12 correct (67%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d74\n making the bed: 9/15 correct (61%); latency 3.0s; prompts FP\u00d74, PP\u00d75, G\u00d73, I\u00d73\n requesting preferred items using AAC device: 11/15 correct (73%); latency 2.6s; prompts FP\u00d72, PP\u00d75, G\u00d73, I\u00d75\n copies simple words from model: 5/9 correct (54%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n identifying community safety signs: 5/8 correct (69%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n Tantrum: freq 2, duration 6m total\n\nSession 6 \u2014 2026-03-27 \u2014 36 min \u2014 1 observer\n ordering in a restaurant: 8/13 correct (64%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d78\n making the bed: 9/15 correct (60%); latency 3.1s; prompts FP\u00d75, PP\u00d74, G\u00d74, I\u00d72\n requesting preferred items using AAC device: 8/11 correct (74%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n copies simple words from model: 7/13 correct (53%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d77\n identifying community safety signs: 6/9 correct (67%); latency 2.8s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d75\n Tantrum: freq 2, duration 8m total\n\nSession 7 \u2014 2026-03-29 \u2014 36 min \u2014 1 observer\n ordering in a restaurant: 6/9 correct (67%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n making the bed: 7/10 correct (66%); latency 3.3s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n requesting preferred items using AAC device: 11/14 correct (78%); latency 2.2s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d76\n copies simple words from model: 6/12 correct (51%); latency 4.0s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d77\n identifying community safety signs: 7/10 correct (75%); latency 2.8s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n Tantrum: freq 2, duration 6m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Attempts at property destruction (throwing materials, swiping items off the surface)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Peer aggression (hitting or pushing peers during group activities)\n- Pushing materials away from the work area\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nTantrum: tangible\n Evidence: behavior occurs when preferred items are restricted and is followed by access to the item.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data with IOA evidence.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 60.1%.\n- Trend direction: upward (first session: 52%, last session: 67%).\n- Tantrum: mean 3.4/session (early-window mean 2.0 -> late-window mean 2.0).\n- IOA data: 97% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "e438e7118ca6b489", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Tantrum": "tangible"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "adolescent", "n_sessions": 7, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["tantrum"], "behavior_functions": ["tangible"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "41987"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9045\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Mand + Tact\nDate range: Sessions 1\u201312 across 24 days (2026-06-11 to 2026-07-05)\n\nACCELERATION PROGRAMS\n1. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n2. selects items by feature (Listener Responding)\n Method: DTT\n3. tacts common objects (Tact)\n Method: DTT\n4. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Elopement \u2014 function hypothesized: automatic\n2. Tantrum \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-11 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 6/8 correct (73%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n selects items by feature: 9/13 correct (66%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d712\n tacts common objects: 8/12 correct (70%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 12/15 correct (77%); latency 2.5s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d77\n Elopement: freq 2\n Tantrum: freq 2, duration 10m total\n\nSession 2 \u2014 2026-06-13 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 9/13 correct (71%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d79\n selects items by feature: 8/14 correct (59%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n tacts common objects: 10/14 correct (71%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d711\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/13 correct (73%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d78\n Elopement: freq 1\n Tantrum: freq 2, duration 6m total\n\nSession 3 \u2014 2026-06-15 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 5/9 correct (60%); latency 3.3s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n selects items by feature: 7/13 correct (55%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n tacts common objects: 6/9 correct (65%); latency 2.9s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/12 correct (61%); latency 3.3s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d73\n Elopement: freq 1\n Tantrum: freq 4, duration 8m total\n\nSession 4 \u2014 2026-06-17 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 6/14 correct (46%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d77\n selects items by feature: 4/8 correct (48%); latency 4.0s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n tacts common objects: 5/8 correct (58%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/15 correct (55%); latency 3.4s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d77\n Elopement: freq 2\n Tantrum: freq 4, duration 16m total\n\nSession 5 \u2014 2026-06-19 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 5/10 correct (48%); latency 3.7s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n selects items by feature: 6/14 correct (43%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n tacts common objects: 5/9 correct (52%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/15 correct (47%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d75, I\u00d79\n Elopement: freq 3\n Tantrum: freq 3, duration 15m total\n\nSession 6 \u2014 2026-06-21 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 5/15 correct (34%); latency 4.7s; prompts FP\u00d72, PP\u00d75, G\u00d71, I\u00d77\n selects items by feature: 3/11 correct (31%); latency 4.8s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n tacts common objects: 6/14 correct (44%); latency 4.0s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d710\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/8 correct (47%); latency 4.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n Elopement: freq 3\n Tantrum: freq 4, duration 20m total\n\nSession 7 \u2014 2026-06-23 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 4/14 correct (29%); latency 4.5s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d78\n selects items by feature: 3/14 correct (23%); latency 4.8s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d78\n tacts common objects: 4/9 correct (47%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/11 correct (37%); latency 4.5s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n Elopement: freq 3\n Tantrum: freq 3, duration 6m total\n\nSession 8 \u2014 2026-06-25 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 3/15 correct (23%); latency 4.7s; prompts FP\u00d75, PP\u00d70, G\u00d72, I\u00d78\n selects items by feature: 3/15 correct (19%); latency 5.3s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d712\n tacts common objects: 5/11 correct (42%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/12 correct (34%); latency 4.8s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d73\n Elopement: freq 3\n Tantrum: freq 5, duration 15m total\n\nSession 9 \u2014 2026-06-27 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 1/11 correct (12%); latency 5.2s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n selects items by feature: 2/15 correct (14%); latency 5.7s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d711\n tacts common objects: 4/13 correct (32%); latency 4.5s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d79\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/15 correct (28%); latency 4.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d711\n Elopement: freq 4\n Tantrum: freq 4, duration 16m total\n\nSession 10 \u2014 2026-06-29 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 1/14 correct (10%); latency 5.5s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d78\n selects items by feature: 1/14 correct (10%); latency 5.8s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d711\n tacts common objects: 4/10 correct (36%); latency 4.7s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 3/14 correct (21%); latency 4.8s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d76\n Elopement: freq 3\n Tantrum: freq 5, duration 15m total\n\nSession 11 \u2014 2026-07-01 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 1/11 correct (10%); latency 5.4s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n selects items by feature: 1/9 correct (10%); latency 5.7s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n tacts common objects: 2/8 correct (24%); latency 5.0s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 2/11 correct (14%); latency 5.4s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n Elopement: freq 4\n Tantrum: freq 6, duration 24m total\n\nSession 12 \u2014 2026-07-03 \u2014 33 min \u2014 1 observer\n follows 1-step motor instructions: 2/15 correct (10%); latency 5.7s; prompts FP\u00d75, PP\u00d72, G\u00d72, I\u00d76\n selects items by feature: 1/8 correct (10%); latency 5.3s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n tacts common objects: 3/12 correct (24%); latency 5.1s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 1/14 correct (10%); latency 5.6s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d77\n Elopement: freq 4\n Tantrum: freq 5, duration 25m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Turning away from task or staff\n- Increased response latency (3\u20135\u00d7 baseline)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 73% to 10% across 12 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nElopement: automatic\n Evidence: behavior persists across contexts without clear social mediation.\nTantrum: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 35.4%.\n- Trend direction: downward (first session: 73%, last session: 10%).\n- Elopement: mean 2.8/session (early-window mean 1.5 -> late-window mean 3.8).\n- Tantrum: mean 3.9/session (early-window mean 3.0 -> late-window mean 5.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "86b21efbc1764ec5", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Elopement": "automatic", "Tantrum": "escape"}, "escalation_level": 4, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "early", "n_sessions": 12, "n_programs": 4, "n_behaviors": 2, "behavior_ids": ["elopement", "tantrum"], "behavior_functions": ["automatic", "escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "57327"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: putting on a shirt (pullover)\nCurriculum: AFLS Basic Living Skills\nLearner: Adult Learner\nMastery Status: Developing\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: putting on a shirt (pullover)\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Developing\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Hold the shirt with the front facing away.\n2. Place both arms into the sleeves.\n3. Pull the opening over the head.\n4. Push arms through the sleeves fully.\n5. Pull the bottom of the shirt down to straighten it.\n\n## Prompt Strategy Per Step\nStrategy: Most-to-Least\nStart with full-physical prompt at each step; fade to partial physical, gestural, verbal, independent.\nCurrent prompt level: At the developing stage, use full-physical or partial-physical prompts at each step; fade systematically.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "5c576fdd565d9397", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "putting on a shirt (pullover)", "program_type": "independence", "learner_profile": "adult", "mastery_state": "developing", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "putting on a shirt (pullover)", "module": "basic_living", "mastery_criterion": "mc_self_initiation", "chain_type": "total_task", "prompt_strategy": "most_to_least", "reinforcement_schedule": "crf_per_step", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "75542"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: engages in social games (peek-a-boo, tickle)\nCurriculum: Social Behavior & Social Play L1\nLearner: Early Learner\nMastery Status: Mastered at current level\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: engages in social games (peek-a-boo, tickle)\n- Curriculum: Social Behavior & Social Play L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: shared snack.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's shared snack routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "3544c885f5b9153e", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "engages in social games (peek-a-boo, tickle)", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "time_delay", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "16366"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: crossing a street safely\nCurriculum: AFLS Community Participation Skills\nLearner: Adult Learner\nMastery Status: Generalization phase\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: crossing a street safely\n- Curriculum: AFLS Community Participation Skills\n- Learner: Adult Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Approach the crosswalk and stop at the curb.\n2. Look left, look right, look left again.\n3. Identify the walk signal or absence of traffic.\n4. Begin to cross while continuing to scan for vehicles.\n5. Cross directly to the opposite curb.\n6. Step up onto the sidewalk.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 90s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "748e3971ed7eb394", "gold_labels": {"method": "task_analysis", "domain": "AFLS.community", "skill": "crossing a street safely", "program_type": "independence", "learner_profile": "adult", "mastery_state": "generalization", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "crossing a street safely", "module": "community", "mastery_criterion": "mc_fluent_chain", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "98892"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6427\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Mand + Tolerating Denied Access\nDate range: Sessions 1\u20139 across 18 days (2026-06-07 to 2026-06-25)\n\nACCELERATION PROGRAMS\n1. doing laundry (Home Skills)\n Method: Task Analysis\n2. requesting a break during extended tasks (Mand)\n Method: NET\n3. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n4. simple meal preparation (Home Skills)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: tangible\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-07 \u2014 39 min \u2014 1 observer\n doing laundry: 7/9 correct (79%); latency 2.6s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d76\n requesting a break during extended tasks: 6/8 correct (81%); latency 2.1s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n wait calmly when a preferred activity is denied: 7/10 correct (69%); latency 3.0s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n simple meal preparation: 9/11 correct (86%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d75\n Tantrum: freq 1, duration 5m total\n\nSession 2 \u2014 2026-06-09 \u2014 39 min \u2014 1 observer\n doing laundry: 9/11 correct (80%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d74\n requesting a break during extended tasks: 10/12 correct (83%); latency 2.2s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d78\n wait calmly when a preferred activity is denied: 11/15 correct (72%); latency 2.7s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d77\n simple meal preparation: 11/14 correct (82%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d711\n Tantrum: freq 1, duration 4m total\n\nSession 3 \u2014 2026-06-11 \u2014 39 min \u2014 1 observer\n doing laundry: 6/8 correct (80%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n requesting a break during extended tasks: 6/8 correct (80%); latency 2.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n wait calmly when a preferred activity is denied: 6/8 correct (72%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n simple meal preparation: 7/9 correct (82%); latency 2.1s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n Tantrum: freq 1, duration 3m total\n\nSession 4 \u2014 2026-06-13 \u2014 39 min \u2014 1 observer\n doing laundry: 4/9 correct (46%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d73\n requesting a break during extended tasks: 4/8 correct (44%); latency 4.2s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 4/9 correct (43%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d76\n simple meal preparation: 5/9 correct (51%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n Tantrum: freq 0\n\nSession 5 \u2014 2026-06-15 \u2014 39 min \u2014 1 observer\n doing laundry: 5/11 correct (46%); latency 3.7s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d77\n requesting a break during extended tasks: 5/11 correct (47%); latency 4.1s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 5/11 correct (44%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d78\n simple meal preparation: 6/11 correct (53%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n Tantrum: freq 0\n\nSession 6 \u2014 2026-06-17 \u2014 39 min \u2014 1 observer\n doing laundry: 7/15 correct (46%); latency 4.1s; prompts FP\u00d70, PP\u00d75, G\u00d73, I\u00d77\n requesting a break during extended tasks: 5/11 correct (49%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n wait calmly when a preferred activity is denied: 6/13 correct (43%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d78\n simple meal preparation: 7/12 correct (55%); latency 3.7s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d73\n Tantrum: freq 1, duration 4m total\n\nSession 7 \u2014 2026-06-19 \u2014 IOA SESSION \u2014 2 observers\n doing laundry: 43% (primary); IOA 91% agreement\n requesting a break during extended tasks: 47% (primary); IOA 91% agreement\n wait calmly when a preferred activity is denied: 50% (primary); IOA 91% agreement\n simple meal preparation: 51% (primary); IOA 91% agreement\n Tantrum: freq 1, duration 4m total; IOA 91% agreement\n\nSession 8 \u2014 2026-06-21 \u2014 39 min \u2014 1 observer\n doing laundry: 5/11 correct (47%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n requesting a break during extended tasks: 8/15 correct (50%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d75, I\u00d76\n wait calmly when a preferred activity is denied: 4/8 correct (54%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n simple meal preparation: 5/9 correct (59%); latency 3.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n Tantrum: freq 0\n\nSession 9 \u2014 2026-06-23 \u2014 39 min \u2014 1 observer\n doing laundry: 7/14 correct (52%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n requesting a break during extended tasks: 7/13 correct (57%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d79\n wait calmly when a preferred activity is denied: 8/13 correct (63%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n simple meal preparation: 8/12 correct (68%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d74\n Tantrum: freq 2, duration 4m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Behavior Function Hypothesis\nTantrum: tangible\n Evidence: behavior occurs when preferred items are restricted and is followed by access to the item.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 9 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 57.6%.\n- Trend direction: downward (first session: 79%, last session: 52%).\n- Tantrum: mean 0.8/session (early-window mean 1.0 -> late-window mean 1.0).\n- IOA data: 91% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "9fbe31b7612cabb9", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {"Tantrum": "tangible"}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "adult", "n_sessions": 9, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["tantrum"], "behavior_functions": ["tangible"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "37908"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8223\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Mand + Reading + Tolerating Denied Access\nDate range: Sessions 1\u20139 across 18 days (2026-08-11 to 2026-08-29)\n\nACCELERATION PROGRAMS\n1. reads 10\u201320 sight words (Reading)\n Method: DTT\n2. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n3. indicating completion ('all done', 'finished') (Mand)\n Method: NET\n4. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n5. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n\nDECELERATION TARGETS\n1. Property destruction \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-11 \u2014 38 min \u2014 1 observer\n reads 10\u201320 sight words: 6/9 correct (66%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n wait calmly when access to preferred item is denied: 9/14 correct (67%); latency 3.0s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d77\n indicating completion ('all done', 'finished'): 6/10 correct (62%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/13 correct (54%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n follows 1-step motor instructions: 8/12 correct (69%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d78\n Property destruction: freq 2\n\nSession 2 \u2014 2026-08-13 \u2014 38 min \u2014 1 observer\n reads 10\u201320 sight words: 5/8 correct (59%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n wait calmly when access to preferred item is denied: 5/9 correct (60%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n indicating completion ('all done', 'finished'): 7/12 correct (59%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/14 correct (54%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n follows 1-step motor instructions: 9/13 correct (72%); latency 2.8s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d75\n Property destruction: freq 1\n\nSession 3 \u2014 2026-08-15 \u2014 38 min \u2014 1 observer\n reads 10\u201320 sight words: 7/11 correct (67%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n wait calmly when access to preferred item is denied: 6/9 correct (62%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d72\n indicating completion ('all done', 'finished'): 8/11 correct (69%); latency 2.7s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/13 correct (56%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d75\n follows 1-step motor instructions: 9/13 correct (71%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d711\n Property destruction: freq 4\n\nSession 4 \u2014 2026-08-17 \u2014 38 min \u2014 1 observer\n reads 10\u201320 sight words: 6/8 correct (70%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n wait calmly when access to preferred item is denied: 6/10 correct (64%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d78\n indicating completion ('all done', 'finished'): 8/12 correct (68%); latency 2.7s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d711\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/11 correct (51%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n follows 1-step motor instructions: 7/11 correct (68%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n Property destruction: freq 5\n ABC (property destruction): A = staff engaged in paperwork nearby; B = yelled name + tapped staff; C = staff attended and redirected\n\nSession 5 \u2014 2026-08-19 \u2014 IOA SESSION \u2014 2 observers\n reads 10\u201320 sight words: 71% (primary); IOA 96% agreement\n wait calmly when access to preferred item is denied: 69% (primary); IOA 96% agreement\n indicating completion ('all done', 'finished'): 64% (primary); IOA 96% agreement\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 54% (primary); IOA 96% agreement\n follows 1-step motor instructions: 79% (primary); IOA 96% agreement\n Property destruction: freq 1; IOA 96% agreement\n\nSession 6 \u2014 2026-08-21 \u2014 38 min \u2014 1 observer\n reads 10\u201320 sight words: 6/10 correct (64%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n wait calmly when access to preferred item is denied: 8/12 correct (66%); latency 3.0s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d73\n indicating completion ('all done', 'finished'): 10/14 correct (74%); latency 2.5s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/9 correct (55%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n follows 1-step motor instructions: 7/10 correct (74%); latency 2.8s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n Property destruction: freq 1\n\nSession 7 \u2014 2026-08-23 \u2014 38 min \u2014 1 observer\n reads 10\u201320 sight words: 9/14 correct (65%); latency 3.4s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d76\n wait calmly when access to preferred item is denied: 11/14 correct (76%); latency 2.5s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d75\n indicating completion ('all done', 'finished'): 6/9 correct (71%); latency 2.5s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/13 correct (58%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d79\n follows 1-step motor instructions: 10/12 correct (80%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d76\n Property destruction: freq 2\n\nSession 8 \u2014 2026-08-25 \u2014 38 min \u2014 1 observer\n reads 10\u201320 sight words: 6/9 correct (71%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n wait calmly when access to preferred item is denied: 10/14 correct (74%); latency 2.4s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d79\n indicating completion ('all done', 'finished'): 6/8 correct (78%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/11 correct (54%); latency 3.5s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n follows 1-step motor instructions: 11/12 correct (88%); latency 1.9s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d75\n Property destruction: freq 1\n\nSession 9 \u2014 2026-08-27 \u2014 38 min \u2014 1 observer\n reads 10\u201320 sight words: 7/10 correct (65%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n wait calmly when access to preferred item is denied: 11/15 correct (75%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d75, I\u00d78\n indicating completion ('all done', 'finished'): 10/13 correct (75%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d711\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/10 correct (54%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n follows 1-step motor instructions: 9/11 correct (81%); latency 2.0s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d75\n Property destruction: freq 2\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Pushing materials away from the work area\n- Self-stimulatory behavior increase during demand periods\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nProperty destruction: attention\n Evidence: ABC events in the log support the attention function; behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 9 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 66.5%.\n- Trend direction: downward (first session: 66%, last session: 65%).\n- Property destruction: mean 2.1/session (early-window mean 2.3 -> late-window mean 1.7).\n- IOA data: 96% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "7c191178acb6612f", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Property destruction": "attention"}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "early", "n_sessions": 9, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["property_destruction"], "behavior_functions": ["attention"], "has_abc_data": true, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "23299"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: clocking in at start of shift\nCurriculum: AFLS Vocational Skills\nLearner: Adult Learner\nMastery Status: Emerging\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: clocking in at start of shift\n- Curriculum: AFLS Vocational Skills\n- Learner: Adult Learner\n- Current mastery: Emerging\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Arrive at the workplace by the scheduled time.\n2. Locate the time clock or digital system.\n3. Enter identification (ID card / badge / code).\n4. Confirm the clock-in timestamp.\n5. Notify the supervisor or check the day's task list.\n6. Proceed to the assigned workstation.\n\n## Prompt Strategy Per Step\nStrategy: Graduated Guidance\nHand-over-hand physical guidance with fading pressure; move to shadow, then independent.\nCurrent prompt level: At the emerging stage, provide hand-over-hand guidance at each step; reduce physical pressure across sessions.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed independently with 2 different adults in 2 different settings across 2 consecutive days.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "3f1ba02b0880c98d", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "clocking in at start of shift", "program_type": "independence", "learner_profile": "adult", "mastery_state": "emerging", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "clocking in at start of shift", "module": "vocational", "mastery_criterion": "mc_generalization", "chain_type": "total_task", "prompt_strategy": "graduated_guidance", "reinforcement_schedule": "crf_per_step", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "39765"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: writes numbers 1\u201310\nCurriculum: Writing L2\nLearner: Early Learner\nMastery Status: Mastered at current level\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: writes numbers 1\u201310\n- Curriculum: Writing L2\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: 6, 10, 3\nDistractor stimuli: 7, 2, 1, 8\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nToken economy \u2014 Tokens delivered per correct response; exchanged at session end for a back-up reinforcer appropriate to the learner (for children: candy, cookies, brief leisure-time access, preferred activity, screen time, or a favorite sensory item). Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "5979b1067f9cb981", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L2", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "writes numbers 1\u201310", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "token_economy", "error_correction": "transfer_trial", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "15942"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a toleration program for this self-care / medical / caregiver-delivered skill.\n\nTarget: tolerating tooth brushing by caregiver\nCurriculum: AFLS Basic Living Skills\nLearner: Adolescent Learner\nMastery Status: Mastered at current level\n\nPlease include the toleration end goal, shaping progression, antecedent strategies, reinforcement plan, refusal / safety procedures, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating tooth brushing by caregiver\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for tooth brushing performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nfull 2-minute tooth-brushing routine completed by caregiver without refusal, crying, SIB, or aggression\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1-second toothbrush contact with teeth\n2. 3 seconds of brushing\n3. 5 seconds of brushing\n4. 15 seconds of brushing\n5. 30 seconds of brushing\n6. 60 seconds of brushing\n7. Full 2-minute brushing routine\n\nCurrent shaping step: At the mastered stage, begin at shaping step 5 (\"30 seconds of brushing\") and advance through step 6 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal duration tolerated across 3 consecutive sessions with no safety behaviors (refusal, crying, SIB, aggression, property destruction).\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 2 different settings and with 3 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "b26eab424c93c320", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating tooth brushing by caregiver", "program_type": "toleration", "learner_profile": "adolescent", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating tooth brushing by caregiver", "module": "basic_living", "mastery_criterion": "mc_toleration_full_duration", "shaping_n_steps": 7}, "teacher_model": null, "seed_tag": "42817"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: completes simple 3\u20134 piece puzzles\nCurriculum: Visual Perceptual Skills & Matching-to-Sample L1\nLearner Level: Early Learner\nBaseline: Near mastery\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: completes simple 3\u20134 piece puzzles\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: napkin, sock, backpack\nDistractor stimuli: cup, bottle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "09bdbd5a14b3a9fa", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "completes simple 3\u20134 piece puzzles", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "fr2", "error_correction": "backstep", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "5667"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a chaining program for the following.\n\nSkill: completing assigned tasks in order\nCurriculum: AFLS Vocational Skills\nLearner Level: Adult Learner\nBaseline: Near mastery\n\nInclude the full Task Analysis structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: completing assigned tasks in order\n- Curriculum: AFLS Vocational Skills\n- Learner: Adult Learner\n- Current mastery: Near mastery\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Review the task list for the shift. <- Learner-taught step (forward chaining starts here)\n2. Gather needed materials for the first task.\n3. Complete the first task to the specified standard.\n4. Mark the first task complete on the list.\n5. Return materials to storage.\n6. Move to the next task on the list and repeat.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the near mastery stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nToken economy \u2014 One token per correctly-completed step; token exchange at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\n100% of steps completed independently (no prompts) across 3 consecutive trials of the full chain.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "efc84cccae744192", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "completing assigned tasks in order", "program_type": "independence", "learner_profile": "adult", "mastery_state": "near", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "completing assigned tasks in order", "module": "vocational", "mastery_criterion": "mc_all_steps_independent", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "57808"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: describes function of common objects\nCurriculum: Intraverbal L2\nLearner Level: School-Age Learner\nBaseline: Emerging\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: describes function of common objects\n- Curriculum: Intraverbal L2\n- Learner: School-Age Learner\n- Current mastery: Emerging\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: transition conversation.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's transition conversation routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the emerging stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use with a peer in unstructured free play across 2 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "d5fdbe0e45328959", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L2", "learner_profile": "school_age", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "describes function of common objects", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_peer_initiation"}, "teacher_model": null, "seed_tag": "70185"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8285\nProfile: Adult Learner (18+ years)\nCurricula: Independent Living + Mand + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u201312 across 24 days (2026-07-18 to 2026-08-11)\n\nACCELERATION PROGRAMS\n1. requesting a break during extended tasks (Mand)\n Method: NET\n2. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n3. indicating 'all done' at task completion (Mand)\n Method: NET\n4. managing a budget (Independent Living)\n Method: Task Analysis\n5. self-advocacy statements (Independent Living)\n Method: BST\n6. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n\nDECELERATION TARGETS\n1. Pica \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-18 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 6/13 correct (43%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d712\n completing assigned tasks in order: 4/11 correct (40%); latency 4.2s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d77\n indicating 'all done' at task completion: 5/11 correct (43%); latency 4.1s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n managing a budget: 8/15 correct (51%); latency 3.7s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d76\n self-advocacy statements: 5/15 correct (37%); latency 4.4s; prompts FP\u00d75, PP\u00d70, G\u00d71, I\u00d79\n wait calmly when a preferred activity is denied: 4/10 correct (43%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n Pica: attempts 0\n\nSession 2 \u2014 2026-07-20 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 5/11 correct (46%); latency 4.2s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n completing assigned tasks in order: 3/9 correct (37%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n indicating 'all done' at task completion: 6/11 correct (53%); latency 3.3s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d76\n managing a budget: 4/8 correct (50%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n self-advocacy statements: 6/13 correct (46%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d711\n wait calmly when a preferred activity is denied: 5/11 correct (47%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d77\n Pica: attempts 1 (1 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 3 \u2014 2026-07-22 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 6/13 correct (50%); latency 3.8s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d75\n completing assigned tasks in order: 4/9 correct (48%); latency 3.7s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n indicating 'all done' at task completion: 6/10 correct (58%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n managing a budget: 6/9 correct (61%); latency 3.4s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d76\n self-advocacy statements: 6/11 correct (52%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d76\n wait calmly when a preferred activity is denied: 7/14 correct (48%); latency 3.7s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d76\n Pica: attempts 2 (1 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 4 \u2014 2026-07-24 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 6/10 correct (59%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n completing assigned tasks in order: 7/13 correct (51%); latency 3.8s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d78\n indicating 'all done' at task completion: 10/14 correct (71%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d79\n managing a budget: 6/9 correct (62%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n self-advocacy statements: 5/9 correct (57%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n wait calmly when a preferred activity is denied: 9/15 correct (60%); latency 3.1s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d76\n Pica: attempts 1 (0 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 5 \u2014 2026-07-26 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 8/13 correct (64%); latency 3.4s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d73\n completing assigned tasks in order: 6/11 correct (59%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n indicating 'all done' at task completion: 6/8 correct (76%); latency 2.7s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n managing a budget: 10/14 correct (74%); latency 2.6s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d79\n self-advocacy statements: 9/14 correct (65%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d77\n wait calmly when a preferred activity is denied: 5/8 correct (65%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n Pica: attempts 1 (0 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 6 \u2014 2026-07-28 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 6/9 correct (69%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n completing assigned tasks in order: 9/15 correct (58%); latency 3.5s; prompts FP\u00d75, PP\u00d73, G\u00d71, I\u00d76\n indicating 'all done' at task completion: 9/12 correct (78%); latency 2.6s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d72\n managing a budget: 12/15 correct (79%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d75, I\u00d78\n self-advocacy statements: 6/8 correct (73%); latency 2.6s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n wait calmly when a preferred activity is denied: 5/8 correct (65%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n Pica: attempts 1 (1 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 7 \u2014 2026-07-30 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 7/9 correct (74%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n completing assigned tasks in order: 7/10 correct (67%); latency 3.0s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d72\n indicating 'all done' at task completion: 9/10 correct (91%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n managing a budget: 8/10 correct (80%); latency 2.2s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n self-advocacy statements: 10/13 correct (81%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n wait calmly when a preferred activity is denied: 9/14 correct (67%); latency 2.7s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d710\n Pica: attempts 1 (1 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 8 \u2014 2026-08-01 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 7/9 correct (78%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n completing assigned tasks in order: 10/13 correct (75%); latency 2.6s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d78\n indicating 'all done' at task completion: 12/13 correct (94%); latency 2.0s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d78\n managing a budget: 12/14 correct (89%); latency 2.0s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d79\n self-advocacy statements: 8/9 correct (87%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n wait calmly when a preferred activity is denied: 9/12 correct (75%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d79\n Pica: attempts 0\n\nSession 9 \u2014 2026-08-03 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 10/13 correct (76%); latency 2.6s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n completing assigned tasks in order: 7/9 correct (83%); latency 2.2s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n indicating 'all done' at task completion: 10/10 correct (95%); latency 1.7s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n managing a budget: 14/15 correct (93%); latency 1.9s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d710\n self-advocacy statements: 11/12 correct (95%); latency 1.9s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d74\n wait calmly when a preferred activity is denied: 9/11 correct (85%); latency 2.0s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n Pica: attempts 1 (1 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 10 \u2014 2026-08-05 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 11/14 correct (82%); latency 2.1s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d76\n completing assigned tasks in order: 9/11 correct (82%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n indicating 'all done' at task completion: 10/10 correct (95%); latency 1.7s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n managing a budget: 8/8 correct (95%); latency 1.6s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n self-advocacy statements: 10/10 correct (95%); latency 1.9s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 9/10 correct (86%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d77\n Pica: attempts 0\n\nSession 11 \u2014 2026-08-07 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 10/12 correct (87%); latency 2.1s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d76\n completing assigned tasks in order: 11/12 correct (92%); latency 1.6s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d73\n indicating 'all done' at task completion: 9/9 correct (95%); latency 1.9s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d73\n managing a budget: 8/8 correct (95%); latency 1.7s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n self-advocacy statements: 10/10 correct (95%); latency 1.7s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n wait calmly when a preferred activity is denied: 10/11 correct (90%); latency 1.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n Pica: attempts 1 (1 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 12 \u2014 2026-08-09 \u2014 42 min \u2014 1 observer\n requesting a break during extended tasks: 11/13 correct (87%); latency 2.0s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d76\n completing assigned tasks in order: 12/13 correct (95%); latency 2.0s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d72\n indicating 'all done' at task completion: 10/11 correct (95%); latency 1.9s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n managing a budget: 9/9 correct (95%); latency 2.0s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n self-advocacy statements: 13/14 correct (95%); latency 2.0s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d710\n wait calmly when a preferred activity is denied: 9/10 correct (93%); latency 1.9s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d77\n Pica: attempts 2 (1 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Quick response latency (within 2\u20133 seconds)\n- Appropriate sitting posture maintained\n- Reaching for materials proactively\n- Smiling during reinforcement delivery\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- Steady improvement: accuracy rose from 43% to 87% across 12 sessions.\n- No clinical concerns at this time; mastery criteria should be reachable within a few additional sessions.\n\n## Pattern Classification\nmastery_progression\n\nAccuracy is ascending cleanly across sessions with no interfering behaviors, consistent with a mastery-progression trajectory.\n\n## Behavior Function Hypothesis\nPica: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Continue current teaching procedure \u2014 it is effective for this learner.\n- Maintain current stimulus arrangement; begin planning next skill in sequence.\n\n### Consequence strategies\n- Begin thinning reinforcement from CRF to FR-2 as accuracy stabilizes above 85%.\n- Continue differential reinforcement for independent responses.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 67.8%.\n- Trend direction: upward (first session: 43%, last session: 87%).\n- Pica: mean 0.9/session (early-window mean 1.0 -> late-window mean 1.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "16ed6f0f450e545e", "gold_labels": {"pattern_class": "mastery_progression", "behavior_functions": {"Pica": "automatic"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "mastery_progression", "learner_profile": "adult", "n_sessions": 12, "n_programs": 6, "n_behaviors": 1, "behavior_ids": ["pica"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "20691"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: scheduling a medical appointment\nCurriculum: AFLS Independent Living Skills\nLearner: Adult Learner\nMastery Status: Generalization phase\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: scheduling a medical appointment\n- Curriculum: AFLS Independent Living Skills\n- Learner: Adult Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Identify the reason for the appointment. <- Learner-taught step (forward chaining starts here)\n2. Locate the provider's contact information.\n3. Call or use the online system.\n4. Provide name, date of birth, and insurance information.\n5. Request an available appointment time.\n6. Confirm the appointment and save it to the calendar.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "498c53a8430cff22", "gold_labels": {"method": "task_analysis", "domain": "AFLS.independent_living", "skill": "scheduling a medical appointment", "program_type": "independence", "learner_profile": "adult", "mastery_state": "generalization", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "scheduling a medical appointment", "module": "independent_living", "mastery_criterion": "mc_self_initiation", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "50550"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: tacts common animals\nCurriculum: Tact L1\nLearner: Early Learner\nMastery Status: Near mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts common animals\n- Curriculum: Tact L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What animal is this?\"\nVariations: \"What is this?\"; \"Name this animal\"\nPresentation: Present an animal picture card and ask while pointing.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: frog, lion, horse\nDistractor stimuli: elephant, rabbit\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "33dfb6b1b25a4cbf", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts common animals", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "vr3", "error_correction": "backstep", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "69141"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3420\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Self-Care\nDate range: Sessions 1\u20138 across 16 days (2026-06-01 to 2026-06-17)\n\nACCELERATION PROGRAMS\n1. tolerating haircut (Self-Care)\n Method: Task Analysis\n2. ordering in a restaurant (Community)\n Method: Task Analysis\n3. identifying community safety signs (Community)\n Method: DTT\n4. tolerating tooth brushing by caregiver (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Toileting accident (urine or bowel) \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-01 \u2014 42 min \u2014 1 observer\n tolerating haircut: 10/14 correct (71%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d74\n ordering in a restaurant: 7/10 correct (67%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d75\n identifying community safety signs: 11/13 correct (85%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n tolerating tooth brushing by caregiver: 12/15 correct (80%); latency 2.5s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d710\n Toileting accident (urine or bowel): urine: 4 in-toilet / 1 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 2 \u2014 2026-06-03 \u2014 42 min \u2014 1 observer\n tolerating haircut: 9/12 correct (71%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d77\n ordering in a restaurant: 6/9 correct (64%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d73\n identifying community safety signs: 8/11 correct (72%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n tolerating tooth brushing by caregiver: 10/14 correct (72%); latency 2.7s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d75\n Toileting accident (urine or bowel): urine: 3 in-toilet / 3 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 3 \u2014 2026-06-05 \u2014 42 min \u2014 1 observer\n tolerating haircut: 7/11 correct (63%); latency 3.2s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n ordering in a restaurant: 7/11 correct (62%); latency 3.3s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n identifying community safety signs: 8/13 correct (64%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n tolerating tooth brushing by caregiver: 9/15 correct (63%); latency 3.2s; prompts FP\u00d75, PP\u00d72, G\u00d71, I\u00d77\n Toileting accident (urine or bowel): urine: 2 in-toilet / 2 accidents; BM: 0 in-toilet / 0 accidents\n ABC (toileting accident (urine or bowel)): A = transition from preferred activity to non-preferred task; B = voided (urine) en route to the work area; C = staff redirected to bathroom, changed clothing\n\nSession 4 \u2014 2026-06-07 \u2014 42 min \u2014 1 observer\n tolerating haircut: 7/13 correct (54%); latency 3.3s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n ordering in a restaurant: 7/12 correct (58%); latency 3.3s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d77\n identifying community safety signs: 9/15 correct (62%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d76\n tolerating tooth brushing by caregiver: 7/11 correct (64%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n Toileting accident (urine or bowel): urine: 3 in-toilet / 4 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 5 \u2014 2026-06-09 \u2014 42 min \u2014 1 observer\n tolerating haircut: 4/10 correct (44%); latency 4.0s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d76\n ordering in a restaurant: 6/14 correct (46%); latency 4.1s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n identifying community safety signs: 6/11 correct (52%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n tolerating tooth brushing by caregiver: 7/13 correct (52%); latency 3.6s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d77\n Toileting accident (urine or bowel): urine: 0 in-toilet / 5 accidents; BM: 0 in-toilet / 0 accidents\n ABC (toileting accident (urine or bowel)): A = transition from preferred activity to non-preferred task; B = voided (urine) en route to the work area; C = staff redirected to bathroom, changed clothing\n\nSession 6 \u2014 2026-06-11 \u2014 42 min \u2014 1 observer\n tolerating haircut: 5/12 correct (40%); latency 4.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n ordering in a restaurant: 4/10 correct (42%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d76\n identifying community safety signs: 4/9 correct (47%); latency 4.0s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n tolerating tooth brushing by caregiver: 7/13 correct (51%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d76\n Toileting accident (urine or bowel): urine: 1 in-toilet / 4 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 7 \u2014 2026-06-13 \u2014 42 min \u2014 1 observer\n tolerating haircut: 5/15 correct (32%); latency 4.5s; prompts FP\u00d75, PP\u00d70, G\u00d75, I\u00d75\n ordering in a restaurant: 5/14 correct (34%); latency 4.3s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d711\n identifying community safety signs: 4/10 correct (36%); latency 4.2s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d74\n tolerating tooth brushing by caregiver: 7/15 correct (45%); latency 4.2s; prompts FP\u00d70, PP\u00d75, G\u00d73, I\u00d77\n Toileting accident (urine or bowel): urine: 2 in-toilet / 4 accidents; BM: 0 in-toilet / 2 accidents\n\nSession 8 \u2014 2026-06-15 \u2014 42 min \u2014 1 observer\n tolerating haircut: 3/9 correct (28%); latency 4.6s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n ordering in a restaurant: 5/14 correct (35%); latency 4.4s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d78\n identifying community safety signs: 2/9 correct (27%); latency 4.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n tolerating tooth brushing by caregiver: 4/11 correct (32%); latency 4.8s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n Toileting accident (urine or bowel): urine: 0 in-toilet / 5 accidents; BM: 1 in-toilet / 0 accidents\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Crying during demand presentation\n- Turning away from task or staff"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (71% -> 28%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nToileting accident (urine or bowel): escape\n Evidence: ABC events in the log support the escape function; behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 50.5%.\n- Trend direction: downward (first session: 71%, last session: 28%).\n- Toileting accident (urine or bowel): mean 4.0/session (early-window mean 2.5 -> late-window mean 5.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "47144ed42308d4ac", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Toileting accident (urine or bowel)": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "adolescent", "n_sessions": 8, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["toileting_accident"], "behavior_functions": ["escape"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "94010"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8754\nProfile: Adult Learner (18+ years)\nCurricula: Community + Home Skills + Mand + Self-Care + Vocational\nDate range: Sessions 1\u201311 across 22 days (2026-02-17 to 2026-03-11)\n\nACCELERATION PROGRAMS\n1. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n2. requesting assistance using AAC device (Mand)\n Method: NET\n3. using public transportation (Community)\n Method: Task Analysis\n4. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n5. simple meal preparation (Home Skills)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Mouthing \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-17 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 9/13 correct (71%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n requesting assistance using AAC device: 8/11 correct (77%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d710\n using public transportation: 7/8 correct (84%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n completing assigned tasks in order: 9/12 correct (76%); latency 2.6s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d75\n simple meal preparation: 8/11 correct (76%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n Mouthing: freq 2; PIR 12%\n\nSession 2 \u2014 2026-02-19 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 11/15 correct (74%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d712\n requesting assistance using AAC device: 8/11 correct (74%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n using public transportation: 9/10 correct (85%); latency 2.4s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n completing assigned tasks in order: 6/8 correct (71%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n simple meal preparation: 10/13 correct (76%); latency 2.6s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d79\n Mouthing: freq 0; PIR 4%\n\nSession 3 \u2014 2026-02-21 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 8/11 correct (76%); latency 2.7s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d79\n requesting assistance using AAC device: 7/10 correct (72%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n using public transportation: 6/8 correct (78%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n completing assigned tasks in order: 8/11 correct (73%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n simple meal preparation: 6/8 correct (78%); latency 2.2s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n Mouthing: freq 2; PIR 13%\n\nSession 4 \u2014 2026-02-23 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 4/12 correct (33%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n requesting assistance using AAC device: 4/9 correct (39%); latency 4.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n using public transportation: 5/12 correct (45%); latency 4.2s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d74\n completing assigned tasks in order: 4/9 correct (45%); latency 3.8s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d73\n simple meal preparation: 4/8 correct (45%); latency 3.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n Mouthing: freq 1; PIR 10%\n\nSession 5 \u2014 2026-02-25 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 3/8 correct (36%); latency 4.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n requesting assistance using AAC device: 4/12 correct (36%); latency 4.2s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d73\n using public transportation: 4/9 correct (47%); latency 3.9s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n completing assigned tasks in order: 6/13 correct (47%); latency 3.8s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n simple meal preparation: 6/12 correct (48%); latency 3.7s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d76\n Mouthing: freq 1; PIR 6%\n\nSession 6 \u2014 2026-02-27 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 4/11 correct (36%); latency 4.4s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n requesting assistance using AAC device: 5/11 correct (44%); latency 3.9s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n using public transportation: 4/8 correct (55%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n completing assigned tasks in order: 6/11 correct (54%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n simple meal preparation: 7/14 correct (53%); latency 3.6s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d78\n Mouthing: freq 1; PIR 12%\n\nSession 7 \u2014 2026-03-01 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 4/11 correct (35%); latency 4.6s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n requesting assistance using AAC device: 4/9 correct (47%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n using public transportation: 6/10 correct (60%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n completing assigned tasks in order: 7/11 correct (61%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d76\n simple meal preparation: 8/14 correct (60%); latency 3.0s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d77\n Mouthing: freq 1; PIR 13%\n\nSession 8 \u2014 2026-03-03 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 5/12 correct (40%); latency 4.2s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d76\n requesting assistance using AAC device: 8/15 correct (54%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d79\n using public transportation: 8/12 correct (67%); latency 2.8s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d78\n completing assigned tasks in order: 9/13 correct (68%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d710\n simple meal preparation: 10/15 correct (66%); latency 3.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d79\n Mouthing: freq 0; PIR 2%\n\nSession 9 \u2014 2026-03-05 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 4/9 correct (50%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n requesting assistance using AAC device: 8/14 correct (59%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d714\n using public transportation: 10/14 correct (71%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d77\n completing assigned tasks in order: 7/10 correct (73%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d77\n simple meal preparation: 7/9 correct (74%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d78\n Mouthing: freq 0; PIR 6%\n\nSession 10 \u2014 2026-03-07 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 8/14 correct (61%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d79\n requesting assistance using AAC device: 7/10 correct (69%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n using public transportation: 11/15 correct (76%); latency 2.5s; prompts FP\u00d75, PP\u00d71, G\u00d72, I\u00d77\n completing assigned tasks in order: 7/9 correct (73%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n simple meal preparation: 9/12 correct (79%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d75\n Mouthing: freq 2; PIR 14%\n\nSession 11 \u2014 2026-03-09 \u2014 53 min \u2014 1 observer\n dressing (pants, shirt): 7/10 correct (72%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n requesting assistance using AAC device: 9/12 correct (75%); latency 2.9s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d710\n using public transportation: 6/8 correct (80%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n completing assigned tasks in order: 9/13 correct (73%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d711\n simple meal preparation: 12/15 correct (79%); latency 2.7s; prompts FP\u00d73, PP\u00d75, G\u00d75, I\u00d72\n Mouthing: freq 1; PIR 9%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Looking away during SD presentation\n- Playing with non-task materials\n- Leaving seat without permission"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Behavior Function Hypothesis\nMouthing: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 53.1%.\n- Trend direction: upward (first session: 71%, last session: 72%).\n- Mouthing: mean 1.0/session (early-window mean 1.3 -> late-window mean 1.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "414037a2432bb275", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {"Mouthing": "automatic"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "adult", "n_sessions": 11, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["mouthing"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "2880"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: provides definitions of words\nCurriculum: Intraverbal L3\nLearner: School-Age Learner\nMastery Status: Mastered at current level\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: provides definitions of words\n- Curriculum: Intraverbal L3\n- Learner: School-Age Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: post-activity debrief.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's post-activity debrief routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use with a peer in unstructured free play across 2 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "b5331fa15b5b19d4", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L3", "learner_profile": "school_age", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "provides definitions of words", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_peer_initiation"}, "teacher_model": null, "seed_tag": "76914"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9260\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Motor Imitation + Tact + Writing\nDate range: Sessions 1\u20138 across 16 days (2026-06-04 to 2026-06-20)\n\nACCELERATION PROGRAMS\n1. copies simple words from model (Writing)\n Method: DTT\n2. tacts common objects (Tact)\n Method: DTT\n3. selects items by feature (Listener Responding)\n Method: DTT\n4. imitates 3-step motor sequences (Motor Imitation)\n Method: DTT variant\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: escape\n2. Toileting accident (urine or bowel) \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-04 \u2014 47 min \u2014 1 observer\n copies simple words from model: 7/10 correct (73%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n tacts common objects: 11/14 correct (80%); latency 2.3s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d75\n selects items by feature: 6/8 correct (70%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n imitates 3-step motor sequences: 10/12 correct (81%); latency 2.4s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d72\n Tantrum: freq 1, duration 4m total\n Toileting accident (urine or bowel): urine: 2 in-toilet / 3 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 2 \u2014 2026-06-06 \u2014 47 min \u2014 1 observer\n copies simple words from model: 6/10 correct (65%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n tacts common objects: 10/15 correct (67%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d79\n selects items by feature: 9/13 correct (70%); latency 2.7s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n imitates 3-step motor sequences: 10/13 correct (73%); latency 2.4s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d78\n Tantrum: freq 2, duration 6m total\n Toileting accident (urine or bowel): urine: 3 in-toilet / 2 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 3 \u2014 2026-06-08 \u2014 47 min \u2014 1 observer\n copies simple words from model: 6/10 correct (63%); latency 3.0s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d76\n tacts common objects: 9/13 correct (68%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d75\n selects items by feature: 6/10 correct (61%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n imitates 3-step motor sequences: 9/12 correct (73%); latency 2.8s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d75\n Tantrum: freq 2, duration 6m total\n Toileting accident (urine or bowel): urine: 2 in-toilet / 2 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 4 \u2014 2026-06-10 \u2014 47 min \u2014 1 observer\n copies simple words from model: 6/10 correct (58%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d73\n tacts common objects: 6/10 correct (57%); latency 3.7s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n selects items by feature: 7/13 correct (56%); latency 3.5s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n imitates 3-step motor sequences: 7/11 correct (59%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d710\n Tantrum: freq 3, duration 9m total\n Toileting accident (urine or bowel): urine: 3 in-toilet / 1 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 5 \u2014 2026-06-12 \u2014 47 min \u2014 1 observer\n copies simple words from model: 6/14 correct (45%); latency 4.0s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n tacts common objects: 5/9 correct (54%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n selects items by feature: 7/15 correct (48%); latency 3.9s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d711\n imitates 3-step motor sequences: 6/9 correct (62%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n Tantrum: freq 2, duration 6m total\n Toileting accident (urine or bowel): urine: 1 in-toilet / 4 accidents; BM: 0 in-toilet / 0 accidents\n ABC (tantrum): A = demand to complete math problem; B = threw materials and vocalized 'no'; C = staff removed demand, redirected\n\nSession 6 \u2014 2026-06-14 \u2014 47 min \u2014 1 observer\n copies simple words from model: 5/12 correct (42%); latency 4.3s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d75\n tacts common objects: 7/13 correct (54%); latency 3.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d712\n selects items by feature: 5/10 correct (49%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n imitates 3-step motor sequences: 6/11 correct (52%); latency 3.6s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n Tantrum: freq 4, duration 16m total\n Toileting accident (urine or bowel): urine: 1 in-toilet / 4 accidents; BM: 0 in-toilet / 0 accidents\n ABC (tantrum): A = asked to finish dressing task; B = kicked at materials; C = task paused for 3 min\n\nSession 7 \u2014 2026-06-16 \u2014 47 min \u2014 1 observer\n copies simple words from model: 3/9 correct (28%); latency 4.7s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n tacts common objects: 7/14 correct (49%); latency 3.8s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d79\n selects items by feature: 5/12 correct (38%); latency 4.1s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d76\n imitates 3-step motor sequences: 6/12 correct (50%); latency 3.9s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d76\n Tantrum: freq 4, duration 12m total\n Toileting accident (urine or bowel): urine: 1 in-toilet / 3 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 8 \u2014 2026-06-18 \u2014 47 min \u2014 1 observer\n copies simple words from model: 3/11 correct (26%); latency 4.9s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n tacts common objects: 6/12 correct (46%); latency 4.0s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d76\n selects items by feature: 4/10 correct (40%); latency 4.4s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n imitates 3-step motor sequences: 3/8 correct (39%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n Tantrum: freq 4, duration 20m total\n Toileting accident (urine or bowel): urine: 2 in-toilet / 4 accidents; BM: 0 in-toilet / 0 accidents\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Crying during demand presentation\n- Increased response latency (3\u20135\u00d7 baseline)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 73% to 26% across 8 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nTantrum: escape\n Evidence: ABC events in the log support the escape function; behavior occurs in the context of demand presentation and terminates contingent on task removal.\nToileting accident (urine or bowel): automatic\n Evidence: ABC events in the log support the automatic function; behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 49.9%.\n- Trend direction: downward (first session: 73%, last session: 26%).\n- Tantrum: mean 2.8/session (early-window mean 1.5 -> late-window mean 4.0).\n- Toileting accident (urine or bowel): mean 3.0/session (early-window mean 2.5 -> late-window mean 3.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "177d6d6940e9ae56", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Tantrum": "escape", "Toileting accident (urine or bowel)": "automatic"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "early", "n_sessions": 8, "n_programs": 4, "n_behaviors": 2, "behavior_ids": ["tantrum", "toileting_accident"], "behavior_functions": ["escape", "automatic"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "93700"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: spontaneously uses humor appropriately\nCurriculum: Spontaneous Vocal Behavior L3\nLearner: School-Age Learner\nMastery Status: Developing\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously uses humor appropriately\n- Curriculum: Spontaneous Vocal Behavior L3\n- Learner: School-Age Learner\n- Current mastery: Developing\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: activity setup.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's activity setup routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the developing stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nAverage rate of \u2265 3 spontaneous responses per 30-minute session across 3 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "4f72329f66d84ca7", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L3", "learner_profile": "school_age", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously uses humor appropriately", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_spontaneous_rate"}, "teacher_model": null, "seed_tag": "33330"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: showering\nCurriculum: AFLS Basic Living Skills\nLearner: Adult Learner\nMastery Status: Approaching mastery\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: showering\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Approaching mastery\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Backward chaining\nComplete all steps for the learner except the last; teach the last step first, then work backward. The final reinforcer (task completion) is always present for the learner.\n\nSteps:\n1. Enter the shower and close the curtain.\n2. Turn on the water and adjust temperature.\n3. Wet body completely.\n4. Apply soap to a washcloth.\n5. Wash body systematically (face -> torso -> arms -> legs -> feet).\n6. Rinse all soap off.\n7. Apply shampoo and rub into hair.\n8. Rinse hair completely.\n9. Turn off the water.\n10. Exit the shower and dry off with a towel. <- Learner-taught step (backward chaining starts here)\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the approaching mastery stage, use partial-physical or gestural prompts only at steps where errors occur; allow independence elsewhere.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nDifferential per-step + terminal \u2014 Small per-step reinforcement for independent responses; larger reinforcer at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 180s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "0738a04d982f38bb", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "showering", "program_type": "independence", "learner_profile": "adult", "mastery_state": "approaching", "chain_type": "backward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "showering", "module": "basic_living", "mastery_criterion": "mc_fluent_chain", "chain_type": "backward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "differential_per_step", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "42817"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: mands to use the bathroom (e.g., \"bathroom\", \"potty\", \"I need to go\", AAC bathroom icon)\nCurriculum: Mand L1\nLearner: Early Learner\nMastery Status: Emerging\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands to use the bathroom (e.g., \"bathroom\", \"potty\", \"I need to go\", AAC bathroom icon)\n- Curriculum: Mand L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a scheduled toileting window (typically 30\u201360 minutes after fluid intake) and observe for pre-toileting signs (body position, vocalization, squirming). Model the mand topography (vocal, sign, or AAC icon) at the first sign of need; reinforce any approximation with immediate escort to the bathroom. Do not prompt after an accident has started.\nPrimary natural context: end-of-activity transition.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's end-of-activity transition routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Verbal fill-in\nDeliver a partial phrase and pause; learner completes the vocal response.\nCurrent prompt level: At the emerging stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: immediate escort to the bathroom; the learner is not required to complete the current task before going. Pairing the mand with timely bathroom access is what teaches the learner that requesting works.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "93db21fda89a9ac4", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands to use the bathroom (e.g., \"bathroom\", \"potty\", \"I need to go\", AAC bathroom icon)", "mo_category": "mand_bathroom", "mo_arrangement": "bathroom_opportunity", "prompt_strategy": "verbal_fill_in", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "44373"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a toleration program for this self-care / medical / caregiver-delivered skill.\n\nTarget: tolerating tooth brushing by caregiver\nCurriculum: AFLS Basic Living Skills\nLearner: School-Age Learner\nMastery Status: Developing\n\nPlease include the toleration end goal, shaping progression, antecedent strategies, reinforcement plan, refusal / safety procedures, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating tooth brushing by caregiver\n- Curriculum: AFLS Basic Living Skills\n- Learner: School-Age Learner\n- Current mastery: Developing\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for tooth brushing performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nfull 2-minute tooth-brushing routine completed by caregiver without refusal, crying, SIB, or aggression\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1-second toothbrush contact with teeth\n2. 3 seconds of brushing\n3. 5 seconds of brushing\n4. 15 seconds of brushing\n5. 30 seconds of brushing\n6. 60 seconds of brushing\n7. Full 2-minute brushing routine\n\nCurrent shaping step: At the developing stage, begin at shaping step 2 (\"3 seconds of brushing\") and advance through step 3 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal activity tolerated with 2 different caregivers (primary caregiver + one other) across 2 consecutive weeks.\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 3 different settings and with 3 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "f74496eb00c5aa6a", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating tooth brushing by caregiver", "program_type": "toleration", "learner_profile": "school_age", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating tooth brushing by caregiver", "module": "basic_living", "mastery_criterion": "mc_toleration_caregivers", "shaping_n_steps": 7}, "teacher_model": null, "seed_tag": "92010"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5476\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Mand + Reading + Tact\nDate range: Sessions 1\u20138 across 16 days (2026-10-20 to 2026-11-05)\n\nACCELERATION PROGRAMS\n1. tacts common objects (Tact)\n Method: DTT\n2. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n3. reads 10\u201320 sight words (Reading)\n Method: DTT\n4. tacts colors of objects (Tact)\n Method: DTT\n5. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n6. sounds out CVC words (Reading)\n Method: DTT\n\nDECELERATION TARGETS\n1. Verbal aggression \u2014 function hypothesized: escape\n2. Motor stereotypy \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-20 \u2014 58 min \u2014 1 observer\n tacts common objects: 10/14 correct (71%); latency 2.8s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n follows 1-step motor instructions: 7/9 correct (76%); latency 2.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n reads 10\u201320 sight words: 9/13 correct (71%); latency 2.6s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d73\n tacts colors of objects: 9/11 correct (82%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 5/8 correct (66%); latency 2.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n sounds out CVC words: 10/12 correct (79%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d73\n Verbal aggression: freq 1\n Motor stereotypy: freq 3; PIR 25%\n\nSession 2 \u2014 2026-10-22 \u2014 58 min \u2014 1 observer\n tacts common objects: 9/13 correct (68%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d710\n follows 1-step motor instructions: 8/11 correct (76%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n reads 10\u201320 sight words: 7/11 correct (65%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n tacts colors of objects: 10/13 correct (78%); latency 2.2s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 9/14 correct (62%); latency 3.1s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d76\n sounds out CVC words: 8/10 correct (77%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d76\n Verbal aggression: freq 2\n Motor stereotypy: freq 2; PIR 13%\n\nSession 3 \u2014 2026-10-24 \u2014 58 min \u2014 1 observer\n tacts common objects: 7/11 correct (60%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d711\n follows 1-step motor instructions: 10/15 correct (69%); latency 3.1s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d77\n reads 10\u201320 sight words: 7/10 correct (65%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n tacts colors of objects: 6/9 correct (68%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 9/15 correct (57%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d79\n sounds out CVC words: 9/14 correct (67%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d78\n Verbal aggression: freq 2\n Motor stereotypy: freq 4; PIR 17%\n\nSession 4 \u2014 2026-10-26 \u2014 58 min \u2014 1 observer\n tacts common objects: 4/8 correct (46%); latency 4.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n follows 1-step motor instructions: 8/13 correct (59%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d710\n reads 10\u201320 sight words: 8/14 correct (60%); latency 3.5s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d78\n tacts colors of objects: 8/13 correct (63%); latency 3.2s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 7/13 correct (50%); latency 3.5s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n sounds out CVC words: 9/13 correct (66%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d78\n Verbal aggression: freq 3\n Motor stereotypy: freq 3; PIR 13%\n\nSession 5 \u2014 2026-10-28 \u2014 58 min \u2014 1 observer\n tacts common objects: 7/15 correct (46%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d711\n follows 1-step motor instructions: 6/12 correct (51%); latency 4.0s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d711\n reads 10\u201320 sight words: 5/11 correct (45%); latency 4.0s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n tacts colors of objects: 8/14 correct (59%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d710\n requesting a break ('break please' or AAC 'I need a break'): 6/12 correct (51%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d79\n sounds out CVC words: 7/12 correct (59%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d78\n Verbal aggression: freq 2\n Motor stereotypy: freq 4; PIR 16%\n\nSession 6 \u2014 2026-10-30 \u2014 58 min \u2014 1 observer\n tacts common objects: 3/9 correct (34%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d77\n follows 1-step motor instructions: 5/13 correct (42%); latency 4.1s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d73\n reads 10\u201320 sight words: 4/9 correct (45%); latency 4.2s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n tacts colors of objects: 5/10 correct (48%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d79\n requesting a break ('break please' or AAC 'I need a break'): 6/13 correct (47%); latency 3.8s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d77\n sounds out CVC words: 5/9 correct (56%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n Verbal aggression: freq 3\n Motor stereotypy: freq 4; PIR 18%\n\nSession 7 \u2014 2026-11-01 \u2014 58 min \u2014 1 observer\n tacts common objects: 4/15 correct (29%); latency 4.6s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d77\n follows 1-step motor instructions: 4/10 correct (39%); latency 4.3s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n reads 10\u201320 sight words: 4/14 correct (31%); latency 4.5s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d79\n tacts colors of objects: 5/12 correct (44%); latency 3.8s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d77\n requesting a break ('break please' or AAC 'I need a break'): 6/14 correct (42%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d77\n sounds out CVC words: 7/15 correct (46%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d713\n Verbal aggression: freq 4\n Motor stereotypy: freq 5; PIR 28%\n\nSession 8 \u2014 2026-11-03 \u2014 58 min \u2014 1 observer\n tacts common objects: 3/14 correct (19%); latency 5.0s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d710\n follows 1-step motor instructions: 3/9 correct (35%); latency 4.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 4/15 correct (29%); latency 4.5s; prompts FP\u00d75, PP\u00d75, G\u00d75, I\u00d70\n tacts colors of objects: 2/8 correct (30%); latency 4.9s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 4/15 correct (29%); latency 4.7s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d78\n sounds out CVC words: 4/10 correct (38%); latency 4.3s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n Verbal aggression: freq 4\n Motor stereotypy: freq 5; PIR 34%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n- Crying during demand presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 71% to 19% across 8 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nVerbal aggression: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\nMotor stereotypy: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 46.6%.\n- Trend direction: downward (first session: 71%, last session: 19%).\n- Verbal aggression: mean 2.6/session (early-window mean 1.5 -> late-window mean 4.0).\n- Motor stereotypy: mean 3.8/session (early-window mean 2.5 -> late-window mean 5.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "a2270cd3bba824bd", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Verbal aggression": "escape", "Motor stereotypy": "automatic"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "early", "n_sessions": 8, "n_programs": 6, "n_behaviors": 2, "behavior_ids": ["verbal_aggression", "motor_stereotypy"], "behavior_functions": ["escape", "automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "80693"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: writes own name from model\nCurriculum: Writing L1\nLearner: Early Learner\nMastery Status: Developing\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: writes own name from model\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: plate, cup, key\nDistractor stimuli: brush, sock\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "0b4e2e44fb081590", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "writes own name from model", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "crf", "error_correction": "four_step", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "97173"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: copies simple words from model\nCurriculum: Writing L2\nLearner Level: School-Age Learner\nBaseline: Emerging\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: copies simple words from model\n- Curriculum: Writing L2\n- Learner: School-Age Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: ball, napkin, book\nDistractor stimuli: scissors, bottle, crayon, shoe\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nPrevent errors by using high prompts from the start; fade gradually. Paired with most-to-least prompt hierarchy.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "fc9f902f28333340", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L2", "learner_profile": "school_age", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "copies simple words from model", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "crf", "error_correction": "errorless", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "93978"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a chaining program for the following.\n\nSkill: washing hands\nCurriculum: AFLS Basic Living Skills\nLearner Level: Adult Learner\nBaseline: Developing\n\nInclude the full Task Analysis structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: washing hands\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Developing\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Walk to the sink.\n2. Turn on the water.\n3. Wet hands under the water.\n4. Apply soap to hands.\n5. Rub hands together for 15\u201320 seconds, covering fronts, backs, and between fingers.\n6. Rinse hands thoroughly under the water.\n7. Turn off the water.\n8. Dry hands with a towel.\n\n## Prompt Strategy Per Step\nStrategy: Most-to-Least\nStart with full-physical prompt at each step; fade to partial physical, gestural, verbal, independent.\nCurrent prompt level: At the developing stage, use full-physical or partial-physical prompts at each step; fade systematically.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed independently with 2 different adults in 2 different settings across 2 consecutive days.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "b20b699b0e4041db", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "washing hands", "program_type": "independence", "learner_profile": "adult", "mastery_state": "developing", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "washing hands", "module": "basic_living", "mastery_criterion": "mc_generalization", "chain_type": "total_task", "prompt_strategy": "most_to_least", "reinforcement_schedule": "crf_per_step", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "39765"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: identifies coins by name\nCurriculum Reference: Math L2\nLearner Profile: School-Age Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies coins by name\n- Curriculum: Math L2\n- Learner: School-Age Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What number is this?\"\nVariations: \"Which number?\"; \"Tell me the number\"\nPresentation: Present the numeral card.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: book, bottle, blanket\nDistractor stimuli: key, toothbrush, block, crayon\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "dee5a7c95f01526a", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L2", "learner_profile": "school_age", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies coins by name", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "46080"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: sequences 3\u20134 step picture sequences\nCurriculum: Visual Perceptual Skills & Matching-to-Sample L3\nLearner: School-Age Learner\nMastery Status: Generalization phase\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: sequences 3\u20134 step picture sequences\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L3\n- Learner: School-Age Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: pencil, car, napkin\nDistractor stimuli: cup, glue, scissors, bottle, apple\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "6037fda7fc41aae9", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L3", "learner_profile": "school_age", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "sequences 3\u20134 step picture sequences", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "vr3", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "87673"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: points to named common objects\nCurriculum: Listener Responding L1\nLearner: Early Learner\nMastery Status: Emerging\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: points to named common objects\n- Curriculum: Listener Responding L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: block, sock, car\nDistractor stimuli: toothbrush, blanket\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "66289c580f527dd4", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "points to named common objects", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "78310"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4550\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Mand + Reading\nDate range: Sessions 1\u20138 across 16 days (2026-03-16 to 2026-04-01)\n\nACCELERATION PROGRAMS\n1. requesting help when a task is difficult (Mand)\n Method: NET\n2. making the bed (Home Skills)\n Method: Task Analysis\n3. identifying community safety signs (Community)\n Method: DTT\n4. sounds out CVC words (Reading)\n Method: DTT\n5. requesting preferred items using AAC device (Mand)\n Method: NET\n6. indicating 'all done' with a step or activity (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-03-16 \u2014 53 min \u2014 1 observer\n requesting help when a task is difficult: 2/8 correct (23%); latency 4.8s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n making the bed: 3/14 correct (20%); latency 5.3s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d710\n identifying community safety signs: 3/8 correct (37%); latency 4.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n sounds out CVC words: 2/9 correct (27%); latency 4.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n requesting preferred items using AAC device: 5/15 correct (34%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d79\n indicating 'all done' with a step or activity: 3/10 correct (35%); latency 4.5s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n\nSession 2 \u2014 2026-03-18 \u2014 53 min \u2014 1 observer\n requesting help when a task is difficult: 4/11 correct (34%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n making the bed: 3/11 correct (30%); latency 4.5s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n identifying community safety signs: 8/15 correct (50%); latency 3.9s; prompts FP\u00d73, PP\u00d75, G\u00d71, I\u00d76\n sounds out CVC words: 6/15 correct (37%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d75, I\u00d76\n requesting preferred items using AAC device: 4/8 correct (46%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n indicating 'all done' with a step or activity: 4/9 correct (43%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n\nSession 3 \u2014 2026-03-20 \u2014 53 min \u2014 1 observer\n requesting help when a task is difficult: 5/12 correct (41%); latency 4.2s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d77\n making the bed: 4/10 correct (37%); latency 4.5s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n identifying community safety signs: 7/11 correct (63%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n sounds out CVC words: 5/11 correct (45%); latency 4.3s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n requesting preferred items using AAC device: 4/8 correct (53%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n indicating 'all done' with a step or activity: 5/10 correct (52%); latency 3.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n\nSession 4 \u2014 2026-03-22 \u2014 53 min \u2014 1 observer\n requesting help when a task is difficult: 7/13 correct (51%); latency 3.9s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d75\n making the bed: 7/15 correct (48%); latency 4.1s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d710\n identifying community safety signs: 10/15 correct (70%); latency 2.6s; prompts FP\u00d72, PP\u00d75, G\u00d71, I\u00d77\n sounds out CVC words: 7/13 correct (54%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d78\n requesting preferred items using AAC device: 6/9 correct (64%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n indicating 'all done' with a step or activity: 6/10 correct (64%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n\nSession 5 \u2014 2026-03-24 \u2014 53 min \u2014 1 observer\n requesting help when a task is difficult: 6/9 correct (63%); latency 3.1s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n making the bed: 7/13 correct (57%); latency 3.5s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n identifying community safety signs: 11/13 correct (84%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d77\n sounds out CVC words: 10/15 correct (67%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d714\n requesting preferred items using AAC device: 7/10 correct (73%); latency 3.0s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n indicating 'all done' with a step or activity: 7/9 correct (75%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n\nSession 6 \u2014 2026-03-26 \u2014 53 min \u2014 1 observer\n requesting help when a task is difficult: 7/10 correct (73%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n making the bed: 8/14 correct (60%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n identifying community safety signs: 13/14 correct (91%); latency 2.0s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d78\n sounds out CVC words: 8/10 correct (75%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n requesting preferred items using AAC device: 7/9 correct (83%); latency 2.3s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n indicating 'all done' with a step or activity: 9/11 correct (82%); latency 2.0s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n\nSession 7 \u2014 2026-03-28 \u2014 53 min \u2014 1 observer\n requesting help when a task is difficult: 7/9 correct (83%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n making the bed: 10/14 correct (70%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d77\n identifying community safety signs: 13/13 correct (97%); latency 1.7s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d79\n sounds out CVC words: 10/12 correct (85%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d710\n requesting preferred items using AAC device: 8/9 correct (89%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d73\n indicating 'all done' with a step or activity: 11/12 correct (93%); latency 2.0s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d78\n\nSession 8 \u2014 2026-03-30 \u2014 53 min \u2014 1 observer\n requesting help when a task is difficult: 11/12 correct (94%); latency 1.8s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d78\n making the bed: 10/13 correct (79%); latency 2.3s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d74\n identifying community safety signs: 13/13 correct (97%); latency 1.6s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d78\n sounds out CVC words: 14/15 correct (93%); latency 1.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d713\n requesting preferred items using AAC device: 9/9 correct (97%); latency 1.7s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n indicating 'all done' with a step or activity: 9/9 correct (97%); latency 1.8s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Reaching for materials proactively\n- Quick response latency (within 2\u20133 seconds)\n- Requesting more trials verbally"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 23% to 94% across 8 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 57.4%.\n- Trend direction: upward (first session: 23%, last session: 94%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "c0aea6ab20025cac", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "adolescent", "n_sessions": 8, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "31476"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: spontaneously comments on events\nCurriculum: Spontaneous Vocal Behavior L1\nLearner: Early Learner\nMastery Status: Generalization phase\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously comments on events\n- Curriculum: Spontaneous Vocal Behavior L1\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: morning greeting.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's morning greeting routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the generalization stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "9d734f49246a1442", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L1", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously comments on events", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "time_delay", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "70185"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: tacts prepositions (in, on, under)\nCurriculum: Tact L2\nLearner: Early Learner\nMastery Status: Emerging\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts prepositions (in, on, under)\n- Curriculum: Tact L2\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Where is it?\"\nVariations: \"Where is the {object}?\"; \"Tell me where\"\nPresentation: Arrange two objects in a target spatial relation and ask about the position.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: shoe, sock, plate\nDistractor stimuli: hat, car, backpack, napkin\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "2ad4df8308934d66", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L2", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts prepositions (in, on, under)", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "crf", "error_correction": "backstep", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "69064"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4011\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Echoic + Mand + Tact + Writing\nDate range: Sessions 1\u201310 across 20 days (2026-04-06 to 2026-04-26)\n\nACCELERATION PROGRAMS\n1. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n2. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n3. echoes 2-word phrases (Echoic)\n Method: DTT variant\n4. copies simple words from model (Writing)\n Method: DTT\n5. tacts common objects (Tact)\n Method: DTT\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-06 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/8 correct (41%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 4/15 correct (26%); latency 4.7s; prompts FP\u00d75, PP\u00d73, G\u00d74, I\u00d73\n echoes 2-word phrases: 5/14 correct (33%); latency 4.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d712\n copies simple words from model: 7/9 correct (73%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n tacts common objects: 6/10 correct (58%); latency 3.7s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d77\n\nSession 2 \u2014 2026-04-08 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/14 correct (43%); latency 4.2s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d77\n requesting a break ('break please' or AAC 'I need a break'): 5/10 correct (46%); latency 3.7s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n echoes 2-word phrases: 5/13 correct (38%); latency 4.5s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d79\n copies simple words from model: 7/10 correct (74%); latency 2.6s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n tacts common objects: 7/14 correct (50%); latency 4.0s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d76\n\nSession 3 \u2014 2026-04-10 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/14 correct (48%); latency 3.9s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d711\n requesting a break ('break please' or AAC 'I need a break'): 6/12 correct (53%); latency 3.3s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n echoes 2-word phrases: 4/14 correct (30%); latency 4.8s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n copies simple words from model: 9/11 correct (79%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n tacts common objects: 3/9 correct (36%); latency 4.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n\nSession 4 \u2014 2026-04-12 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/13 correct (64%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d710\n requesting a break ('break please' or AAC 'I need a break'): 6/11 correct (51%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n echoes 2-word phrases: 3/10 correct (27%); latency 4.6s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d76\n copies simple words from model: 8/10 correct (78%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n tacts common objects: 5/10 correct (50%); latency 3.8s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n\nSession 5 \u2014 2026-04-14 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/10 correct (34%); latency 4.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n requesting a break ('break please' or AAC 'I need a break'): 7/14 correct (51%); latency 3.8s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d79\n echoes 2-word phrases: 6/10 correct (63%); latency 3.0s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n copies simple words from model: 8/10 correct (80%); latency 2.5s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n tacts common objects: 5/14 correct (32%); latency 4.4s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n\nSession 6 \u2014 2026-04-16 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/12 correct (63%); latency 3.1s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 3/11 correct (29%); latency 4.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d78\n echoes 2-word phrases: 3/11 correct (30%); latency 4.8s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n copies simple words from model: 6/8 correct (78%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n tacts common objects: 8/14 correct (55%); latency 3.7s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d712\n\nSession 7 \u2014 2026-04-18 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/11 correct (61%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 3/12 correct (28%); latency 5.0s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d78\n echoes 2-word phrases: 7/15 correct (48%); latency 3.6s; prompts FP\u00d75, PP\u00d72, G\u00d75, I\u00d73\n copies simple words from model: 6/8 correct (75%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n tacts common objects: 8/15 correct (54%); latency 3.3s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d79\n\nSession 8 \u2014 2026-04-20 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/11 correct (57%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 3/9 correct (30%); latency 4.5s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n echoes 2-word phrases: 3/11 correct (30%); latency 4.7s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n copies simple words from model: 8/15 correct (54%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d714\n tacts common objects: 6/15 correct (37%); latency 4.2s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d79\n\nSession 9 \u2014 2026-04-22 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/9 correct (40%); latency 4.0s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n requesting a break ('break please' or AAC 'I need a break'): 4/9 correct (49%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n echoes 2-word phrases: 4/8 correct (45%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n copies simple words from model: 6/10 correct (55%); latency 3.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n tacts common objects: 2/9 correct (22%); latency 4.8s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d76\n\nSession 10 \u2014 2026-04-24 \u2014 52 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/13 correct (67%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 4/8 correct (54%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n echoes 2-word phrases: 4/10 correct (42%); latency 4.2s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n copies simple words from model: 8/12 correct (68%); latency 2.8s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d710\n tacts common objects: 6/13 correct (47%); latency 3.8s; prompts FP\u00d70, PP\u00d74, G\u00d72, I\u00d77\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Echolalic responding (repeating SD rather than answering)\n- Stereotypic behavior during inter-trial intervals"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 54% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 51.7%.\n- Trend direction: upward (first session: 41%, last session: 67%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "2190c7a8f2f78d43", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "early", "n_sessions": 10, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "9737"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1654\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Independent Living + Mand + Self-Care + Tolerating Denied Access\nDate range: Sessions 1\u20139 across 18 days (2026-04-19 to 2026-05-07)\n\nACCELERATION PROGRAMS\n1. simple meal preparation (Home Skills)\n Method: Task Analysis\n2. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n3. indicating 'all done' at task completion (Mand)\n Method: NET\n4. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n5. self-advocacy statements (Independent Living)\n Method: BST\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-19 \u2014 55 min \u2014 1 observer\n simple meal preparation: 6/8 correct (75%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n wait calmly when a preferred activity is denied: 12/14 correct (85%); latency 2.0s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d76\n indicating 'all done' at task completion: 10/13 correct (76%); latency 2.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d712\n dressing (pants, shirt): 7/9 correct (80%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n self-advocacy statements: 9/11 correct (78%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n\nSession 2 \u2014 2026-04-21 \u2014 55 min \u2014 1 observer\n simple meal preparation: 11/15 correct (74%); latency 2.9s; prompts FP\u00d75, PP\u00d74, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 10/12 correct (83%); latency 2.3s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d71\n indicating 'all done' at task completion: 11/15 correct (74%); latency 2.4s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d713\n dressing (pants, shirt): 11/15 correct (76%); latency 2.5s; prompts FP\u00d74, PP\u00d70, G\u00d75, I\u00d76\n self-advocacy statements: 12/14 correct (83%); latency 2.1s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d77\n\nSession 3 \u2014 2026-04-23 \u2014 55 min \u2014 1 observer\n simple meal preparation: 10/13 correct (77%); latency 2.4s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d75\n wait calmly when a preferred activity is denied: 9/11 correct (82%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n indicating 'all done' at task completion: 7/10 correct (72%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n dressing (pants, shirt): 6/8 correct (76%); latency 2.4s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n self-advocacy statements: 11/13 correct (85%); latency 1.9s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d76\n\nSession 4 \u2014 2026-04-25 \u2014 55 min \u2014 1 observer\n simple meal preparation: 3/8 correct (37%); latency 4.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 4/9 correct (42%); latency 4.0s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n indicating 'all done' at task completion: 4/8 correct (44%); latency 4.0s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n dressing (pants, shirt): 4/9 correct (47%); latency 3.9s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d79\n self-advocacy statements: 6/12 correct (47%); latency 4.2s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d78\n\nSession 5 \u2014 2026-04-27 \u2014 55 min \u2014 1 observer\n simple meal preparation: 6/15 correct (41%); latency 4.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d79\n wait calmly when a preferred activity is denied: 5/10 correct (47%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n indicating 'all done' at task completion: 6/13 correct (47%); latency 4.0s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d76\n dressing (pants, shirt): 7/14 correct (50%); latency 4.0s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d78\n self-advocacy statements: 4/9 correct (47%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n\nSession 6 \u2014 2026-04-29 \u2014 55 min \u2014 1 observer\n simple meal preparation: 5/13 correct (38%); latency 4.5s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d78\n wait calmly when a preferred activity is denied: 5/11 correct (43%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n indicating 'all done' at task completion: 6/11 correct (53%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d77\n dressing (pants, shirt): 4/8 correct (46%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n self-advocacy statements: 5/9 correct (52%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n\nSession 7 \u2014 2026-05-01 \u2014 55 min \u2014 1 observer\n simple meal preparation: 5/13 correct (37%); latency 4.4s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d78\n wait calmly when a preferred activity is denied: 5/12 correct (45%); latency 3.9s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d70\n indicating 'all done' at task completion: 5/9 correct (61%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n dressing (pants, shirt): 7/14 correct (47%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n self-advocacy statements: 5/9 correct (56%); latency 3.2s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n\nSession 8 \u2014 2026-05-03 \u2014 55 min \u2014 1 observer\n simple meal preparation: 6/12 correct (47%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d75\n wait calmly when a preferred activity is denied: 5/10 correct (54%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d77\n indicating 'all done' at task completion: 5/8 correct (65%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n dressing (pants, shirt): 4/8 correct (50%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n self-advocacy statements: 5/8 correct (61%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n\nSession 9 \u2014 2026-05-05 \u2014 55 min \u2014 1 observer\n simple meal preparation: 6/11 correct (58%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n wait calmly when a preferred activity is denied: 8/13 correct (61%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d713\n indicating 'all done' at task completion: 10/15 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d78\n dressing (pants, shirt): 6/12 correct (52%); latency 3.6s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d74\n self-advocacy statements: 8/12 correct (70%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d76\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Stereotypic behavior during inter-trial intervals\n- Delayed responding (>5 seconds consistently)\n- Looking away during SD presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 53.6%.\n- Trend direction: downward (first session: 75%, last session: 58%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "1a87f0703e9bbe08", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "adult", "n_sessions": 9, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "19304"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: mands for a break (e.g., \"break please\", AAC \"I need a break\")\nCurriculum: Mand L1\nLearner: Early Learner\nMastery Status: Approaching mastery\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands for a break (e.g., \"break please\", AAC \"I need a break\")\n- Curriculum: Mand L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nPresent a brief non-preferred task or demand at a level the learner can tolerate but may wish to pause. Wait for a request-for-break topography; honor the request immediately on first acquisition (CRF), thin later.\nPrimary natural context: academic period.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's academic period routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Verbal fill-in\nDeliver a partial phrase and pause; learner completes the vocal response.\nCurrent prompt level: At the approaching mastery stage, use time delay (0 s -> 2 s -> 4 s) before delivering any model prompt; reinforce independent responses differentially.\n\n## Natural Reinforcer\nNatural reinforcer: immediate brief escape from the demand (30\u201360 seconds) to a neutral or preferred activity.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "5e7ef552782ae9cc", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands for a break (e.g., \"break please\", AAC \"I need a break\")", "mo_category": "mand_break", "mo_arrangement": "break_opportunity", "prompt_strategy": "verbal_fill_in", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "16366"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: washing hands\nCurriculum: AFLS Basic Living Skills\nLearner: Adult Learner\nMastery Status: Developing\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: washing hands\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Developing\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Walk to the sink.\n2. Turn on the water.\n3. Wet hands under the water.\n4. Apply soap to hands.\n5. Rub hands together for 15\u201320 seconds, covering fronts, backs, and between fingers.\n6. Rinse hands thoroughly under the water.\n7. Turn off the water.\n8. Dry hands with a towel.\n\n## Prompt Strategy Per Step\nStrategy: Most-to-Least\nStart with full-physical prompt at each step; fade to partial physical, gestural, verbal, independent.\nCurrent prompt level: At the developing stage, use full-physical or partial-physical prompts at each step; fade systematically.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed independently with 2 different adults in 2 different settings across 2 consecutive days.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "e5d6245b70edb285", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "washing hands", "program_type": "independence", "learner_profile": "adult", "mastery_state": "developing", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "washing hands", "module": "basic_living", "mastery_criterion": "mc_generalization", "chain_type": "total_task", "prompt_strategy": "most_to_least", "reinforcement_schedule": "crf_per_step", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "80658"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5210\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Mand + Self-Care + Writing\nDate range: Sessions 1\u201310 across 20 days (2026-03-17 to 2026-04-06)\n\nACCELERATION PROGRAMS\n1. requesting a break during non-preferred activities (Mand)\n Method: NET\n2. brushing teeth independently (Self-Care)\n Method: Task Analysis\n3. indicating 'all done' with a step or activity (Mand)\n Method: NET\n4. ordering in a restaurant (Community)\n Method: Task Analysis\n5. copies simple words from model (Writing)\n Method: DTT\n6. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-03-17 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 10/14 correct (73%); latency 2.8s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n brushing teeth independently: 6/8 correct (81%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n indicating 'all done' with a step or activity: 9/10 correct (91%); latency 1.9s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n ordering in a restaurant: 7/8 correct (93%); latency 1.6s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n copies simple words from model: 10/11 correct (87%); latency 2.0s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d77\n meal cleanup after eating: 10/12 correct (79%); latency 2.6s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d76\n\nSession 2 \u2014 2026-03-19 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 6/8 correct (72%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n brushing teeth independently: 13/15 correct (87%); latency 1.9s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d77\n indicating 'all done' with a step or activity: 8/9 correct (89%); latency 1.9s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n ordering in a restaurant: 8/8 correct (97%); latency 1.5s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n copies simple words from model: 8/10 correct (81%); latency 2.1s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d74\n meal cleanup after eating: 11/13 correct (83%); latency 2.2s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d71\n\nSession 3 \u2014 2026-03-21 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 11/15 correct (75%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d710\n brushing teeth independently: 7/9 correct (83%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n indicating 'all done' with a step or activity: 11/12 correct (94%); latency 1.6s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d73\n ordering in a restaurant: 8/8 correct (95%); latency 1.8s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n copies simple words from model: 10/12 correct (83%); latency 2.1s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n meal cleanup after eating: 11/14 correct (77%); latency 2.4s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d77\n\nSession 4 \u2014 2026-03-23 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 10/13 correct (76%); latency 2.8s; prompts FP\u00d70, PP\u00d74, G\u00d72, I\u00d77\n brushing teeth independently: 7/8 correct (85%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n indicating 'all done' with a step or activity: 7/8 correct (94%); latency 1.7s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n ordering in a restaurant: 13/14 correct (95%); latency 1.9s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d74\n copies simple words from model: 11/13 correct (82%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n meal cleanup after eating: 10/13 correct (77%); latency 2.7s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d77\n\nSession 5 \u2014 2026-03-25 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 10/14 correct (75%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d711\n brushing teeth independently: 7/8 correct (83%); latency 2.2s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n indicating 'all done' with a step or activity: 10/11 correct (90%); latency 1.7s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n ordering in a restaurant: 10/11 correct (92%); latency 2.0s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n copies simple words from model: 9/11 correct (80%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n meal cleanup after eating: 11/13 correct (82%); latency 2.1s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d75\n\nSession 6 \u2014 2026-03-27 \u2014 IOA SESSION \u2014 2 observers\n requesting a break during non-preferred activities: 72% (primary); IOA 84% agreement\n brushing teeth independently: 82% (primary); IOA 84% agreement\n indicating 'all done' with a step or activity: 93% (primary); IOA 84% agreement\n ordering in a restaurant: 96% (primary); IOA 84% agreement\n copies simple words from model: 78% (primary); IOA 84% agreement\n meal cleanup after eating: 80% (primary); IOA 84% agreement\n\nSession 7 \u2014 2026-03-29 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 11/15 correct (72%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d78\n brushing teeth independently: 9/11 correct (81%); latency 2.3s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d77\n indicating 'all done' with a step or activity: 8/9 correct (93%); latency 1.8s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n ordering in a restaurant: 8/8 correct (98%); latency 1.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n copies simple words from model: 10/13 correct (78%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d79\n meal cleanup after eating: 8/9 correct (84%); latency 2.3s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n\nSession 8 \u2014 2026-03-31 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 5/8 correct (66%); latency 2.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n brushing teeth independently: 10/13 correct (78%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d77\n indicating 'all done' with a step or activity: 10/11 correct (93%); latency 1.9s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n ordering in a restaurant: 11/11 correct (98%); latency 1.3s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d76\n copies simple words from model: 6/8 correct (72%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n meal cleanup after eating: 7/9 correct (82%); latency 2.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n\nSession 9 \u2014 2026-04-02 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 10/15 correct (68%); latency 3.0s; prompts FP\u00d75, PP\u00d71, G\u00d75, I\u00d74\n brushing teeth independently: 12/15 correct (81%); latency 2.4s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d78\n indicating 'all done' with a step or activity: 9/10 correct (92%); latency 1.8s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d76\n ordering in a restaurant: 8/8 correct (98%); latency 1.5s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n copies simple words from model: 11/15 correct (73%); latency 2.5s; prompts FP\u00d74, PP\u00d75, G\u00d71, I\u00d75\n meal cleanup after eating: 7/8 correct (82%); latency 2.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n\nSession 10 \u2014 2026-04-04 \u2014 54 min \u2014 1 observer\n requesting a break during non-preferred activities: 8/12 correct (68%); latency 3.0s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d78\n brushing teeth independently: 9/11 correct (77%); latency 2.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d79\n indicating 'all done' with a step or activity: 12/12 correct (96%); latency 1.8s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d76\n ordering in a restaurant: 10/10 correct (97%); latency 1.8s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d76\n copies simple words from model: 11/15 correct (70%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d714\n meal cleanup after eating: 8/10 correct (85%); latency 2.3s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Stereotypic behavior during inter-trial intervals\n- Playing with non-task materials\n- Looking away during SD presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (73%\u201368%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 10 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 71.6%.\n- Trend direction: downward (first session: 73%, last session: 68%).\n- IOA data: 84% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "f6eb4c97ec65c003", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "adolescent", "n_sessions": 10, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "68487"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-2587\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Reading + Tolerating Denied Access\nDate range: Sessions 1\u201310 across 20 days (2026-05-20 to 2026-06-09)\n\nACCELERATION PROGRAMS\n1. identifies numerals 1\u201320 (Math)\n Method: DTT\n2. sounds out CVC words (Reading)\n Method: DTT\n3. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n4. requesting preferred items using AAC device (e.g., \"I want cookie please\") (Mand)\n Method: NET\n5. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n6. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-20 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 7/13 correct (51%); latency 3.7s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d75\n sounds out CVC words: 5/12 correct (38%); latency 4.1s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d74\n wait calmly when access to preferred item is denied: 5/10 correct (51%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 3/12 correct (29%); latency 4.7s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d75\n indicating 'all done' when an activity is complete: 6/14 correct (43%); latency 3.8s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/15 correct (51%); latency 3.8s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d77\n\nSession 2 \u2014 2026-05-22 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 5/13 correct (35%); latency 4.2s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d78\n sounds out CVC words: 10/14 correct (72%); latency 2.8s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d78\n wait calmly when access to preferred item is denied: 9/15 correct (62%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d711\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/15 correct (56%); latency 3.5s; prompts FP\u00d72, PP\u00d75, G\u00d73, I\u00d75\n indicating 'all done' when an activity is complete: 9/13 correct (73%); latency 2.8s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/8 correct (58%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n\nSession 3 \u2014 2026-05-24 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 6/10 correct (62%); latency 3.0s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n sounds out CVC words: 5/10 correct (47%); latency 4.0s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d76\n wait calmly when access to preferred item is denied: 12/15 correct (82%); latency 2.2s; prompts FP\u00d74, PP\u00d75, G\u00d71, I\u00d75\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 6/15 correct (39%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d77\n indicating 'all done' when an activity is complete: 6/13 correct (49%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 3/9 correct (30%); latency 4.9s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n\nSession 4 \u2014 2026-05-26 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 5/11 correct (50%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n sounds out CVC words: 3/9 correct (36%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n wait calmly when access to preferred item is denied: 6/9 correct (69%); latency 3.0s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 3/9 correct (34%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n indicating 'all done' when an activity is complete: 8/11 correct (73%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/12 correct (49%); latency 3.5s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d73\n\nSession 5 \u2014 2026-05-28 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 5/9 correct (53%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d77\n sounds out CVC words: 6/10 correct (56%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d76\n wait calmly when access to preferred item is denied: 8/13 correct (63%); latency 3.1s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d72\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/15 correct (54%); latency 3.4s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d712\n indicating 'all done' when an activity is complete: 4/9 correct (44%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/8 correct (59%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n\nSession 6 \u2014 2026-05-30 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 7/15 correct (46%); latency 4.1s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d710\n sounds out CVC words: 5/9 correct (59%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n wait calmly when access to preferred item is denied: 8/10 correct (79%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/15 correct (54%); latency 3.3s; prompts FP\u00d70, PP\u00d75, G\u00d73, I\u00d77\n indicating 'all done' when an activity is complete: 4/11 correct (35%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/11 correct (61%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d710\n\nSession 7 \u2014 2026-06-01 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 8/12 correct (69%); latency 3.0s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d75\n sounds out CVC words: 7/12 correct (57%); latency 3.5s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d75\n wait calmly when access to preferred item is denied: 7/13 correct (51%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d73\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 4/9 correct (47%); latency 4.1s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n indicating 'all done' when an activity is complete: 5/13 correct (39%); latency 4.4s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d710\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/11 correct (47%); latency 3.9s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n\nSession 8 \u2014 2026-06-03 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 4/12 correct (37%); latency 4.5s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n sounds out CVC words: 9/15 correct (57%); latency 3.5s; prompts FP\u00d74, PP\u00d75, G\u00d71, I\u00d75\n wait calmly when access to preferred item is denied: 12/14 correct (83%); latency 2.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 2/8 correct (28%); latency 4.8s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n indicating 'all done' when an activity is complete: 8/14 correct (55%); latency 3.3s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/11 correct (57%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n\nSession 9 \u2014 2026-06-05 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 4/13 correct (32%); latency 4.7s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d78\n sounds out CVC words: 9/15 correct (63%); latency 3.4s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d710\n wait calmly when access to preferred item is denied: 6/9 correct (70%); latency 3.0s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d73\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/14 correct (58%); latency 3.7s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d79\n indicating 'all done' when an activity is complete: 9/14 correct (63%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d710\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 3/11 correct (29%); latency 4.8s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d75\n\nSession 10 \u2014 2026-06-07 \u2014 51 min \u2014 1 observer\n identifies numerals 1\u201320: 9/13 correct (66%); latency 3.2s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d72\n sounds out CVC words: 6/13 correct (44%); latency 3.8s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d79\n wait calmly when access to preferred item is denied: 11/14 correct (77%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d711\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 3/11 correct (31%); latency 4.4s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d77\n indicating 'all done' when an activity is complete: 7/12 correct (57%); latency 3.5s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/9 correct (52%); latency 3.4s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Echolalic responding (repeating SD rather than answering)\n- Playing with non-task materials\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 58% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 50.2%.\n- Trend direction: upward (first session: 51%, last session: 66%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "6256c5310000c637", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "school_age", "n_sessions": 10, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "91712"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: engages in social games (peek-a-boo, tickle)\nCurriculum Reference: Social Behavior & Social Play L1\nLearner Profile: Early Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: engages in social games (peek-a-boo, tickle)\n- Curriculum: Social Behavior & Social Play L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: circle time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's circle time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "7f9858a2c702a1d9", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "engages in social games (peek-a-boo, tickle)", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "54871"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4343\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Independent Living + Mand + Self-Care + Vocational\nDate range: Sessions 1\u201311 across 22 days (2026-01-16 to 2026-02-07)\n\nACCELERATION PROGRAMS\n1. simple meal preparation (Home Skills)\n Method: Task Analysis\n2. requesting a break during extended tasks (Mand)\n Method: NET\n3. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n4. brushing teeth independently (Self-Care)\n Method: Task Analysis\n5. managing a budget (Independent Living)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-16 \u2014 59 min \u2014 1 observer\n simple meal preparation: 5/11 correct (49%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n requesting a break during extended tasks: 7/14 correct (53%); latency 3.5s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n completing assigned tasks in order: 9/14 correct (66%); latency 2.7s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n brushing teeth independently: 6/11 correct (54%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d78\n managing a budget: 5/10 correct (49%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n Self-injurious behavior (SIB): freq 3\n\nSession 2 \u2014 2026-01-18 \u2014 59 min \u2014 1 observer\n simple meal preparation: 8/15 correct (54%); latency 3.8s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d78\n requesting a break during extended tasks: 8/15 correct (51%); latency 3.8s; prompts FP\u00d72, PP\u00d75, G\u00d72, I\u00d76\n completing assigned tasks in order: 7/8 correct (85%); latency 2.5s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n brushing teeth independently: 6/10 correct (57%); latency 3.5s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d76\n managing a budget: 9/14 correct (67%); latency 3.3s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d74\n Self-injurious behavior (SIB): freq 7\n\nSession 3 \u2014 2026-01-20 \u2014 59 min \u2014 1 observer\n simple meal preparation: 5/13 correct (38%); latency 4.4s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d78\n requesting a break during extended tasks: 7/12 correct (57%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d710\n completing assigned tasks in order: 10/15 correct (70%); latency 2.9s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d714\n brushing teeth independently: 4/10 correct (41%); latency 4.1s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d76\n managing a budget: 6/8 correct (72%); latency 2.8s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n Self-injurious behavior (SIB): freq 5\n\nSession 4 \u2014 2026-01-22 \u2014 59 min \u2014 1 observer\n simple meal preparation: 8/12 correct (66%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d77\n requesting a break during extended tasks: 4/8 correct (54%); latency 3.9s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n completing assigned tasks in order: 5/8 correct (61%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n brushing teeth independently: 7/15 correct (45%); latency 4.0s; prompts FP\u00d74, PP\u00d74, G\u00d75, I\u00d72\n managing a budget: 7/15 correct (49%); latency 3.9s; prompts FP\u00d71, PP\u00d75, G\u00d74, I\u00d75\n Self-injurious behavior (SIB): freq 2\n\nSession 5 \u2014 2026-01-24 \u2014 59 min \u2014 1 observer\n simple meal preparation: 10/15 correct (69%); latency 2.8s; prompts FP\u00d71, PP\u00d74, G\u00d75, I\u00d75\n requesting a break during extended tasks: 3/10 correct (30%); latency 4.8s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d76\n completing assigned tasks in order: 12/15 correct (80%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d711\n brushing teeth independently: 5/10 correct (51%); latency 3.9s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n managing a budget: 5/10 correct (54%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n Self-injurious behavior (SIB): freq 2\n\nSession 6 \u2014 2026-01-26 \u2014 59 min \u2014 1 observer\n simple meal preparation: 6/9 correct (65%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n requesting a break during extended tasks: 5/8 correct (57%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n completing assigned tasks in order: 8/10 correct (82%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n brushing teeth independently: 3/11 correct (25%); latency 4.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n managing a budget: 6/11 correct (53%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d77\n Self-injurious behavior (SIB): freq 3\n\nSession 7 \u2014 2026-01-28 \u2014 59 min \u2014 1 observer\n simple meal preparation: 5/15 correct (36%); latency 4.5s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d78\n requesting a break during extended tasks: 5/11 correct (49%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n completing assigned tasks in order: 10/14 correct (71%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d78\n brushing teeth independently: 6/11 correct (51%); latency 3.5s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n managing a budget: 5/10 correct (48%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n Self-injurious behavior (SIB): freq 6\n\nSession 8 \u2014 2026-01-30 \u2014 59 min \u2014 1 observer\n simple meal preparation: 6/14 correct (45%); latency 4.2s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d713\n requesting a break during extended tasks: 5/13 correct (41%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d713\n completing assigned tasks in order: 7/9 correct (78%); latency 2.3s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n brushing teeth independently: 5/14 correct (35%); latency 4.2s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d74\n managing a budget: 5/8 correct (67%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n Self-injurious behavior (SIB): freq 7\n\nSession 9 \u2014 2026-02-01 \u2014 59 min \u2014 1 observer\n simple meal preparation: 6/8 correct (71%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n requesting a break during extended tasks: 7/10 correct (67%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d75\n completing assigned tasks in order: 11/14 correct (80%); latency 2.1s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d79\n brushing teeth independently: 9/15 correct (59%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d79\n managing a budget: 5/13 correct (36%); latency 4.5s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d72\n Self-injurious behavior (SIB): freq 5\n\nSession 10 \u2014 2026-02-03 \u2014 59 min \u2014 1 observer\n simple meal preparation: 5/12 correct (40%); latency 4.3s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d78\n requesting a break during extended tasks: 6/12 correct (53%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d76\n completing assigned tasks in order: 9/13 correct (71%); latency 2.6s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d77\n brushing teeth independently: 8/14 correct (54%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d712\n managing a budget: 10/14 correct (72%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d710\n Self-injurious behavior (SIB): freq 3\n\nSession 11 \u2014 2026-02-05 \u2014 59 min \u2014 1 observer\n simple meal preparation: 5/12 correct (45%); latency 3.7s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d71\n requesting a break during extended tasks: 3/8 correct (39%); latency 4.2s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n completing assigned tasks in order: 6/8 correct (75%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n brushing teeth independently: 4/12 correct (34%); latency 4.4s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d76\n managing a budget: 6/10 correct (63%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n Self-injurious behavior (SIB): freq 2\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Stereotypic behavior during inter-trial intervals\n- Delayed responding (>5 seconds consistently)\n- Looking away during SD presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 47% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 52.6%.\n- Trend direction: downward (first session: 49%, last session: 45%).\n- Self-injurious behavior (SIB): mean 4.1/session (early-window mean 5.0 -> late-window mean 3.3).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "e62a7c80808f6e5a", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {"Self-injurious behavior (SIB)": "automatic"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "adult", "n_sessions": 11, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["sib"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "7377"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5337\nProfile: Adult Learner (18+ years)\nCurricula: Self-Care + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u20138 across 16 days (2026-07-03 to 2026-07-19)\n\nACCELERATION PROGRAMS\n1. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n2. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n3. brushing teeth independently (Self-Care)\n Method: Task Analysis\n4. washing hands independently (Self-Care)\n Method: Task Analysis\n5. clocking in at start of shift (Vocational)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Toileting accident (urine or bowel) \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-03 \u2014 30 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 7/15 correct (47%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d78\n dressing (pants, shirt): 4/9 correct (42%); latency 4.4s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d73\n brushing teeth independently: 4/10 correct (40%); latency 3.9s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n washing hands independently: 5/11 correct (43%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n clocking in at start of shift: 4/9 correct (49%); latency 4.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d77\n Toileting accident (urine or bowel): urine: 2 in-toilet / 2 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 2 \u2014 2026-07-05 \u2014 30 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 8/15 correct (56%); latency 3.5s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d79\n dressing (pants, shirt): 7/15 correct (45%); latency 4.0s; prompts FP\u00d75, PP\u00d73, G\u00d71, I\u00d76\n brushing teeth independently: 5/12 correct (45%); latency 4.0s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d75\n washing hands independently: 6/12 correct (50%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d77\n clocking in at start of shift: 9/15 correct (58%); latency 3.3s; prompts FP\u00d75, PP\u00d71, G\u00d74, I\u00d75\n Toileting accident (urine or bowel): urine: 3 in-toilet / 2 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 3 \u2014 2026-07-07 \u2014 30 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 8/12 correct (65%); latency 3.0s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d77\n dressing (pants, shirt): 5/9 correct (53%); latency 3.6s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d75\n brushing teeth independently: 7/14 correct (51%); latency 3.8s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d79\n washing hands independently: 5/8 correct (58%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n clocking in at start of shift: 6/9 correct (66%); latency 2.8s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n Toileting accident (urine or bowel): urine: 3 in-toilet / 2 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 4 \u2014 2026-07-09 \u2014 30 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 6/8 correct (74%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n dressing (pants, shirt): 8/13 correct (61%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d711\n brushing teeth independently: 6/11 correct (54%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n washing hands independently: 9/13 correct (68%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d710\n clocking in at start of shift: 10/14 correct (74%); latency 2.9s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d74\n Toileting accident (urine or bowel): urine: 5 in-toilet / 1 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 5 \u2014 2026-07-11 \u2014 30 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 9/11 correct (79%); latency 2.2s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n dressing (pants, shirt): 10/15 correct (64%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d79\n brushing teeth independently: 6/10 correct (61%); latency 3.3s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d76\n washing hands independently: 6/8 correct (72%); latency 2.5s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n clocking in at start of shift: 11/15 correct (74%); latency 2.6s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d79\n Toileting accident (urine or bowel): urine: 2 in-toilet / 3 accidents; BM: 0 in-toilet / 0 accidents\n ABC (toileting accident (urine or bowel)): A = end of 90-minute block without scheduled toileting; B = soiled (bowel) at the work table; C = staff initiated clean-up and hygiene routine; program paused\n\nSession 6 \u2014 2026-07-13 \u2014 30 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 10/13 correct (80%); latency 2.2s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d77\n dressing (pants, shirt): 9/13 correct (68%); latency 2.8s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n brushing teeth independently: 10/15 correct (68%); latency 2.9s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d77\n washing hands independently: 11/15 correct (75%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d711\n clocking in at start of shift: 6/8 correct (74%); latency 2.7s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n Toileting accident (urine or bowel): urine: 2 in-toilet / 3 accidents; BM: 1 in-toilet / 0 accidents\n ABC (toileting accident (urine or bowel)): A = transition from preferred activity to non-preferred task; B = voided (urine) en route to the work area; C = staff redirected to bathroom, changed clothing\n\nSession 7 \u2014 2026-07-15 \u2014 30 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 10/13 correct (80%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d78\n dressing (pants, shirt): 7/10 correct (73%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n brushing teeth independently: 8/11 correct (70%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d76\n washing hands independently: 10/14 correct (75%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n clocking in at start of shift: 8/11 correct (74%); latency 2.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n Toileting accident (urine or bowel): urine: 2 in-toilet / 1 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 8 \u2014 2026-07-17 \u2014 30 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 6/8 correct (80%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n dressing (pants, shirt): 9/13 correct (73%); latency 2.9s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d79\n brushing teeth independently: 8/11 correct (77%); latency 2.3s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n washing hands independently: 7/10 correct (75%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n clocking in at start of shift: 7/10 correct (74%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d75\n Toileting accident (urine or bowel): urine: 2 in-toilet / 3 accidents; BM: 0 in-toilet / 1 accidents\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Stereotypic behavior during inter-trial intervals\n- Delayed responding (>5 seconds consistently)\n- Echolalic responding (repeating SD rather than answering)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 47% at return, recovering to 80%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Behavior Function Hypothesis\nToileting accident (urine or bowel): automatic\n Evidence: ABC events in the log support the automatic function; behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 70.3%.\n- Trend direction: upward (first session: 47%, last session: 80%).\n- Toileting accident (urine or bowel): mean 2.8/session (early-window mean 2.5 -> late-window mean 3.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "0573834e468df7a5", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {"Toileting accident (urine or bowel)": "automatic"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "adult", "n_sessions": 8, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["toileting_accident"], "behavior_functions": ["automatic"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "99666"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4624\nProfile: Adult Learner (18+ years)\nCurricula: Community + Home Skills + Mand + Self-Care + Vocational\nDate range: Sessions 1\u20138 across 16 days (2026-09-10 to 2026-09-26)\n\nACCELERATION PROGRAMS\n1. using public transportation (Community)\n Method: Task Analysis\n2. clocking in at start of shift (Vocational)\n Method: Task Analysis\n3. requesting a break during extended tasks (Mand)\n Method: NET\n4. brushing teeth independently (Self-Care)\n Method: Task Analysis\n5. simple meal preparation (Home Skills)\n Method: Task Analysis\n6. washing hands independently (Self-Care)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-10 \u2014 55 min \u2014 1 observer\n using public transportation: 9/10 correct (91%); latency 1.9s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d76\n clocking in at start of shift: 11/13 correct (85%); latency 2.4s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d79\n requesting a break during extended tasks: 8/9 correct (85%); latency 1.9s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n brushing teeth independently: 9/11 correct (84%); latency 2.1s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d78\n simple meal preparation: 8/10 correct (83%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n washing hands independently: 9/12 correct (78%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d75\n\nSession 2 \u2014 2026-09-12 \u2014 55 min \u2014 1 observer\n using public transportation: 4/10 correct (41%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n clocking in at start of shift: 4/8 correct (47%); latency 3.7s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n requesting a break during extended tasks: 4/10 correct (37%); latency 4.1s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n brushing teeth independently: 5/13 correct (35%); latency 4.7s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n simple meal preparation: 4/15 correct (29%); latency 4.9s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d77\n washing hands independently: 3/8 correct (41%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n\nSession 3 \u2014 2026-09-14 \u2014 55 min \u2014 1 observer\n using public transportation: 10/11 correct (92%); latency 1.8s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n clocking in at start of shift: 9/10 correct (89%); latency 2.0s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n requesting a break during extended tasks: 10/11 correct (88%); latency 1.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d76\n brushing teeth independently: 8/9 correct (84%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n simple meal preparation: 9/11 correct (83%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n washing hands independently: 9/13 correct (72%); latency 2.5s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d79\n\nSession 4 \u2014 2026-09-16 \u2014 55 min \u2014 1 observer\n using public transportation: 5/15 correct (36%); latency 4.4s; prompts FP\u00d75, PP\u00d72, G\u00d75, I\u00d73\n clocking in at start of shift: 4/10 correct (44%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d78\n requesting a break during extended tasks: 4/11 correct (34%); latency 4.3s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n brushing teeth independently: 4/11 correct (37%); latency 4.3s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n simple meal preparation: 4/13 correct (32%); latency 4.6s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d78\n washing hands independently: 4/9 correct (46%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d76\n\nSession 5 \u2014 2026-09-18 \u2014 55 min \u2014 1 observer\n using public transportation: 8/9 correct (86%); latency 2.0s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n clocking in at start of shift: 12/14 correct (84%); latency 2.2s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d74\n requesting a break during extended tasks: 11/12 correct (89%); latency 2.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d78\n brushing teeth independently: 11/12 correct (89%); latency 2.2s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d75\n simple meal preparation: 7/8 correct (89%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n washing hands independently: 6/8 correct (72%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n\nSession 6 \u2014 2026-09-20 \u2014 55 min \u2014 1 observer\n using public transportation: 5/15 correct (34%); latency 4.3s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d712\n clocking in at start of shift: 6/15 correct (37%); latency 4.6s; prompts FP\u00d73, PP\u00d72, G\u00d75, I\u00d75\n requesting a break during extended tasks: 4/10 correct (39%); latency 4.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d77\n brushing teeth independently: 4/13 correct (34%); latency 4.7s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d78\n simple meal preparation: 3/10 correct (32%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n washing hands independently: 6/12 correct (46%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d78\n\nSession 7 \u2014 2026-09-22 \u2014 55 min \u2014 1 observer\n using public transportation: 12/14 correct (89%); latency 1.9s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d75\n clocking in at start of shift: 12/14 correct (83%); latency 2.1s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d78\n requesting a break during extended tasks: 8/9 correct (93%); latency 1.5s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d79\n brushing teeth independently: 12/14 correct (87%); latency 2.3s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d77\n simple meal preparation: 10/12 correct (83%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d74\n washing hands independently: 7/9 correct (76%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n\nSession 8 \u2014 2026-09-24 \u2014 55 min \u2014 1 observer\n using public transportation: 5/15 correct (34%); latency 4.4s; prompts FP\u00d75, PP\u00d73, G\u00d70, I\u00d77\n clocking in at start of shift: 5/14 correct (38%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d712\n requesting a break during extended tasks: 4/13 correct (34%); latency 4.8s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n brushing teeth independently: 3/8 correct (35%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n simple meal preparation: 3/10 correct (30%); latency 4.8s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n washing hands independently: 4/8 correct (45%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Stereotypic behavior during inter-trial intervals\n- Playing with non-task materials\n- Leaving seat without permission"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 62.9%.\n- Trend direction: downward (first session: 91%, last session: 34%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "5f9e9dd2ffcbe477", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "adult", "n_sessions": 8, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "9961"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: spontaneously tells stories or narratives\nCurriculum: Spontaneous Vocal Behavior L3\nLearner: School-Age Learner\nMastery Status: Mastered at current level\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously tells stories or narratives\n- Curriculum: Spontaneous Vocal Behavior L3\n- Learner: School-Age Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: activity setup.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's activity setup routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Verbal fill-in\nDeliver a partial phrase and pause; learner completes the vocal response.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "bfbfb047539aef8d", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L3", "learner_profile": "school_age", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously tells stories or narratives", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "verbal_fill_in", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "76914"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: selects by single function from array of 3\nCurriculum: LRFFC L1\nLearner Level: Early Learner\nBaseline: Near mastery\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects by single function from array of 3\n- Curriculum: LRFFC L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: blanket, ball, glue\nDistractor stimuli: key, spoon\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy across 2 consecutive sessions with at least 10 trials each.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "64efc35e51522eba", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects by single function from array of 3", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "fr2", "error_correction": "transfer_trial", "mastery_criterion": "mc_80_2sessions"}, "teacher_model": null, "seed_tag": "15942"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5679\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Mand + Reading + Tact\nDate range: Sessions 1\u20136 across 12 days (2026-09-06 to 2026-09-18)\n\nACCELERATION PROGRAMS\n1. tacts common objects (Tact)\n Method: DTT\n2. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n3. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n4. sounds out CVC words (Reading)\n Method: DTT\n5. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-06 \u2014 40 min \u2014 1 observer\n tacts common objects: 3/8 correct (35%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 3/8 correct (38%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/15 correct (28%); latency 4.9s; prompts FP\u00d75, PP\u00d72, G\u00d75, I\u00d73\n sounds out CVC words: 5/14 correct (33%); latency 4.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d710\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/15 correct (26%); latency 5.0s; prompts FP\u00d74, PP\u00d73, G\u00d75, I\u00d73\n\nSession 2 \u2014 2026-09-08 \u2014 40 min \u2014 1 observer\n tacts common objects: 6/13 correct (45%); latency 3.7s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 4/8 correct (47%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/8 correct (35%); latency 4.7s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n sounds out CVC words: 3/8 correct (41%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/15 correct (39%); latency 4.5s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d79\n\nSession 3 \u2014 2026-09-10 \u2014 40 min \u2014 1 observer\n tacts common objects: 5/10 correct (53%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n requesting a break ('break please' or AAC 'I need a break'): 7/14 correct (52%); latency 3.8s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/13 correct (42%); latency 4.0s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d76\n sounds out CVC words: 5/10 correct (47%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/15 correct (47%); latency 4.0s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d712\n\nSession 4 \u2014 2026-09-12 \u2014 40 min \u2014 1 observer\n tacts common objects: 10/15 correct (65%); latency 3.0s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d710\n requesting a break ('break please' or AAC 'I need a break'): 8/13 correct (60%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/10 correct (51%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d77\n sounds out CVC words: 5/9 correct (55%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/14 correct (58%); latency 3.5s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d79\n\nSession 5 \u2014 2026-09-14 \u2014 40 min \u2014 1 observer\n tacts common objects: 6/8 correct (73%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 8/11 correct (70%); latency 3.0s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/9 correct (61%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d73\n sounds out CVC words: 8/12 correct (67%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/12 correct (72%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d77\n\nSession 6 \u2014 2026-09-16 \u2014 40 min \u2014 1 observer\n tacts common objects: 11/14 correct (82%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 6/8 correct (78%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/8 correct (67%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n sounds out CVC words: 7/9 correct (73%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 12/15 correct (80%); latency 2.6s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d77\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Requesting more trials verbally\n- Reaching for materials proactively\n- Quick response latency (within 2\u20133 seconds)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 35% to 82% across 6 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nlow\n\nInsufficient data: only 6 sessions, high variance, and/or no IOA evidence. Recommend additional data collection before programming changes.\n\n## Data-Supported Rationale\n- Mean accuracy across 6 sessions: 58.8%.\n- Trend direction: upward (first session: 35%, last session: 82%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "4296ba4bf545019c", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "low", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "early", "n_sessions": 6, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "81519"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: traces basic shapes (circle, cross)\nCurriculum: Writing L1\nLearner: Early Learner\nMastery Status: Near mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: traces basic shapes (circle, cross)\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: square, triangle, diamond\nDistractor stimuli: oval, circle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "55c107a6331e4d5d", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "traces basic shapes (circle, cross)", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "fr2", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "15942"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: meal cleanup\nCurriculum: AFLS Home Skills\nLearner: Adult Learner\nMastery Status: Emerging\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: meal cleanup\n- Curriculum: AFLS Home Skills\n- Learner: Adult Learner\n- Current mastery: Emerging\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Stack used dishes on one side of the table. <- Learner-taught step (forward chaining starts here)\n2. Carry dishes to the sink or dishwasher.\n3. Rinse food residue into the trash or disposal.\n4. Load dishes into the dishwasher (or wash by hand).\n5. Wipe the table with a damp cloth.\n6. Put away any leftover food into containers.\n7. Place containers in the refrigerator.\n\n## Prompt Strategy Per Step\nStrategy: Graduated Guidance\nHand-over-hand physical guidance with fading pressure; move to shadow, then independent.\nCurrent prompt level: At the emerging stage, provide hand-over-hand guidance at each step; reduce physical pressure across sessions.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "8e1038fba436c97c", "gold_labels": {"method": "task_analysis", "domain": "AFLS.home", "skill": "meal cleanup", "program_type": "independence", "learner_profile": "adult", "mastery_state": "emerging", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "meal cleanup", "module": "home", "mastery_criterion": "mc_self_initiation", "chain_type": "forward", "prompt_strategy": "graduated_guidance", "reinforcement_schedule": "crf_per_step", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "6035"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7884\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Mand + Reading + Tolerating Denied Access\nDate range: Sessions 1\u20137 across 14 days (2026-10-19 to 2026-11-02)\n\nACCELERATION PROGRAMS\n1. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n2. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n3. sounds out CVC words (Reading)\n Method: DTT\n4. mands for missing items needed to complete an activity (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Verbal aggression \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-19 \u2014 33 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 7/15 correct (45%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d75, I\u00d78\n answers WH-questions about familiar topics: 7/13 correct (51%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d710\n sounds out CVC words: 4/10 correct (41%); latency 3.9s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n mands for missing items needed to complete an activity: 5/13 correct (40%); latency 4.4s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d75\n Verbal aggression: freq 2\n ABC (verbal aggression): A = transition to non-preferred activity; B = dropped to floor, cried; C = transition delayed, preferred item offered\n\nSession 2 \u2014 2026-10-21 \u2014 33 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 5/9 correct (57%); latency 3.2s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n answers WH-questions about familiar topics: 4/8 correct (54%); latency 3.7s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n sounds out CVC words: 6/11 correct (51%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d78\n mands for missing items needed to complete an activity: 6/13 correct (47%); latency 3.6s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n Verbal aggression: freq 2\n ABC (verbal aggression): A = demand to complete math problem; B = threw materials and vocalized 'no'; C = staff removed demand, redirected\n\nSession 3 \u2014 2026-10-23 \u2014 33 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/11 correct (69%); latency 2.7s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n answers WH-questions about familiar topics: 9/15 correct (58%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d75, I\u00d76\n sounds out CVC words: 6/9 correct (62%); latency 3.3s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n mands for missing items needed to complete an activity: 5/9 correct (56%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n Verbal aggression: freq 0\n\nSession 4 \u2014 2026-10-25 \u2014 33 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 7/9 correct (79%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d72\n answers WH-questions about familiar topics: 7/10 correct (67%); latency 3.0s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n sounds out CVC words: 7/10 correct (70%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n mands for missing items needed to complete an activity: 10/15 correct (64%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d75\n Verbal aggression: freq 2\n\nSession 5 \u2014 2026-10-27 \u2014 33 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 10/13 correct (79%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d77\n answers WH-questions about familiar topics: 11/15 correct (71%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d79\n sounds out CVC words: 10/14 correct (75%); latency 2.8s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d79\n mands for missing items needed to complete an activity: 7/9 correct (73%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n Verbal aggression: freq 1\n ABC (verbal aggression): A = demand to complete math problem; B = threw materials and vocalized 'no'; C = staff removed demand, redirected\n\nSession 6 \u2014 2026-10-29 \u2014 33 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 11/14 correct (79%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d79\n answers WH-questions about familiar topics: 10/13 correct (77%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d73\n sounds out CVC words: 11/15 correct (75%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d76\n mands for missing items needed to complete an activity: 8/11 correct (76%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d76\n Verbal aggression: freq 2\n\nSession 7 \u2014 2026-10-31 \u2014 33 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 9/12 correct (79%); latency 2.2s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d72\n answers WH-questions about familiar topics: 8/10 correct (83%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n sounds out CVC words: 8/11 correct (75%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n mands for missing items needed to complete an activity: 6/8 correct (76%); latency 2.3s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n Verbal aggression: freq 1\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Playing with non-task materials\n- Looking away during SD presentation\n- Echolalic responding (repeating SD rather than answering)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 45% at return, recovering to 79%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Behavior Function Hypothesis\nVerbal aggression: escape\n Evidence: ABC events in the log support the escape function; behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 69.5%.\n- Trend direction: upward (first session: 45%, last session: 79%).\n- Verbal aggression: mean 1.4/session (early-window mean 2.0 -> late-window mean 1.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "cce0ec4a4aecddae", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {"Verbal aggression": "escape"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "early", "n_sessions": 7, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["verbal_aggression"], "behavior_functions": ["escape"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "39736"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: tacts colors of objects\nCurriculum: Tact L2\nLearner Level: School-Age Learner\nBaseline: Near mastery\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts colors of objects\n- Curriculum: Tact L2\n- Learner: School-Age Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What color?\"\nVariations: \"What color is this?\"; \"Tell me the color\"\nPresentation: Present a single-color object and ask while pointing to it.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: red, green, yellow\nDistractor stimuli: black, purple, blue, orange\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "fdfb3659e4e50012", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L2", "learner_profile": "school_age", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts colors of objects", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "vr3", "error_correction": "backstep", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "69141"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: names items in categories when given the category\nCurriculum: Intraverbal L2\nLearner: Early Learner\nMastery Status: Mastered at current level\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: names items in categories when given the category\n- Curriculum: Intraverbal L2\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: leisure chat.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's leisure chat routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "a9824a31a75a5a55", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L2", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "names items in categories when given the category", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "time_delay", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "70431"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: ordering in a restaurant\nCurriculum Reference: AFLS Community Participation Skills\nLearner Profile: Adult Learner\nCurrent Mastery: Generalization phase\nTeaching Method: Task Analysis / Chaining\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: ordering in a restaurant\n- Curriculum: AFLS Community Participation Skills\n- Learner: Adult Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Approach the counter or wait to be seated.\n2. Review the menu.\n3. Decide on a choice.\n4. Place the order verbally (or with an AAC device).\n5. Respond to clarifying questions.\n6. Pay using money or a card.\n7. Wait for the order and collect it.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 60s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "0d5a9e3ea8e2b305", "gold_labels": {"method": "task_analysis", "domain": "AFLS.community", "skill": "ordering in a restaurant", "program_type": "independence", "learner_profile": "adult", "mastery_state": "generalization", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "ordering in a restaurant", "module": "community", "mastery_criterion": "mc_fluent_chain", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "50630"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4806\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand\nDate range: Sessions 1\u201311 across 22 days (2026-08-27 to 2026-09-18)\n\nACCELERATION PROGRAMS\n1. requesting preferred items using a full sentence (Mand)\n Method: NET\n2. single-word requests for preferred items (Mand)\n Method: NET\n3. requesting preferred items using AAC device (e.g., \"I want cookie please\") (Mand)\n Method: NET\n4. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n5. requesting a break during non-preferred tasks (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-27 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 4/8 correct (52%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n single-word requests for preferred items: 8/15 correct (53%); latency 3.6s; prompts FP\u00d75, PP\u00d70, G\u00d73, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 5/8 correct (57%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n indicating 'all done' when an activity is complete: 7/13 correct (51%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d77\n requesting a break during non-preferred tasks: 8/14 correct (56%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d712\n\nSession 2 \u2014 2026-08-29 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 8/13 correct (60%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n single-word requests for preferred items: 8/14 correct (59%); latency 3.2s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d79\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 5/9 correct (53%); latency 3.7s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n indicating 'all done' when an activity is complete: 8/15 correct (51%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d710\n requesting a break during non-preferred tasks: 9/15 correct (62%); latency 3.4s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d76\n\nSession 3 \u2014 2026-08-31 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 10/15 correct (66%); latency 3.2s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d79\n single-word requests for preferred items: 6/11 correct (52%); latency 3.6s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 5/12 correct (44%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d79\n indicating 'all done' when an activity is complete: 5/8 correct (58%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n requesting a break during non-preferred tasks: 10/14 correct (69%); latency 2.8s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d77\n\nSession 4 \u2014 2026-09-02 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 6/11 correct (56%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n single-word requests for preferred items: 7/14 correct (50%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d711\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/15 correct (54%); latency 3.5s; prompts FP\u00d75, PP\u00d75, G\u00d72, I\u00d73\n indicating 'all done' when an activity is complete: 5/8 correct (57%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n requesting a break during non-preferred tasks: 10/15 correct (63%); latency 3.4s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d78\n\nSession 5 \u2014 2026-09-04 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 10/14 correct (69%); latency 3.1s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d78\n single-word requests for preferred items: 7/14 correct (52%); latency 3.9s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d75\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/15 correct (48%); latency 3.8s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d711\n indicating 'all done' when an activity is complete: 5/9 correct (59%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n requesting a break during non-preferred tasks: 8/11 correct (69%); latency 2.9s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n\nSession 6 \u2014 2026-09-06 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 6/8 correct (70%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n single-word requests for preferred items: 5/10 correct (46%); latency 4.0s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/14 correct (53%); latency 3.7s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d78\n indicating 'all done' when an activity is complete: 6/11 correct (58%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n requesting a break during non-preferred tasks: 7/11 correct (64%); latency 3.0s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n\nSession 7 \u2014 2026-09-08 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 8/11 correct (70%); latency 2.7s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n single-word requests for preferred items: 5/11 correct (45%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 4/9 correct (48%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n indicating 'all done' when an activity is complete: 8/14 correct (55%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d77\n requesting a break during non-preferred tasks: 9/14 correct (62%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d76\n\nSession 8 \u2014 2026-09-10 \u2014 IOA SESSION \u2014 2 observers\n requesting preferred items using a full sentence: 59% (primary); IOA 82% agreement\n single-word requests for preferred items: 40% (primary); IOA 82% agreement\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 51% (primary); IOA 82% agreement\n indicating 'all done' when an activity is complete: 59% (primary); IOA 82% agreement\n requesting a break during non-preferred tasks: 68% (primary); IOA 82% agreement\n\nSession 9 \u2014 2026-09-12 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 8/13 correct (60%); latency 3.3s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d711\n single-word requests for preferred items: 7/15 correct (46%); latency 4.1s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 6/12 correct (51%); latency 3.5s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d75\n indicating 'all done' when an activity is complete: 7/14 correct (49%); latency 4.0s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d710\n requesting a break during non-preferred tasks: 11/14 correct (77%); latency 2.4s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d77\n\nSession 10 \u2014 2026-09-14 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 8/12 correct (67%); latency 3.0s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d76\n single-word requests for preferred items: 3/8 correct (34%); latency 4.5s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/14 correct (58%); latency 3.6s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d76\n indicating 'all done' when an activity is complete: 5/9 correct (50%); latency 3.5s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n requesting a break during non-preferred tasks: 7/9 correct (75%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n\nSession 11 \u2014 2026-09-16 \u2014 44 min \u2014 1 observer\n requesting preferred items using a full sentence: 6/8 correct (77%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n single-word requests for preferred items: 6/13 correct (45%); latency 4.1s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d75\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/13 correct (51%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n indicating 'all done' when an activity is complete: 4/8 correct (54%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n requesting a break during non-preferred tasks: 6/8 correct (79%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Stereotypic behavior during inter-trial intervals\n- Delayed responding (>5 seconds consistently)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Plateau**: accuracy has remained near 64% for 11 sessions without meaningful improvement.\n- Performance is below mastery criteria; current teaching procedure may not be effective for this learner.\n\n## Pattern Classification\nplateau\n\nResponding has stabilized below mastery criterion without meaningful movement, indicating the current procedure is limiting further acquisition.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Modify teaching procedure \u2014 switch prompt type (e.g., from most-to-least to time delay).\n- Conduct preference assessment and update reinforcer menu.\n- Break the current skill into smaller component steps if possible.\n- Increase practice opportunities by embedding targets in natural-environment training.\n\n### Consequence strategies\n- Check for inadvertent reinforcement of near-misses; tighten differential reinforcement.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 11 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 64.3%.\n- Trend direction: upward (first session: 52%, last session: 77%).\n- IOA data: 82% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "19459347411eaca6", "gold_labels": {"pattern_class": "plateau", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "plateau", "learner_profile": "school_age", "n_sessions": 11, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "57608"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6052\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Mand + Reading + Self-Care + Writing\nDate range: Sessions 1\u20139 across 18 days (2026-05-11 to 2026-05-29)\n\nACCELERATION PROGRAMS\n1. identifying community safety signs (Community)\n Method: DTT\n2. requesting a break during non-preferred activities (Mand)\n Method: NET\n3. copies simple words from model (Writing)\n Method: DTT\n4. brushing teeth independently (Self-Care)\n Method: Task Analysis\n5. reads 10\u201320 sight words (Reading)\n Method: DTT\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-11 \u2014 60 min \u2014 1 observer\n identifying community safety signs: 12/12 correct (96%); latency 1.6s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d77\n requesting a break during non-preferred activities: 14/15 correct (94%); latency 2.0s; prompts FP\u00d72, PP\u00d75, G\u00d74, I\u00d74\n copies simple words from model: 10/11 correct (89%); latency 1.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n brushing teeth independently: 9/12 correct (77%); latency 2.6s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d75\n reads 10\u201320 sight words: 8/8 correct (98%); latency 1.6s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n Self-injurious behavior (SIB): freq 1\n\nSession 2 \u2014 2026-05-13 \u2014 60 min \u2014 1 observer\n identifying community safety signs: 10/10 correct (97%); latency 1.3s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n requesting a break during non-preferred activities: 9/9 correct (95%); latency 1.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d77\n copies simple words from model: 7/8 correct (88%); latency 1.8s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n brushing teeth independently: 9/11 correct (80%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 12/12 correct (97%); latency 1.8s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d70\n Self-injurious behavior (SIB): freq 1\n\nSession 3 \u2014 2026-05-15 \u2014 60 min \u2014 1 observer\n identifying community safety signs: 14/14 correct (98%); latency 1.3s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d77\n requesting a break during non-preferred activities: 9/10 correct (94%); latency 1.6s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d72\n copies simple words from model: 11/13 correct (85%); latency 1.9s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d75\n brushing teeth independently: 10/12 correct (87%); latency 2.3s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d78\n reads 10\u201320 sight words: 13/14 correct (96%); latency 1.6s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n Self-injurious behavior (SIB): freq 0\n\nSession 4 \u2014 2026-05-17 \u2014 IOA SESSION \u2014 2 observers\n identifying community safety signs: 98% (primary); IOA 85% agreement\n requesting a break during non-preferred activities: 90% (primary); IOA 85% agreement\n copies simple words from model: 83% (primary); IOA 85% agreement\n brushing teeth independently: 85% (primary); IOA 85% agreement\n reads 10\u201320 sight words: 88% (primary); IOA 85% agreement\n Self-injurious behavior (SIB): freq 0; IOA 85% agreement\n\nSession 5 \u2014 2026-05-19 \u2014 60 min \u2014 1 observer\n identifying community safety signs: 13/13 correct (98%); latency 1.3s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d76\n requesting a break during non-preferred activities: 9/10 correct (94%); latency 1.7s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d76\n copies simple words from model: 8/9 correct (83%); latency 2.1s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n brushing teeth independently: 12/14 correct (84%); latency 2.3s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d77\n reads 10\u201320 sight words: 13/14 correct (90%); latency 1.8s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d76\n Self-injurious behavior (SIB): freq 0\n\nSession 6 \u2014 2026-05-21 \u2014 60 min \u2014 1 observer\n identifying community safety signs: 9/9 correct (98%); latency 1.9s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n requesting a break during non-preferred activities: 7/8 correct (93%); latency 1.6s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n copies simple words from model: 11/14 correct (78%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d78\n brushing teeth independently: 10/12 correct (85%); latency 2.3s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 10/12 correct (84%); latency 2.0s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d77\n Self-injurious behavior (SIB): freq 1\n\nSession 7 \u2014 2026-05-23 \u2014 60 min \u2014 1 observer\n identifying community safety signs: 9/9 correct (98%); latency 1.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n requesting a break during non-preferred activities: 10/11 correct (87%); latency 1.9s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n copies simple words from model: 10/12 correct (80%); latency 2.1s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d78\n brushing teeth independently: 10/12 correct (86%); latency 2.3s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d75\n reads 10\u201320 sight words: 8/9 correct (87%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d74\n Self-injurious behavior (SIB): freq 0\n\nSession 8 \u2014 2026-05-25 \u2014 60 min \u2014 1 observer\n identifying community safety signs: 11/11 correct (98%); latency 1.6s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n requesting a break during non-preferred activities: 9/10 correct (88%); latency 2.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n copies simple words from model: 11/15 correct (74%); latency 2.6s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d79\n brushing teeth independently: 10/11 correct (91%); latency 1.7s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d78\n reads 10\u201320 sight words: 9/11 correct (86%); latency 2.3s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d74\n Self-injurious behavior (SIB): freq 2\n\nSession 9 \u2014 2026-05-27 \u2014 60 min \u2014 1 observer\n identifying community safety signs: 12/12 correct (98%); latency 1.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d78\n requesting a break during non-preferred activities: 9/10 correct (88%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d78\n copies simple words from model: 6/8 correct (76%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n brushing teeth independently: 13/15 correct (89%); latency 2.0s; prompts FP\u00d75, PP\u00d71, G\u00d73, I\u00d76\n reads 10\u201320 sight words: 7/8 correct (81%); latency 2.1s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n Self-injurious behavior (SIB): freq 0\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Looking away during SD presentation\n- Leaving seat without permission\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (96%\u201398%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nhigh\n\nPattern is well-supported: 9 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 97.7%.\n- Trend direction: upward (first session: 96%, last session: 98%).\n- Self-injurious behavior (SIB): mean 0.6/session (early-window mean 0.7 -> late-window mean 0.7).\n- IOA data: 85% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "b7bc12fb0edf56c7", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {"Self-injurious behavior (SIB)": "escape"}, "escalation_level": 3, "confidence": "high", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "adolescent", "n_sessions": 9, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["sib"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "22832"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: mands to indicate completion in context (\"I'm all done with math, can I start reading?\")\nCurriculum: Mand L3\nLearner Level: Adolescent Learner\nBaseline: Mastered at current level\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands to indicate completion in context (\"I'm all done with math, can I start reading?\")\n- Curriculum: Mand L3\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nSet up a clearly-bounded activity with a visible endpoint (e.g., a worksheet, a puzzle, a sorting task). Wait for the learner to indicate completion verbally or via AAC; honor the indication immediately.\nPrimary natural context: sorting task.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's sorting task routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: the activity ends immediately and the learner transitions to the next preferred activity.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use with a peer in unstructured free play across 2 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "9bc27945514f32f3", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L3", "learner_profile": "adolescent", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands to indicate completion in context (\"I'm all done with math, can I start reading?\")", "mo_category": "mand_completion", "mo_arrangement": "completion_opportunity", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_peer_initiation"}, "teacher_model": null, "seed_tag": "44373"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: answers hypothetical questions\nCurriculum: Intraverbal L3\nLearner: Adolescent Learner\nMastery Status: Developing\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: answers hypothetical questions\n- Curriculum: Intraverbal L3\n- Learner: Adolescent Learner\n- Current mastery: Developing\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: leisure chat.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's leisure chat routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the developing stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "9d02438086548861", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L3", "learner_profile": "adolescent", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "answers hypothetical questions", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "time_delay", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "77480"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8083\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Reading\nDate range: Sessions 1\u201310 across 20 days (2026-08-20 to 2026-09-09)\n\nACCELERATION PROGRAMS\n1. sounds out CVC words (Reading)\n Method: DTT\n2. selects items by feature (Listener Responding)\n Method: DTT\n3. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n4. reads 10\u201320 sight words (Reading)\n Method: DTT\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-20 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 3/9 correct (36%); latency 4.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n selects items by feature: 6/13 correct (45%); latency 4.1s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d78\n follows 1-step motor instructions: 4/13 correct (34%); latency 4.7s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d76\n reads 10\u201320 sight words: 6/15 correct (43%); latency 3.9s; prompts FP\u00d73, PP\u00d75, G\u00d74, I\u00d73\n\nSession 2 \u2014 2026-08-22 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 5/12 correct (40%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n selects items by feature: 8/15 correct (55%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d79\n follows 1-step motor instructions: 5/13 correct (38%); latency 4.5s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n reads 10\u201320 sight words: 5/11 correct (45%); latency 4.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n\nSession 3 \u2014 2026-08-24 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 8/15 correct (51%); latency 3.7s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d710\n selects items by feature: 7/11 correct (64%); latency 3.0s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d77\n follows 1-step motor instructions: 7/15 correct (48%); latency 3.7s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d79\n reads 10\u201320 sight words: 5/9 correct (53%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n\nSession 4 \u2014 2026-08-26 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 8/14 correct (57%); latency 3.4s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d77\n selects items by feature: 6/8 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n follows 1-step motor instructions: 8/15 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d75\n reads 10\u201320 sight words: 8/14 correct (58%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d77\n\nSession 5 \u2014 2026-08-28 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 8/14 correct (57%); latency 3.7s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d72\n selects items by feature: 7/10 correct (74%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n follows 1-step motor instructions: 6/10 correct (57%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d76\n reads 10\u201320 sight words: 5/9 correct (57%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n\nSession 6 \u2014 2026-08-30 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 9/14 correct (66%); latency 3.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d78\n selects items by feature: 8/10 correct (79%); latency 2.1s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n follows 1-step motor instructions: 10/14 correct (70%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d712\n reads 10\u201320 sight words: 7/10 correct (68%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d73\n\nSession 7 \u2014 2026-09-01 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 5/8 correct (64%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n selects items by feature: 10/12 correct (82%); latency 2.6s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d77\n follows 1-step motor instructions: 10/15 correct (69%); latency 2.8s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 9/12 correct (71%); latency 2.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d710\n\nSession 8 \u2014 2026-09-03 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 6/9 correct (66%); latency 2.8s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n selects items by feature: 11/12 correct (95%); latency 1.7s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d76\n follows 1-step motor instructions: 10/13 correct (79%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d75\n reads 10\u201320 sight words: 6/8 correct (70%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n\nSession 9 \u2014 2026-09-05 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 8/11 correct (73%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n selects items by feature: 11/12 correct (95%); latency 2.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d79\n follows 1-step motor instructions: 9/11 correct (84%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n reads 10\u201320 sight words: 10/13 correct (78%); latency 2.7s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d78\n\nSession 10 \u2014 2026-09-07 \u2014 49 min \u2014 1 observer\n sounds out CVC words: 8/11 correct (75%); latency 2.8s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n selects items by feature: 13/14 correct (95%); latency 1.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d711\n follows 1-step motor instructions: 9/9 correct (95%); latency 1.8s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n reads 10\u201320 sight words: 8/10 correct (84%); latency 2.0s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d75\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Requesting more trials verbally\n- Smiling during reinforcement delivery"}, {"role": "assistant", "content": "## Clinical Concerns\n- Steady improvement: accuracy rose from 36% to 75% across 10 sessions.\n- No clinical concerns at this time; mastery criteria should be reachable within a few additional sessions.\n\n## Pattern Classification\nmastery_progression\n\nAccuracy is ascending cleanly across sessions with no interfering behaviors, consistent with a mastery-progression trajectory.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Continue current teaching procedure \u2014 it is effective for this learner.\n- Maintain current stimulus arrangement; begin planning next skill in sequence.\n\n### Consequence strategies\n- Begin thinning reinforcement from CRF to FR-2 as accuracy stabilizes above 85%.\n- Continue differential reinforcement for independent responses.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 58.5%.\n- Trend direction: upward (first session: 36%, last session: 75%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "172f70bc92f86142", "gold_labels": {"pattern_class": "mastery_progression", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "mastery_progression", "learner_profile": "early", "n_sessions": 10, "n_programs": 4, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "40195"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: points to named common objects\nCurriculum Reference: Listener Responding L1\nLearner Profile: Early Learner\nCurrent Mastery: Emerging\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: points to named common objects\n- Curriculum: Listener Responding L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: scissors, plate, blanket\nDistractor stimuli: cup, crayon\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "f9393e468b1c91c3", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "points to named common objects", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "crf", "error_correction": "four_step", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "60118"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: completing assigned tasks in order\nCurriculum: AFLS Vocational Skills\nLearner: Adolescent Learner\nMastery Status: Approaching mastery\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: completing assigned tasks in order\n- Curriculum: AFLS Vocational Skills\n- Learner: Adolescent Learner\n- Current mastery: Approaching mastery\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Review the task list for the shift. <- Learner-taught step (forward chaining starts here)\n2. Gather needed materials for the first task.\n3. Complete the first task to the specified standard.\n4. Mark the first task complete on the list.\n5. Return materials to storage.\n6. Move to the next task on the list and repeat.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the approaching mastery stage, use partial-physical or gestural prompts only at steps where errors occur; allow independence elsewhere.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 90s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "16caf940ee524f4f", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "completing assigned tasks in order", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "approaching", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "completing assigned tasks in order", "module": "vocational", "mastery_criterion": "mc_fluent_chain", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "crf_per_step", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "50550"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5625\nProfile: Adult Learner (18+ years)\nCurricula: Independent Living + Self-Care + Vocational\nDate range: Sessions 1\u20139 across 18 days (2026-05-09 to 2026-05-27)\n\nACCELERATION PROGRAMS\n1. clocking in at start of shift (Vocational)\n Method: Task Analysis\n2. brushing teeth independently (Self-Care)\n Method: Task Analysis\n3. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n4. managing a budget (Independent Living)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Vocal stereotypy \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-09 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 8/14 correct (58%); latency 3.3s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n brushing teeth independently: 8/14 correct (61%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d76\n dressing (pants, shirt): 7/9 correct (75%); latency 2.8s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n managing a budget: 9/14 correct (61%); latency 3.3s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d75\n Vocal stereotypy: freq 2; PIR 15%\n\nSession 2 \u2014 2026-05-11 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 8/15 correct (57%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d710\n brushing teeth independently: 10/15 correct (68%); latency 2.7s; prompts FP\u00d75, PP\u00d75, G\u00d72, I\u00d73\n dressing (pants, shirt): 9/12 correct (79%); latency 2.3s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d75\n managing a budget: 6/12 correct (53%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d74\n Vocal stereotypy: freq 2; PIR 13%\n\nSession 3 \u2014 2026-05-13 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 8/13 correct (64%); latency 3.2s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d73\n brushing teeth independently: 5/9 correct (59%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n dressing (pants, shirt): 8/11 correct (73%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d78\n managing a budget: 8/14 correct (60%); latency 3.3s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d74\n Vocal stereotypy: freq 2; PIR 16%\n\nSession 4 \u2014 2026-05-15 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 3/15 correct (23%); latency 5.1s; prompts FP\u00d70, PP\u00d71, G\u00d75, I\u00d79\n brushing teeth independently: 3/8 correct (40%); latency 4.4s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n dressing (pants, shirt): 5/8 correct (59%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n managing a budget: 2/8 correct (27%); latency 4.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n Vocal stereotypy: freq 4; PIR 20%\n\nSession 5 \u2014 2026-05-17 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 4/15 correct (29%); latency 5.0s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d710\n brushing teeth independently: 6/11 correct (51%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d78\n dressing (pants, shirt): 8/12 correct (66%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d76\n managing a budget: 5/15 correct (36%); latency 4.1s; prompts FP\u00d70, PP\u00d72, G\u00d75, I\u00d78\n Vocal stereotypy: freq 5; PIR 27%\n\nSession 6 \u2014 2026-05-19 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 5/12 correct (41%); latency 4.3s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d76\n brushing teeth independently: 8/13 correct (59%); latency 3.6s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d74\n dressing (pants, shirt): 7/10 correct (74%); latency 2.9s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n managing a budget: 4/9 correct (45%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n Vocal stereotypy: freq 1; PIR 14%\n\nSession 7 \u2014 2026-05-21 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 5/10 correct (47%); latency 4.2s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d77\n brushing teeth independently: 8/13 correct (64%); latency 3.2s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d75\n dressing (pants, shirt): 10/14 correct (74%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d712\n managing a budget: 4/8 correct (48%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n Vocal stereotypy: freq 1; PIR 7%\n\nSession 8 \u2014 2026-05-23 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 5/9 correct (55%); latency 3.7s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n brushing teeth independently: 7/11 correct (64%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d77\n dressing (pants, shirt): 10/14 correct (74%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d79\n managing a budget: 7/13 correct (54%); latency 3.6s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d78\n Vocal stereotypy: freq 1; PIR 7%\n\nSession 9 \u2014 2026-05-25 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 8/13 correct (59%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d76\n brushing teeth independently: 9/14 correct (64%); latency 3.1s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d77\n dressing (pants, shirt): 10/13 correct (74%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d710\n managing a budget: 7/13 correct (57%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n Vocal stereotypy: freq 2; PIR 14%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Playing with non-task materials\n- Leaving seat without permission\n- Stereotypic behavior during inter-trial intervals"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Behavior Function Hypothesis\nVocal stereotypy: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 47.9%.\n- Trend direction: upward (first session: 58%, last session: 59%).\n- Vocal stereotypy: mean 2.2/session (early-window mean 2.0 -> late-window mean 1.3).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "bbb60b2a6fe48cf6", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {"Vocal stereotypy": "automatic"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "adult", "n_sessions": 9, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["vocal_stereotypy"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "11442"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: completing assigned tasks in order\nCurriculum: AFLS Vocational Skills\nLearner: Adult Learner\nMastery Status: Generalization phase\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: completing assigned tasks in order\n- Curriculum: AFLS Vocational Skills\n- Learner: Adult Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Backward chaining\nComplete all steps for the learner except the last; teach the last step first, then work backward. The final reinforcer (task completion) is always present for the learner.\n\nSteps:\n1. Review the task list for the shift.\n2. Gather needed materials for the first task.\n3. Complete the first task to the specified standard.\n4. Mark the first task complete on the list.\n5. Return materials to storage.\n6. Move to the next task on the list and repeat. <- Learner-taught step (backward chaining starts here)\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "1b45ae57fb99c795", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "completing assigned tasks in order", "program_type": "independence", "learner_profile": "adult", "mastery_state": "generalization", "chain_type": "backward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "completing assigned tasks in order", "module": "vocational", "mastery_criterion": "mc_self_initiation", "chain_type": "backward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "6035"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: tolerating nail clipping\nCurriculum Reference: AFLS Basic Living Skills\nLearner Profile: Adult Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: Toleration / Systematic Desensitization\n\nThe goal is for the learner to allow the activity to be performed (not to perform it independently). Provide the full program structure including shaping steps and refusal/safety procedures."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating nail clipping\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Mastered at current level\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for nail clipping performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nall 10 fingernails (and optionally toenails) clipped by caregiver without refusal, pulling hand away, or safety behaviors\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1 fingernail clipped\n2. 2 fingernails clipped in one sitting\n3. 5 fingernails clipped (one hand)\n4. All 10 fingernails clipped\n5. All 10 fingernails + 10 toenails clipped\n\nCurrent shaping step: At the mastered stage, begin at shaping step 5 (\"All 10 fingernails + 10 toenails clipped\") and advance through step 5 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal activity tolerated across 2 different settings (e.g., home and clinic) across 2 consecutive weeks without safety behaviors.\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 2 different settings and with 3 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "051b5e3d5b8c3bd9", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating nail clipping", "program_type": "toleration", "learner_profile": "adult", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating nail clipping", "module": "basic_living", "mastery_criterion": "mc_toleration_settings", "shaping_n_steps": 5}, "teacher_model": null, "seed_tag": "21081"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7206\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Self-Care + Writing\nDate range: Sessions 1\u20138 across 16 days (2026-05-02 to 2026-05-18)\n\nACCELERATION PROGRAMS\n1. identifying community safety signs (Community)\n Method: DTT\n2. copies simple words from model (Writing)\n Method: DTT\n3. tolerating haircut (Self-Care)\n Method: Task Analysis\n4. washing hands independently (Self-Care)\n Method: Task Analysis\n5. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Elopement \u2014 function hypothesized: tangible\n2. Property destruction \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-02 \u2014 39 min \u2014 1 observer\n identifying community safety signs: 7/11 correct (67%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d73\n copies simple words from model: 6/9 correct (66%); latency 3.0s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n tolerating haircut: 9/15 correct (61%); latency 3.0s; prompts FP\u00d75, PP\u00d71, G\u00d74, I\u00d75\n washing hands independently: 5/9 correct (54%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n meal cleanup after eating: 6/9 correct (61%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n Elopement: freq 1\n Property destruction: freq 2\n\nSession 2 \u2014 2026-05-04 \u2014 39 min \u2014 1 observer\n identifying community safety signs: 10/15 correct (68%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d76\n copies simple words from model: 6/9 correct (69%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n tolerating haircut: 6/10 correct (58%); latency 3.5s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n washing hands independently: 7/14 correct (52%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n meal cleanup after eating: 8/12 correct (67%); latency 2.9s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d73\n Elopement: freq 0\n Property destruction: freq 1\n\nSession 3 \u2014 2026-05-06 \u2014 39 min \u2014 1 observer\n identifying community safety signs: 8/12 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d710\n copies simple words from model: 6/8 correct (70%); latency 2.9s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n tolerating haircut: 8/14 correct (60%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d710\n washing hands independently: 5/8 correct (61%); latency 3.2s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n meal cleanup after eating: 8/12 correct (68%); latency 3.1s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d75\n Elopement: freq 5\n Property destruction: freq 4\n\nSession 4 \u2014 2026-05-08 \u2014 39 min \u2014 1 observer\n identifying community safety signs: 9/13 correct (69%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d77\n copies simple words from model: 6/9 correct (69%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n tolerating haircut: 6/9 correct (67%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n washing hands independently: 5/10 correct (54%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n meal cleanup after eating: 9/14 correct (65%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d76\n Elopement: freq 4\n Property destruction: freq 4\n\nSession 5 \u2014 2026-05-10 \u2014 39 min \u2014 1 observer\n identifying community safety signs: 8/12 correct (65%); latency 3.3s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d71\n copies simple words from model: 7/10 correct (71%); latency 2.9s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n tolerating haircut: 7/11 correct (65%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d73\n washing hands independently: 7/12 correct (57%); latency 3.7s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d74\n meal cleanup after eating: 9/14 correct (67%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d78\n Elopement: freq 1\n Property destruction: freq 2\n\nSession 6 \u2014 2026-05-12 \u2014 39 min \u2014 1 observer\n identifying community safety signs: 8/12 correct (63%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d79\n copies simple words from model: 9/14 correct (67%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d712\n tolerating haircut: 7/11 correct (66%); latency 2.8s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n washing hands independently: 8/12 correct (63%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d711\n meal cleanup after eating: 10/14 correct (71%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d714\n Elopement: freq 1\n Property destruction: freq 0\n\nSession 7 \u2014 2026-05-14 \u2014 39 min \u2014 1 observer\n identifying community safety signs: 6/8 correct (73%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n copies simple words from model: 10/15 correct (64%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d710\n tolerating haircut: 9/13 correct (72%); latency 2.9s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d75\n washing hands independently: 5/8 correct (63%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n meal cleanup after eating: 7/11 correct (67%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n Elopement: freq 1\n Property destruction: freq 1\n\nSession 8 \u2014 2026-05-16 \u2014 39 min \u2014 1 observer\n identifying community safety signs: 9/13 correct (72%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d77\n copies simple words from model: 8/13 correct (64%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n tolerating haircut: 11/15 correct (71%); latency 3.0s; prompts FP\u00d75, PP\u00d71, G\u00d73, I\u00d76\n washing hands independently: 6/9 correct (68%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n meal cleanup after eating: 9/13 correct (71%); latency 2.8s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d79\n Elopement: freq 1\n Property destruction: freq 2\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Turning away from task or staff\n- Self-stimulatory behavior increase during demand periods\n- Peer aggression (hitting or pushing peers during group activities)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nElopement: tangible\n Evidence: behavior occurs when preferred items are restricted and is followed by access to the item.\nProperty destruction: attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n### Crisis plan\n- If problem-behavior intensity or topography exceeds the learner's baseline safety threshold (SIB causing tissue damage, aggression causing injury, imminent elopement into hazard): pause the extinction procedure and implement the facility's tiered crisis-prevention protocol (e.g., Safety-Care, CPI, or equivalent).\n- De-escalation and environmental safety first; physical intervention is last resort and only by staff currently certified in the facility's framework. Least-restrictive option appropriate to the risk level applies at every step. Physical intervention is used only when specifically authorized for this learner in the BIP \u2014 contraindications (medical, developmental, trauma history) may restrict the procedures available, in which case the plan is de-escalation + environmental safety + supervisor contact only.\n- Contact the supervising BCBA immediately; do not resume the extinction procedure without BCBA review. Document duration, intensity, antecedent, staff response, and post-incident state.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 68.3%.\n- Trend direction: upward (first session: 67%, last session: 72%).\n- Elopement: mean 1.8/session (early-window mean 0.5 -> late-window mean 1.0).\n- Property destruction: mean 2.0/session (early-window mean 1.5 -> late-window mean 1.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "4bd9407b04f41885", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Elopement": "tangible", "Property destruction": "attention"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "adolescent", "n_sessions": 8, "n_programs": 5, "n_behaviors": 2, "behavior_ids": ["elopement", "property_destruction"], "behavior_functions": ["tangible", "attention"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "73910"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a chaining program for the following.\n\nSkill: operating the dishwasher\nCurriculum: AFLS Home Skills\nLearner Level: Adolescent Learner\nBaseline: Mastered at current level\n\nInclude the full Task Analysis structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: operating the dishwasher\n- Curriculum: AFLS Home Skills\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Collect dirty dishes from the table and sink area. <- Learner-taught step (forward chaining starts here)\n2. Scrape any solid food residue into the trash.\n3. Rinse dishes briefly under water.\n4. Open the dishwasher door.\n5. Load plates and bowls into the bottom rack.\n6. Load cups, glasses, and small items into the top rack.\n7. Place utensils handle-down in the utensil basket.\n8. Add detergent to the detergent dispenser.\n9. Close the dishwasher door.\n10. Select the appropriate wash cycle and press Start.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the mastered stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nToken economy \u2014 One token per correctly-completed step; token exchange at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\n100% of steps completed independently (no prompts) across 3 consecutive trials of the full chain.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "9a8ae982b3acf3aa", "gold_labels": {"method": "task_analysis", "domain": "AFLS.home", "skill": "operating the dishwasher", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "mastered", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "operating the dishwasher", "module": "home", "mastery_criterion": "mc_all_steps_independent", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "39765"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5575\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Mand + Self-Care + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u20138 across 16 days (2026-01-13 to 2026-01-29)\n\nACCELERATION PROGRAMS\n1. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n2. doing laundry (Home Skills)\n Method: Task Analysis\n3. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n4. requesting assistance using AAC device (Mand)\n Method: NET\n5. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n6. simple meal preparation (Home Skills)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-13 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 8/13 correct (63%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d710\n doing laundry: 7/14 correct (49%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d77\n dressing (pants, shirt): 4/8 correct (54%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n requesting assistance using AAC device: 6/8 correct (70%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n wait calmly when a preferred activity is denied: 7/14 correct (52%); latency 3.5s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d78\n simple meal preparation: 5/9 correct (56%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n\nSession 2 \u2014 2026-01-15 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 8/12 correct (66%); latency 3.0s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d74\n doing laundry: 5/11 correct (48%); latency 3.6s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n dressing (pants, shirt): 7/13 correct (50%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d78\n requesting assistance using AAC device: 8/12 correct (63%); latency 3.1s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 7/11 correct (61%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n simple meal preparation: 5/9 correct (57%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n\nSession 3 \u2014 2026-01-17 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 5/9 correct (61%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n doing laundry: 6/13 correct (50%); latency 3.6s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d75\n dressing (pants, shirt): 6/12 correct (52%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d76\n requesting assistance using AAC device: 7/10 correct (67%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n wait calmly when a preferred activity is denied: 7/11 correct (67%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d75\n simple meal preparation: 8/11 correct (69%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d75\n\nSession 4 \u2014 2026-01-19 \u2014 IOA SESSION \u2014 2 observers\n completing assigned tasks in order: 66% (primary); IOA 94% agreement\n doing laundry: 44% (primary); IOA 94% agreement\n dressing (pants, shirt): 53% (primary); IOA 94% agreement\n requesting assistance using AAC device: 73% (primary); IOA 94% agreement\n wait calmly when a preferred activity is denied: 59% (primary); IOA 94% agreement\n simple meal preparation: 68% (primary); IOA 94% agreement\n\nSession 5 \u2014 2026-01-21 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 7/11 correct (62%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d77\n doing laundry: 7/13 correct (52%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d78\n dressing (pants, shirt): 4/8 correct (53%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n requesting assistance using AAC device: 6/10 correct (59%); latency 3.3s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n wait calmly when a preferred activity is denied: 7/11 correct (61%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n simple meal preparation: 7/11 correct (68%); latency 2.7s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n\nSession 6 \u2014 2026-01-23 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 6/9 correct (64%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d77\n doing laundry: 6/15 correct (39%); latency 4.3s; prompts FP\u00d75, PP\u00d74, G\u00d73, I\u00d73\n dressing (pants, shirt): 6/10 correct (55%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d77\n requesting assistance using AAC device: 6/8 correct (73%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n wait calmly when a preferred activity is denied: 5/8 correct (66%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n simple meal preparation: 8/15 correct (51%); latency 3.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d711\n\nSession 7 \u2014 2026-01-25 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 8/13 correct (62%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d78\n doing laundry: 6/12 correct (48%); latency 3.7s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d78\n dressing (pants, shirt): 5/10 correct (48%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n requesting assistance using AAC device: 5/8 correct (65%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n wait calmly when a preferred activity is denied: 10/14 correct (72%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n simple meal preparation: 6/12 correct (51%); latency 3.8s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d75\n\nSession 8 \u2014 2026-01-27 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 9/14 correct (67%); latency 3.0s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d76\n doing laundry: 3/10 correct (32%); latency 4.5s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d74\n dressing (pants, shirt): 3/8 correct (40%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n requesting assistance using AAC device: 7/10 correct (73%); latency 2.6s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n wait calmly when a preferred activity is denied: 8/11 correct (69%); latency 3.0s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n simple meal preparation: 7/13 correct (52%); latency 3.8s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Looking away during SD presentation\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Plateau**: accuracy has remained near 65% for 8 sessions without meaningful improvement.\n- Performance is below mastery criteria; current teaching procedure may not be effective for this learner.\n\n## Pattern Classification\nplateau\n\nResponding has stabilized below mastery criterion without meaningful movement, indicating the current procedure is limiting further acquisition.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Modify teaching procedure \u2014 switch prompt type (e.g., from most-to-least to time delay).\n- Conduct preference assessment and update reinforcer menu.\n- Break the current skill into smaller component steps if possible.\n- Increase practice opportunities by embedding targets in natural-environment training.\n\n### Consequence strategies\n- Check for inadvertent reinforcement of near-misses; tighten differential reinforcement.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 8 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 63.9%.\n- Trend direction: upward (first session: 63%, last session: 67%).\n- IOA data: 94% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "921c053f189072e5", "gold_labels": {"pattern_class": "plateau", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "plateau", "learner_profile": "adult", "n_sessions": 8, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "18407"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1294\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Mand + Self-Care + Tolerating Denied Access\nDate range: Sessions 1\u201310 across 20 days (2026-07-16 to 2026-08-05)\n\nACCELERATION PROGRAMS\n1. tolerating tooth brushing by caregiver (Self-Care)\n Method: Task Analysis\n2. requesting help when a task is difficult (Mand)\n Method: NET\n3. indicating 'all done' with a step or activity (Mand)\n Method: NET\n4. identifying community safety signs (Community)\n Method: DTT\n5. requesting a break during non-preferred activities (Mand)\n Method: NET\n6. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-16 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 8/15 correct (55%); latency 3.5s; prompts FP\u00d71, PP\u00d75, G\u00d70, I\u00d79\n requesting help when a task is difficult: 7/11 correct (62%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d78\n indicating 'all done' with a step or activity: 6/9 correct (70%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n identifying community safety signs: 9/13 correct (66%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d77\n requesting a break during non-preferred activities: 6/8 correct (69%); latency 2.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n wait calmly when access to preferred item is denied: 7/12 correct (58%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d75\n\nSession 2 \u2014 2026-07-18 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 7/11 correct (64%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d79\n requesting help when a task is difficult: 8/13 correct (61%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d76\n indicating 'all done' with a step or activity: 6/9 correct (64%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n identifying community safety signs: 8/12 correct (65%); latency 2.9s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d75\n requesting a break during non-preferred activities: 10/15 correct (68%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d78\n wait calmly when access to preferred item is denied: 5/8 correct (59%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n\nSession 3 \u2014 2026-07-20 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 6/11 correct (57%); latency 3.7s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n requesting help when a task is difficult: 6/10 correct (62%); latency 3.0s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d74\n indicating 'all done' with a step or activity: 8/11 correct (69%); latency 2.7s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n identifying community safety signs: 10/15 correct (68%); latency 3.1s; prompts FP\u00d75, PP\u00d73, G\u00d71, I\u00d76\n requesting a break during non-preferred activities: 8/11 correct (69%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n wait calmly when access to preferred item is denied: 5/8 correct (57%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n\nSession 4 \u2014 2026-07-22 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 9/15 correct (57%); latency 3.5s; prompts FP\u00d75, PP\u00d72, G\u00d74, I\u00d74\n requesting help when a task is difficult: 6/11 correct (53%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n indicating 'all done' with a step or activity: 9/12 correct (71%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d76\n identifying community safety signs: 6/9 correct (67%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d79\n requesting a break during non-preferred activities: 10/13 correct (75%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d75\n wait calmly when access to preferred item is denied: 6/10 correct (56%); latency 3.8s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n\nSession 5 \u2014 2026-07-24 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 4/14 correct (29%); latency 4.9s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d76\n requesting help when a task is difficult: 4/12 correct (29%); latency 4.8s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d73\n indicating 'all done' with a step or activity: 4/10 correct (40%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d74\n identifying community safety signs: 6/14 correct (42%); latency 3.9s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d77\n requesting a break during non-preferred activities: 4/11 correct (35%); latency 4.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n wait calmly when access to preferred item is denied: 3/9 correct (31%); latency 4.4s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n\nSession 6 \u2014 2026-07-26 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 4/11 correct (38%); latency 4.4s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n requesting help when a task is difficult: 5/14 correct (37%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d77\n indicating 'all done' with a step or activity: 5/10 correct (52%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n identifying community safety signs: 6/13 correct (49%); latency 3.7s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d75\n requesting a break during non-preferred activities: 4/9 correct (42%); latency 4.1s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n wait calmly when access to preferred item is denied: 4/12 correct (36%); latency 4.1s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d74\n\nSession 7 \u2014 2026-07-28 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 5/10 correct (47%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n requesting help when a task is difficult: 7/14 correct (47%); latency 4.0s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d712\n indicating 'all done' with a step or activity: 7/12 correct (56%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d76\n identifying community safety signs: 5/8 correct (57%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n requesting a break during non-preferred activities: 4/9 correct (47%); latency 4.1s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d72\n wait calmly when access to preferred item is denied: 6/12 correct (46%); latency 4.0s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d74\n\nSession 8 \u2014 2026-07-30 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 7/13 correct (53%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d79\n requesting help when a task is difficult: 7/12 correct (54%); latency 3.8s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n indicating 'all done' with a step or activity: 9/14 correct (66%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d713\n identifying community safety signs: 7/12 correct (60%); latency 3.5s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d73\n requesting a break during non-preferred activities: 7/15 correct (49%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d77\n wait calmly when access to preferred item is denied: 6/13 correct (46%); latency 4.1s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d76\n\nSession 9 \u2014 2026-08-01 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 7/13 correct (53%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d712\n requesting help when a task is difficult: 5/9 correct (58%); latency 3.2s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d76\n indicating 'all done' with a step or activity: 7/10 correct (67%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n identifying community safety signs: 7/10 correct (69%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d78\n requesting a break during non-preferred activities: 7/14 correct (53%); latency 3.8s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d710\n wait calmly when access to preferred item is denied: 5/9 correct (56%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n\nSession 10 \u2014 2026-08-03 \u2014 48 min \u2014 1 observer\n tolerating tooth brushing by caregiver: 5/8 correct (59%); latency 3.3s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n requesting help when a task is difficult: 5/8 correct (58%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n indicating 'all done' with a step or activity: 8/12 correct (67%); latency 3.1s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d77\n identifying community safety signs: 6/9 correct (69%); latency 3.0s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n requesting a break during non-preferred activities: 5/8 correct (58%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n wait calmly when access to preferred item is denied: 5/8 correct (59%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Playing with non-task materials\n- Leaving seat without permission\n- Stereotypic behavior during inter-trial intervals"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 51.2%.\n- Trend direction: upward (first session: 55%, last session: 59%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "ddcf715425482dc0", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "adolescent", "n_sessions": 10, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "52659"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-2923\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Writing\nDate range: Sessions 1\u201311 across 22 days (2026-03-24 to 2026-04-15)\n\nACCELERATION PROGRAMS\n1. identifies numerals 1\u201320 (Math)\n Method: DTT\n2. copies simple words from model (Writing)\n Method: DTT\n3. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-03-24 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 8/10 correct (85%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n copies simple words from model: 7/8 correct (82%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n indicating 'all done' when an activity is complete: 7/8 correct (82%); latency 2.0s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n\nSession 2 \u2014 2026-03-26 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 11/14 correct (78%); latency 2.2s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d77\n copies simple words from model: 8/11 correct (76%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n indicating 'all done' when an activity is complete: 10/12 correct (83%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d79\n\nSession 3 \u2014 2026-03-28 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 9/11 correct (85%); latency 2.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n copies simple words from model: 11/14 correct (77%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d713\n indicating 'all done' when an activity is complete: 11/13 correct (87%); latency 1.9s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d76\n\nSession 4 \u2014 2026-03-30 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 5/9 correct (55%); latency 3.3s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d76\n copies simple words from model: 6/14 correct (40%); latency 4.0s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d75\n indicating 'all done' when an activity is complete: 7/11 correct (64%); latency 3.0s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n\nSession 5 \u2014 2026-04-01 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 6/11 correct (50%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n copies simple words from model: 3/9 correct (37%); latency 4.1s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n indicating 'all done' when an activity is complete: 8/13 correct (62%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d77\n\nSession 6 \u2014 2026-04-03 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 5/9 correct (54%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n copies simple words from model: 4/11 correct (37%); latency 4.4s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n indicating 'all done' when an activity is complete: 6/10 correct (63%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d77\n\nSession 7 \u2014 2026-04-05 \u2014 IOA SESSION \u2014 2 observers\n identifies numerals 1\u201320: 59% (primary); IOA 84% agreement\n copies simple words from model: 38% (primary); IOA 84% agreement\n indicating 'all done' when an activity is complete: 70% (primary); IOA 84% agreement\n\nSession 8 \u2014 2026-04-07 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 8/13 correct (62%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d77\n copies simple words from model: 4/10 correct (43%); latency 4.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n indicating 'all done' when an activity is complete: 11/15 correct (75%); latency 2.4s; prompts FP\u00d75, PP\u00d72, G\u00d70, I\u00d78\n\nSession 9 \u2014 2026-04-09 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 9/14 correct (68%); latency 2.8s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n copies simple words from model: 7/13 correct (51%); latency 3.9s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d77\n indicating 'all done' when an activity is complete: 11/14 correct (80%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n\nSession 10 \u2014 2026-04-11 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 6/9 correct (71%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n copies simple words from model: 7/13 correct (55%); latency 3.4s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d74\n indicating 'all done' when an activity is complete: 13/15 correct (85%); latency 2.2s; prompts FP\u00d73, PP\u00d75, G\u00d72, I\u00d75\n\nSession 11 \u2014 2026-04-13 \u2014 59 min \u2014 1 observer\n identifies numerals 1\u201320: 6/8 correct (73%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n copies simple words from model: 6/10 correct (61%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n indicating 'all done' when an activity is complete: 11/13 correct (85%); latency 2.2s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Stereotypic behavior during inter-trial intervals\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 11 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 67.3%.\n- Trend direction: downward (first session: 85%, last session: 73%).\n- IOA data: 84% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "6e2ad2ab8130afd0", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "school_age", "n_sessions": 11, "n_programs": 3, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "54582"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3050\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Tolerating Denied Access\nDate range: Sessions 1\u201312 across 24 days (2026-09-11 to 2026-10-05)\n\nACCELERATION PROGRAMS\n1. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n2. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n3. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n\nDECELERATION TARGETS\n1. Elopement \u2014 function hypothesized: escape\n2. Tantrum \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-11 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/9 correct (85%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/12 correct (83%); latency 2.1s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n wait calmly when access to preferred item is denied: 10/13 correct (76%); latency 2.6s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d76\n Elopement: freq 2\n Tantrum: freq 3, duration 6m total\n\nSession 2 \u2014 2026-09-13 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/8 correct (73%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/8 correct (73%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n wait calmly when access to preferred item is denied: 11/15 correct (77%); latency 2.4s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d713\n Elopement: freq 2\n Tantrum: freq 2, duration 8m total\n\nSession 3 \u2014 2026-09-15 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 10/14 correct (73%); latency 2.5s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/13 correct (63%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d75\n wait calmly when access to preferred item is denied: 6/9 correct (64%); latency 3.3s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n Elopement: freq 2\n Tantrum: freq 3, duration 12m total\n\nSession 4 \u2014 2026-09-17 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/9 correct (63%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/13 correct (58%); latency 3.4s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n wait calmly when access to preferred item is denied: 7/11 correct (64%); latency 3.1s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n Elopement: freq 3\n Tantrum: freq 3, duration 15m total\n\nSession 5 \u2014 2026-09-19 \u2014 IOA SESSION \u2014 2 observers\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 65% (primary); IOA 91% agreement\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 59% (primary); IOA 91% agreement\n wait calmly when access to preferred item is denied: 59% (primary); IOA 91% agreement\n Elopement: freq 5; IOA 91% agreement\n Tantrum: freq 4, duration 8m total; IOA 91% agreement\n\nSession 6 \u2014 2026-09-21 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/13 correct (54%); latency 3.7s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/13 correct (53%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d78\n wait calmly when access to preferred item is denied: 7/13 correct (57%); latency 3.4s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n Elopement: freq 4\n Tantrum: freq 5, duration 25m total\n\nSession 7 \u2014 2026-09-23 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/14 correct (54%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d713\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/8 correct (44%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n wait calmly when access to preferred item is denied: 6/12 correct (47%); latency 4.1s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d712\n Elopement: freq 5\n Tantrum: freq 5, duration 10m total\n\nSession 8 \u2014 2026-09-25 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/12 correct (50%); latency 3.6s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/15 correct (34%); latency 4.6s; prompts FP\u00d75, PP\u00d71, G\u00d75, I\u00d74\n wait calmly when access to preferred item is denied: 3/8 correct (43%); latency 4.1s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n Elopement: freq 6\n Tantrum: freq 5, duration 15m total\n\nSession 9 \u2014 2026-09-27 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/12 correct (38%); latency 4.1s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 2/9 correct (26%); latency 4.7s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n wait calmly when access to preferred item is denied: 5/12 correct (40%); latency 4.5s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d79\n Elopement: freq 7\n Tantrum: freq 6, duration 30m total\n\nSession 10 \u2014 2026-09-29 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/15 correct (37%); latency 4.5s; prompts FP\u00d75, PP\u00d73, G\u00d72, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/13 correct (20%); latency 5.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d78\n wait calmly when access to preferred item is denied: 3/9 correct (33%); latency 4.2s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n Elopement: freq 7\n Tantrum: freq 8, duration 24m total\n\nSession 11 \u2014 2026-10-01 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/13 correct (35%); latency 4.3s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 1/11 correct (13%); latency 5.4s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d77\n wait calmly when access to preferred item is denied: 2/8 correct (29%); latency 4.4s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n Elopement: freq 7\n Tantrum: freq 8, duration 40m total\n\nSession 12 \u2014 2026-10-03 \u2014 33 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 2/10 correct (25%); latency 4.6s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 1/11 correct (11%); latency 5.6s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n wait calmly when access to preferred item is denied: 2/11 correct (21%); latency 5.2s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n Elopement: freq 9\n Tantrum: freq 8, duration 40m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Vocal refusal ('no', 'I don't want to')\n- Crying during demand presentation\n- Pushing materials away from the work area\n- Attempts at property destruction (throwing materials, swiping items off the surface)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (85% -> 25%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nElopement: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\nTantrum: attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nhigh\n\nPattern is well-supported: 12 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 54.3%.\n- Trend direction: downward (first session: 85%, last session: 25%).\n- Elopement: mean 4.9/session (early-window mean 2.2 -> late-window mean 7.5).\n- Tantrum: mean 5.0/session (early-window mean 2.8 -> late-window mean 7.5).\n- IOA data: 91% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "d6705be2dbe0d3bb", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Elopement": "escape", "Tantrum": "attention"}, "escalation_level": 4, "confidence": "high", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "school_age", "n_sessions": 12, "n_programs": 3, "n_behaviors": 2, "behavior_ids": ["elopement", "tantrum"], "behavior_functions": ["escape", "attention"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "95315"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3442\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Social Behavior + Writing\nDate range: Sessions 1\u201310 across 20 days (2026-01-08 to 2026-01-28)\n\nACCELERATION PROGRAMS\n1. takes turns during structured activities (Social Behavior)\n Method: PRT\n2. requesting preferred items using a full sentence (Mand)\n Method: NET\n3. requesting preferred items using AAC device (e.g., \"I want cookie please\") (Mand)\n Method: NET\n4. copies simple words from model (Writing)\n Method: DTT\n5. mands for missing items needed to complete an activity (Mand)\n Method: NET\n6. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Verbal aggression \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-08 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 6/8 correct (79%); latency 2.3s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n requesting preferred items using a full sentence: 11/14 correct (79%); latency 2.6s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d78\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 10/10 correct (95%); latency 2.0s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n copies simple words from model: 10/11 correct (91%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n mands for missing items needed to complete an activity: 13/15 correct (90%); latency 2.2s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/10 correct (72%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d74\n Verbal aggression: freq 1\n\nSession 2 \u2014 2026-01-10 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 8/11 correct (77%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n requesting preferred items using a full sentence: 8/10 correct (79%); latency 2.3s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d76\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 11/11 correct (98%); latency 1.3s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n copies simple words from model: 10/11 correct (87%); latency 2.1s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n mands for missing items needed to complete an activity: 7/8 correct (90%); latency 1.8s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/10 correct (76%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d79\n Verbal aggression: freq 1\n\nSession 3 \u2014 2026-01-12 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 8/10 correct (83%); latency 2.3s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n requesting preferred items using a full sentence: 11/14 correct (78%); latency 2.7s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d79\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 12/12 correct (98%); latency 1.9s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d77\n copies simple words from model: 8/8 correct (95%); latency 1.7s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n mands for missing items needed to complete an activity: 11/13 correct (83%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 11/15 correct (72%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d77\n Verbal aggression: freq 1\n\nSession 4 \u2014 2026-01-14 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 10/13 correct (77%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d77\n requesting preferred items using a full sentence: 9/12 correct (77%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d711\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 10/10 correct (98%); latency 1.7s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n copies simple words from model: 8/8 correct (95%); latency 1.9s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n mands for missing items needed to complete an activity: 7/8 correct (89%); latency 1.7s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/11 correct (76%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n Verbal aggression: freq 1\n\nSession 5 \u2014 2026-01-16 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 12/15 correct (83%); latency 2.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d79\n requesting preferred items using a full sentence: 8/11 correct (74%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 12/12 correct (98%); latency 1.8s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n copies simple words from model: 13/14 correct (91%); latency 1.7s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d74\n mands for missing items needed to complete an activity: 9/10 correct (87%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/9 correct (77%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n Verbal aggression: freq 2\n\nSession 6 \u2014 2026-01-18 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 9/11 correct (79%); latency 2.3s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d710\n requesting preferred items using a full sentence: 10/14 correct (72%); latency 2.8s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 10/10 correct (98%); latency 1.6s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d76\n copies simple words from model: 10/10 correct (97%); latency 1.7s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n mands for missing items needed to complete an activity: 9/10 correct (85%); latency 1.9s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/8 correct (75%); latency 2.7s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n Verbal aggression: freq 0\n\nSession 7 \u2014 2026-01-20 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 10/12 correct (81%); latency 2.3s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d76\n requesting preferred items using a full sentence: 9/13 correct (71%); latency 3.0s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d78\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 14/14 correct (98%); latency 1.7s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d78\n copies simple words from model: 11/11 correct (98%); latency 1.4s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d76\n mands for missing items needed to complete an activity: 9/12 correct (77%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/10 correct (73%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n Verbal aggression: freq 1\n\nSession 8 \u2014 2026-01-22 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 11/13 correct (88%); latency 2.1s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d78\n requesting preferred items using a full sentence: 8/12 correct (67%); latency 2.8s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 15/15 correct (98%); latency 1.3s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d76\n copies simple words from model: 15/15 correct (98%); latency 1.8s; prompts FP\u00d74, PP\u00d75, G\u00d73, I\u00d73\n mands for missing items needed to complete an activity: 12/15 correct (80%); latency 2.5s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d79\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/9 correct (76%); latency 2.4s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n Verbal aggression: freq 0\n\nSession 9 \u2014 2026-01-24 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 10/12 correct (84%); latency 2.4s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d76\n requesting preferred items using a full sentence: 7/10 correct (71%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d78\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 14/14 correct (98%); latency 1.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d79\n copies simple words from model: 8/8 correct (98%); latency 1.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n mands for missing items needed to complete an activity: 12/15 correct (78%); latency 2.3s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d710\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/10 correct (77%); latency 2.2s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n Verbal aggression: freq 1\n\nSession 10 \u2014 2026-01-26 \u2014 31 min \u2014 1 observer\n takes turns during structured activities: 11/13 correct (86%); latency 2.2s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d76\n requesting preferred items using a full sentence: 8/12 correct (64%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d710\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 14/14 correct (98%); latency 1.3s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d75\n copies simple words from model: 8/8 correct (98%); latency 1.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n mands for missing items needed to complete an activity: 11/15 correct (73%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 11/14 correct (76%); latency 2.8s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d79\n Verbal aggression: freq 2\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Delayed responding (>5 seconds consistently)\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (79%\u201386%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Behavior Function Hypothesis\nVerbal aggression: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 81.8%.\n- Trend direction: upward (first session: 79%, last session: 86%).\n- Verbal aggression: mean 1.0/session (early-window mean 1.0 -> late-window mean 1.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "d0f7fca363ad9c8b", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {"Verbal aggression": "escape"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "school_age", "n_sessions": 10, "n_programs": 6, "n_behaviors": 1, "behavior_ids": ["verbal_aggression"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "71533"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: tacts abstract concepts (same/different, first/last)\nCurriculum Reference: Tact L3\nLearner Profile: Adolescent Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts abstract concepts (same/different, first/last)\n- Curriculum: Tact L3\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What is this?\"\nVariations: \"Tell me what you see\"; \"What's that?\"; \"Name this\"\nPresentation: Present the target stimulus within visual field and ask while pointing to it.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: crayon, key, backpack\nDistractor stimuli: phone, hat, spoon, scissors, jacket\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "389196e0b33b3448", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L3", "learner_profile": "adolescent", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts abstract concepts (same/different, first/last)", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "fr2", "error_correction": "simple_correction", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "20338"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: responds to peer initiations appropriately\nCurriculum Reference: Social Behavior & Social Play L2\nLearner Profile: Early Learner\nCurrent Mastery: Near mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: responds to peer initiations appropriately\n- Curriculum: Social Behavior & Social Play L2\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: shared snack.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's shared snack routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the near mastery stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "632d49434d10897a", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L2", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "responds to peer initiations appropriately", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "time_delay", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "76914"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6950\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Listener Responding + Mand\nDate range: Sessions 1\u20139 across 18 days (2026-05-06 to 2026-05-24)\n\nACCELERATION PROGRAMS\n1. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n2. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n3. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n4. selects items by feature (Listener Responding)\n Method: DTT\n\nDECELERATION TARGETS\n1. Property destruction \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-06 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 9/10 correct (86%); latency 1.9s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d74\n answers WH-questions about familiar topics: 8/10 correct (78%); latency 2.3s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/10 correct (78%); latency 2.2s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n selects items by feature: 8/11 correct (76%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d74\n Property destruction: freq 0\n\nSession 2 \u2014 2026-05-08 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 10/14 correct (74%); latency 2.8s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d712\n answers WH-questions about familiar topics: 10/13 correct (80%); latency 2.3s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/9 correct (70%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n selects items by feature: 10/15 correct (70%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d75, I\u00d79\n Property destruction: freq 1\n\nSession 3 \u2014 2026-05-10 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 9/12 correct (73%); latency 2.8s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d75\n answers WH-questions about familiar topics: 10/14 correct (68%); latency 3.2s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/9 correct (66%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n selects items by feature: 5/9 correct (60%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n Property destruction: freq 3\n\nSession 4 \u2014 2026-05-12 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 6/10 correct (62%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n answers WH-questions about familiar topics: 6/8 correct (72%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/12 correct (58%); latency 3.5s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d73\n selects items by feature: 6/12 correct (53%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d76\n Property destruction: freq 3\n\nSession 5 \u2014 2026-05-14 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 8/14 correct (59%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d710\n answers WH-questions about familiar topics: 7/11 correct (63%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/12 correct (55%); latency 3.7s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d75\n selects items by feature: 4/9 correct (49%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d77\n Property destruction: freq 4\n\nSession 6 \u2014 2026-05-16 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 7/14 correct (51%); latency 3.7s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d711\n answers WH-questions about familiar topics: 5/8 correct (62%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/8 correct (57%); latency 3.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n selects items by feature: 5/14 correct (37%); latency 4.1s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d76\n Property destruction: freq 4\n\nSession 7 \u2014 2026-05-18 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 5/11 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n answers WH-questions about familiar topics: 5/9 correct (54%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/12 correct (46%); latency 3.7s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d75\n selects items by feature: 3/10 correct (34%); latency 4.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n Property destruction: freq 4\n\nSession 8 \u2014 2026-05-20 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 5/15 correct (31%); latency 4.4s; prompts FP\u00d75, PP\u00d74, G\u00d73, I\u00d73\n answers WH-questions about familiar topics: 6/11 correct (53%); latency 3.5s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (40%); latency 4.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d77\n selects items by feature: 3/11 correct (29%); latency 4.5s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n Property destruction: freq 5\n\nSession 9 \u2014 2026-05-22 \u2014 38 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 3/12 correct (29%); latency 5.0s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d74\n answers WH-questions about familiar topics: 7/15 correct (45%); latency 3.7s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/9 correct (40%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n selects items by feature: 2/11 correct (22%); latency 4.8s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d74\n Property destruction: freq 5\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Turning away from task or staff\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (86% -> 29%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nProperty destruction: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 56.3%.\n- Trend direction: downward (first session: 86%, last session: 29%).\n- Property destruction: mean 3.2/session (early-window mean 1.3 -> late-window mean 4.7).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "ac7c2835f3befc58", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Property destruction": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "early", "n_sessions": 9, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["property_destruction"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "73913"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6120\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Home Skills + Self-Care\nDate range: Sessions 1\u201311 across 22 days (2026-01-07 to 2026-01-29)\n\nACCELERATION PROGRAMS\n1. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n2. washing hands independently (Self-Care)\n Method: Task Analysis\n3. brushing teeth independently (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: tangible\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-07 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 11/13 correct (81%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d710\n washing hands independently: 6/8 correct (79%); latency 2.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n brushing teeth independently: 8/10 correct (82%); latency 2.3s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n Tantrum: freq 2, duration 10m total\n\nSession 2 \u2014 2026-01-09 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 11/13 correct (83%); latency 2.4s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d78\n washing hands independently: 11/14 correct (76%); latency 2.6s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d711\n brushing teeth independently: 9/11 correct (80%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n Tantrum: freq 0\n\nSession 3 \u2014 2026-01-11 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 8/10 correct (79%); latency 2.5s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n washing hands independently: 7/9 correct (80%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n brushing teeth independently: 10/12 correct (80%); latency 2.2s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d77\n Tantrum: freq 2, duration 8m total\n\nSession 4 \u2014 2026-01-13 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 6/13 correct (48%); latency 3.5s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d77\n washing hands independently: 6/12 correct (51%); latency 3.8s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d79\n brushing teeth independently: 8/15 correct (50%); latency 3.9s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d77\n Tantrum: freq 1, duration 2m total\n\nSession 5 \u2014 2026-01-15 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 5/10 correct (47%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n washing hands independently: 7/14 correct (52%); latency 3.6s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d76\n brushing teeth independently: 7/14 correct (52%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d79\n Tantrum: freq 1, duration 2m total\n\nSession 6 \u2014 2026-01-17 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 6/13 correct (49%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d73\n washing hands independently: 8/15 correct (54%); latency 3.7s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d75\n brushing teeth independently: 5/9 correct (55%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n Tantrum: freq 2, duration 4m total\n\nSession 7 \u2014 2026-01-19 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 8/15 correct (52%); latency 3.7s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d77\n washing hands independently: 6/12 correct (48%); latency 4.0s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d72\n brushing teeth independently: 7/11 correct (65%); latency 3.4s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n Tantrum: freq 1, duration 2m total\n\nSession 8 \u2014 2026-01-21 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 6/12 correct (54%); latency 3.6s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d76\n washing hands independently: 6/10 correct (57%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d77\n brushing teeth independently: 11/15 correct (76%); latency 2.6s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d78\n Tantrum: freq 1, duration 3m total\n\nSession 9 \u2014 2026-01-23 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 6/10 correct (63%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n washing hands independently: 6/10 correct (62%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d78\n brushing teeth independently: 7/9 correct (81%); latency 2.2s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n Tantrum: freq 2, duration 8m total\n\nSession 10 \u2014 2026-01-25 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 8/12 correct (70%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d76\n washing hands independently: 7/10 correct (66%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n brushing teeth independently: 10/12 correct (81%); latency 2.3s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d73\n Tantrum: freq 2, duration 8m total\n ABC (tantrum): A = peer took preferred toy; B = grabbed toy back + cried; C = staff mediated and returned item\n\nSession 11 \u2014 2026-01-27 \u2014 44 min \u2014 1 observer\n meal cleanup after eating: 12/15 correct (79%); latency 2.6s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d711\n washing hands independently: 9/12 correct (75%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d74\n brushing teeth independently: 9/11 correct (81%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n Tantrum: freq 1, duration 4m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Delayed responding (>5 seconds consistently)\n- Leaving seat without permission\n- Playing with non-task materials\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Behavior Function Hypothesis\nTantrum: tangible\n Evidence: ABC events in the log support the tangible function; behavior occurs when preferred items are restricted and is followed by access to the item.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 64.1%.\n- Trend direction: downward (first session: 81%, last session: 79%).\n- Tantrum: mean 1.4/session (early-window mean 1.3 -> late-window mean 1.7).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "8567f65e7969a8e9", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {"Tantrum": "tangible"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "adolescent", "n_sessions": 11, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["tantrum"], "behavior_functions": ["tangible"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "1699"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9274\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Mand + Reading + Writing\nDate range: Sessions 1\u20137 across 14 days (2026-07-07 to 2026-07-21)\n\nACCELERATION PROGRAMS\n1. indicating completion ('all done', 'finished') (Mand)\n Method: NET\n2. copies simple words from model (Writing)\n Method: DTT\n3. reads 10\u201320 sight words (Reading)\n Method: DTT\n\nDECELERATION TARGETS\n1. Mouthing \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-07 \u2014 39 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 6/13 correct (46%); latency 4.0s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d79\n copies simple words from model: 5/11 correct (41%); latency 4.2s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n reads 10\u201320 sight words: 4/14 correct (32%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d78\n Mouthing: freq 0; PIR 3%\n\nSession 2 \u2014 2026-07-09 \u2014 39 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 6/13 correct (49%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d78\n copies simple words from model: 6/14 correct (44%); latency 3.8s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d75\n reads 10\u201320 sight words: 6/15 correct (40%); latency 4.1s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d76\n Mouthing: freq 1; PIR 6%\n\nSession 3 \u2014 2026-07-11 \u2014 39 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 6/11 correct (54%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n copies simple words from model: 7/15 correct (47%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d712\n reads 10\u201320 sight words: 5/11 correct (49%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n Mouthing: freq 0; PIR 0%\n\nSession 4 \u2014 2026-07-13 \u2014 39 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 5/9 correct (59%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d76\n copies simple words from model: 8/14 correct (55%); latency 3.3s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d79\n reads 10\u201320 sight words: 7/12 correct (56%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d78\n Mouthing: freq 2; PIR 9%\n ABC (mouthing): A = quiet unstructured moment between trials; B = engaged in hand-flapping; C = no social consequence; self-terminated after 30s\n\nSession 5 \u2014 2026-07-15 \u2014 39 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 9/14 correct (63%); latency 3.4s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n copies simple words from model: 8/12 correct (63%); latency 3.1s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d75\n reads 10\u201320 sight words: 8/13 correct (65%); latency 3.1s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d78\n Mouthing: freq 1; PIR 9%\n\nSession 6 \u2014 2026-07-17 \u2014 39 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 7/10 correct (68%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d76\n copies simple words from model: 8/12 correct (69%); latency 2.8s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d74\n reads 10\u201320 sight words: 8/12 correct (70%); latency 3.0s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d74\n Mouthing: freq 2; PIR 11%\n\nSession 7 \u2014 2026-07-19 \u2014 39 min \u2014 1 observer\n indicating completion ('all done', 'finished'): 6/9 correct (71%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n copies simple words from model: 9/13 correct (72%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d78\n reads 10\u201320 sight words: 11/15 correct (72%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d711\n Mouthing: freq 0; PIR 10%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Leaving seat without permission\n- Playing with non-task materials\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 46% at return, recovering to 71%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Behavior Function Hypothesis\nMouthing: automatic\n Evidence: ABC events in the log support the automatic function; behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 58.6%.\n- Trend direction: upward (first session: 46%, last session: 71%).\n- Mouthing: mean 0.9/session (early-window mean 0.5 -> late-window mean 1.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "033a32bfc33c1177", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {"Mouthing": "automatic"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "early", "n_sessions": 7, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["mouthing"], "behavior_functions": ["automatic"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "23188"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5515\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Listener Responding + Mand + Reading + Tact\nDate range: Sessions 1\u20139 across 18 days (2026-04-18 to 2026-05-06)\n\nACCELERATION PROGRAMS\n1. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n2. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n3. reads 10\u201320 sight words (Reading)\n Method: DTT\n4. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n5. tacts colors of objects (Tact)\n Method: DTT\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-18 \u2014 44 min \u2014 1 observer\n follows 1-step motor instructions: 5/9 correct (50%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n answers WH-questions about familiar topics: 6/13 correct (47%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n reads 10\u201320 sight words: 7/15 correct (50%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d711\n requesting a break ('break please' or AAC 'I need a break'): 6/14 correct (46%); latency 4.2s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d77\n tacts colors of objects: 7/14 correct (51%); latency 3.5s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d79\n Self-injurious behavior (SIB): freq 0\n\nSession 2 \u2014 2026-04-20 \u2014 44 min \u2014 1 observer\n follows 1-step motor instructions: 5/9 correct (53%); latency 3.9s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n answers WH-questions about familiar topics: 7/12 correct (58%); latency 3.5s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d75\n reads 10\u201320 sight words: 7/13 correct (55%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 6/12 correct (52%); latency 3.6s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d73\n tacts colors of objects: 5/9 correct (59%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n Self-injurious behavior (SIB): freq 2\n\nSession 3 \u2014 2026-04-22 \u2014 44 min \u2014 1 observer\n follows 1-step motor instructions: 5/8 correct (59%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n answers WH-questions about familiar topics: 7/10 correct (67%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n reads 10\u201320 sight words: 6/10 correct (60%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 5/9 correct (59%); latency 3.3s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d76\n tacts colors of objects: 7/10 correct (66%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n Self-injurious behavior (SIB): freq 1\n\nSession 4 \u2014 2026-04-24 \u2014 44 min \u2014 1 observer\n follows 1-step motor instructions: 9/15 correct (63%); latency 3.2s; prompts FP\u00d75, PP\u00d71, G\u00d75, I\u00d74\n answers WH-questions about familiar topics: 6/8 correct (75%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n reads 10\u201320 sight words: 7/10 correct (69%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n requesting a break ('break please' or AAC 'I need a break'): 6/9 correct (66%); latency 3.1s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n tacts colors of objects: 10/13 correct (75%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n Self-injurious behavior (SIB): freq 0\n\nSession 5 \u2014 2026-04-26 \u2014 44 min \u2014 1 observer\n follows 1-step motor instructions: 8/12 correct (68%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d76\n answers WH-questions about familiar topics: 12/15 correct (83%); latency 2.0s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d77\n reads 10\u201320 sight words: 7/9 correct (75%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 8/10 correct (76%); latency 2.3s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d74\n tacts colors of objects: 8/10 correct (80%); latency 2.6s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n Self-injurious behavior (SIB): freq 1\n\nSession 6 \u2014 2026-04-28 \u2014 44 min \u2014 1 observer\n follows 1-step motor instructions: 7/9 correct (75%); latency 2.5s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d77\n answers WH-questions about familiar topics: 10/12 correct (83%); latency 2.3s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d74\n reads 10\u201320 sight words: 6/8 correct (79%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 8/10 correct (82%); latency 2.0s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d76\n tacts colors of objects: 8/10 correct (80%); latency 2.6s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d74\n Self-injurious behavior (SIB): freq 1\n\nSession 7 \u2014 2026-04-30 \u2014 IOA SESSION \u2014 2 observers\n follows 1-step motor instructions: 75% (primary); IOA 83% agreement\n answers WH-questions about familiar topics: 83% (primary); IOA 83% agreement\n reads 10\u201320 sight words: 79% (primary); IOA 83% agreement\n requesting a break ('break please' or AAC 'I need a break'): 83% (primary); IOA 83% agreement\n tacts colors of objects: 80% (primary); IOA 83% agreement\n Self-injurious behavior (SIB): freq 2; IOA 83% agreement\n\nSession 8 \u2014 2026-05-02 \u2014 44 min \u2014 1 observer\n follows 1-step motor instructions: 8/10 correct (75%); latency 2.4s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n answers WH-questions about familiar topics: 8/10 correct (83%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n reads 10\u201320 sight words: 11/14 correct (79%); latency 2.2s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 8/10 correct (83%); latency 2.4s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d77\n tacts colors of objects: 10/13 correct (80%); latency 2.3s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d711\n Self-injurious behavior (SIB): freq 1\n\nSession 9 \u2014 2026-05-04 \u2014 44 min \u2014 1 observer\n follows 1-step motor instructions: 6/8 correct (75%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n answers WH-questions about familiar topics: 12/14 correct (83%); latency 2.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d711\n reads 10\u201320 sight words: 7/9 correct (79%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 11/13 correct (83%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d75\n tacts colors of objects: 7/9 correct (80%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d76\n Self-injurious behavior (SIB): freq 1\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Looking away during SD presentation\n- Delayed responding (>5 seconds consistently)\n- Leaving seat without permission"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 50% at return, recovering to 75%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nhigh\n\nPattern is well-supported: 9 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 66.0%.\n- Trend direction: upward (first session: 50%, last session: 75%).\n- Self-injurious behavior (SIB): mean 1.0/session (early-window mean 1.0 -> late-window mean 1.3).\n- IOA data: 83% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "1088fded3c749272", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {"Self-injurious behavior (SIB)": "escape"}, "escalation_level": 3, "confidence": "high", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "early", "n_sessions": 9, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["sib"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "60991"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: using public transportation\nCurriculum Reference: AFLS Community Participation Skills\nLearner Profile: Adult Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: Task Analysis / Chaining\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: using public transportation\n- Curriculum: AFLS Community Participation Skills\n- Learner: Adult Learner\n- Current mastery: Mastered at current level\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Confirm the correct stop or station. <- Learner-taught step (forward chaining starts here)\n2. Purchase or have the fare ready.\n3. Wait at the designated boarding area.\n4. Board the vehicle when it arrives.\n5. Pay the fare or present the pass.\n6. Sit or stand safely.\n7. Monitor the route for the correct stop.\n8. Exit at the correct stop.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the mastered stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nToken economy \u2014 One token per correctly-completed step; token exchange at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "3e9f1e4489999688", "gold_labels": {"method": "task_analysis", "domain": "AFLS.community", "skill": "using public transportation", "program_type": "independence", "learner_profile": "adult", "mastery_state": "mastered", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "using public transportation", "module": "community", "mastery_criterion": "mc_self_initiation", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "92010"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9796\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Home Skills + Mand + Self-Care\nDate range: Sessions 1\u201310 across 20 days (2026-02-25 to 2026-03-17)\n\nACCELERATION PROGRAMS\n1. tolerating haircut (Self-Care)\n Method: Task Analysis\n2. indicating 'all done' with a step or activity (Mand)\n Method: NET\n3. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n4. requesting help when a task is difficult (Mand)\n Method: NET\n5. brushing teeth independently (Self-Care)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-25 \u2014 54 min \u2014 1 observer\n tolerating haircut: 4/9 correct (44%); latency 4.0s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n indicating 'all done' with a step or activity: 5/11 correct (45%); latency 3.8s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n meal cleanup after eating: 7/12 correct (58%); latency 3.6s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d75\n requesting help when a task is difficult: 10/13 correct (75%); latency 2.7s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d75\n brushing teeth independently: 5/8 correct (56%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n\nSession 2 \u2014 2026-02-27 \u2014 54 min \u2014 1 observer\n tolerating haircut: 8/11 correct (72%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d78\n indicating 'all done' with a step or activity: 6/10 correct (56%); latency 3.4s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n meal cleanup after eating: 7/12 correct (57%); latency 3.7s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d75\n requesting help when a task is difficult: 10/13 correct (75%); latency 2.4s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d74\n brushing teeth independently: 6/12 correct (50%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d711\n\nSession 3 \u2014 2026-03-01 \u2014 54 min \u2014 1 observer\n tolerating haircut: 7/12 correct (56%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d77\n indicating 'all done' with a step or activity: 6/9 correct (65%); latency 3.3s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n meal cleanup after eating: 9/15 correct (63%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d710\n requesting help when a task is difficult: 12/14 correct (85%); latency 2.2s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n brushing teeth independently: 5/8 correct (57%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n\nSession 4 \u2014 2026-03-03 \u2014 54 min \u2014 1 observer\n tolerating haircut: 6/8 correct (78%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n indicating 'all done' with a step or activity: 7/13 correct (56%); latency 3.7s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n meal cleanup after eating: 8/12 correct (68%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d77\n requesting help when a task is difficult: 6/11 correct (52%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n brushing teeth independently: 5/8 correct (60%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n\nSession 5 \u2014 2026-03-05 \u2014 54 min \u2014 1 observer\n tolerating haircut: 9/14 correct (67%); latency 2.8s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d75\n indicating 'all done' with a step or activity: 8/13 correct (61%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d78\n meal cleanup after eating: 7/9 correct (81%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n requesting help when a task is difficult: 8/10 correct (79%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d74\n brushing teeth independently: 4/8 correct (53%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n\nSession 6 \u2014 2026-03-07 \u2014 IOA SESSION \u2014 2 observers\n tolerating haircut: 56% (primary); IOA 87% agreement\n indicating 'all done' with a step or activity: 53% (primary); IOA 87% agreement\n meal cleanup after eating: 87% (primary); IOA 87% agreement\n requesting help when a task is difficult: 61% (primary); IOA 87% agreement\n brushing teeth independently: 65% (primary); IOA 87% agreement\n\nSession 7 \u2014 2026-03-09 \u2014 54 min \u2014 1 observer\n tolerating haircut: 6/12 correct (46%); latency 4.0s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d78\n indicating 'all done' with a step or activity: 4/9 correct (44%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n meal cleanup after eating: 6/8 correct (80%); latency 2.6s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n requesting help when a task is difficult: 10/12 correct (81%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d75\n brushing teeth independently: 5/13 correct (42%); latency 4.0s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d76\n\nSession 8 \u2014 2026-03-11 \u2014 54 min \u2014 1 observer\n tolerating haircut: 7/9 correct (76%); latency 2.4s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d73\n indicating 'all done' with a step or activity: 8/13 correct (61%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d79\n meal cleanup after eating: 6/9 correct (72%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n requesting help when a task is difficult: 8/11 correct (74%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n brushing teeth independently: 4/10 correct (39%); latency 4.0s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d74\n\nSession 9 \u2014 2026-03-13 \u2014 54 min \u2014 1 observer\n tolerating haircut: 9/13 correct (70%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d77\n indicating 'all done' with a step or activity: 5/12 correct (45%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d76\n meal cleanup after eating: 6/10 correct (65%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n requesting help when a task is difficult: 5/8 correct (63%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n brushing teeth independently: 8/13 correct (60%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d79\n\nSession 10 \u2014 2026-03-15 \u2014 54 min \u2014 1 observer\n tolerating haircut: 7/10 correct (73%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n indicating 'all done' with a step or activity: 6/10 correct (64%); latency 2.9s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n meal cleanup after eating: 11/13 correct (82%); latency 2.6s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d75\n requesting help when a task is difficult: 5/8 correct (63%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n brushing teeth independently: 3/9 correct (38%); latency 4.1s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Echolalic responding (repeating SD rather than answering)\n- Stereotypic behavior during inter-trial intervals\n- Delayed responding (>5 seconds consistently)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 58% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 10 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 63.8%.\n- Trend direction: upward (first session: 44%, last session: 73%).\n- IOA data: 87% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "97f9122e04592919", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "adolescent", "n_sessions": 10, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "81514"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7332\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Reading + Writing\nDate range: Sessions 1\u201312 across 24 days (2026-01-17 to 2026-02-10)\n\nACCELERATION PROGRAMS\n1. copies simple words from model (Writing)\n Method: DTT\n2. single-word requests for preferred items (Mand)\n Method: NET\n3. sounds out CVC words (Reading)\n Method: DTT\n4. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n5. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-17 \u2014 41 min \u2014 1 observer\n copies simple words from model: 10/13 correct (79%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d711\n single-word requests for preferred items: 8/11 correct (72%); latency 2.8s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d76\n sounds out CVC words: 10/14 correct (72%); latency 2.8s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d79\n indicating 'all done' when an activity is complete: 7/9 correct (81%); latency 2.2s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/8 correct (81%); latency 2.1s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n Self-injurious behavior (SIB): freq 1\n\nSession 2 \u2014 2026-01-19 \u2014 41 min \u2014 1 observer\n copies simple words from model: 6/8 correct (79%); latency 2.5s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n single-word requests for preferred items: 7/9 correct (75%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n sounds out CVC words: 10/14 correct (74%); latency 2.4s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d75\n indicating 'all done' when an activity is complete: 7/8 correct (84%); latency 2.0s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/9 correct (82%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n Self-injurious behavior (SIB): freq 1\n\nSession 3 \u2014 2026-01-21 \u2014 41 min \u2014 1 observer\n copies simple words from model: 8/11 correct (73%); latency 2.5s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d75\n single-word requests for preferred items: 6/8 correct (74%); latency 2.9s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n sounds out CVC words: 11/15 correct (75%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d77\n indicating 'all done' when an activity is complete: 12/15 correct (80%); latency 2.1s; prompts FP\u00d75, PP\u00d73, G\u00d75, I\u00d72\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/11 correct (79%); latency 2.7s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d710\n Self-injurious behavior (SIB): freq 1\n\nSession 4 \u2014 2026-01-23 \u2014 41 min \u2014 1 observer\n copies simple words from model: 9/12 correct (75%); latency 2.7s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d70\n single-word requests for preferred items: 6/8 correct (71%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n sounds out CVC words: 6/9 correct (71%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d72\n indicating 'all done' when an activity is complete: 11/13 correct (82%); latency 2.1s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/9 correct (78%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d76\n Self-injurious behavior (SIB): freq 0\n\nSession 5 \u2014 2026-01-25 \u2014 41 min \u2014 1 observer\n copies simple words from model: 4/9 correct (46%); latency 4.2s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n single-word requests for preferred items: 5/12 correct (42%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d78\n sounds out CVC words: 5/15 correct (34%); latency 4.5s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d78\n indicating 'all done' when an activity is complete: 5/13 correct (42%); latency 4.0s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/11 correct (38%); latency 4.1s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n Self-injurious behavior (SIB): freq 0\n\nSession 6 \u2014 2026-01-27 \u2014 41 min \u2014 1 observer\n copies simple words from model: 6/13 correct (46%); latency 3.9s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d73\n single-word requests for preferred items: 4/12 correct (35%); latency 4.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d77\n sounds out CVC words: 5/14 correct (36%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d75\n indicating 'all done' when an activity is complete: 5/10 correct (46%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 3/9 correct (38%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n Self-injurious behavior (SIB): freq 2\n\nSession 7 \u2014 2026-01-29 \u2014 41 min \u2014 1 observer\n copies simple words from model: 4/8 correct (52%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n single-word requests for preferred items: 5/12 correct (40%); latency 4.0s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d73\n sounds out CVC words: 3/8 correct (38%); latency 4.1s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n indicating 'all done' when an activity is complete: 6/14 correct (46%); latency 4.1s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/10 correct (40%); latency 4.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n Self-injurious behavior (SIB): freq 1\n\nSession 8 \u2014 2026-01-31 \u2014 41 min \u2014 1 observer\n copies simple words from model: 5/8 correct (58%); latency 3.3s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n single-word requests for preferred items: 3/8 correct (39%); latency 4.4s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n sounds out CVC words: 5/14 correct (39%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d78\n indicating 'all done' when an activity is complete: 6/13 correct (49%); latency 4.0s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d79\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/14 correct (44%); latency 4.1s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d710\n Self-injurious behavior (SIB): freq 2\n\nSession 9 \u2014 2026-02-02 \u2014 41 min \u2014 1 observer\n copies simple words from model: 8/13 correct (61%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d79\n single-word requests for preferred items: 5/12 correct (42%); latency 4.0s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d79\n sounds out CVC words: 5/11 correct (44%); latency 4.1s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n indicating 'all done' when an activity is complete: 6/11 correct (54%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/8 correct (50%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n Self-injurious behavior (SIB): freq 1\n\nSession 10 \u2014 2026-02-04 \u2014 41 min \u2014 1 observer\n copies simple words from model: 10/15 correct (69%); latency 2.8s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d77\n single-word requests for preferred items: 6/13 correct (46%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d710\n sounds out CVC words: 6/12 correct (53%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d75\n indicating 'all done' when an activity is complete: 6/10 correct (57%); latency 3.6s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/12 correct (56%); latency 3.7s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d75\n Self-injurious behavior (SIB): freq 2\n\nSession 11 \u2014 2026-02-06 \u2014 41 min \u2014 1 observer\n copies simple words from model: 8/11 correct (73%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d79\n single-word requests for preferred items: 5/10 correct (53%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n sounds out CVC words: 7/12 correct (61%); latency 3.1s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d74\n indicating 'all done' when an activity is complete: 5/8 correct (67%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/15 correct (62%); latency 3.0s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d713\n Self-injurious behavior (SIB): freq 1\n\nSession 12 \u2014 2026-02-08 \u2014 41 min \u2014 1 observer\n copies simple words from model: 11/15 correct (76%); latency 2.5s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d79\n single-word requests for preferred items: 7/13 correct (56%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d79\n sounds out CVC words: 10/15 correct (66%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d711\n indicating 'all done' when an activity is complete: 6/8 correct (71%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 10/15 correct (66%); latency 3.3s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d711\n Self-injurious behavior (SIB): freq 1\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Echolalic responding (repeating SD rather than answering)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 65.7%.\n- Trend direction: downward (first session: 79%, last session: 76%).\n- Self-injurious behavior (SIB): mean 1.1/session (early-window mean 0.8 -> late-window mean 1.2).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "2b825786b519b265", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {"Self-injurious behavior (SIB)": "automatic"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "school_age", "n_sessions": 12, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["sib"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "74717"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1192\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Social Behavior + Writing\nDate range: Sessions 1\u201311 across 22 days (2026-04-12 to 2026-05-04)\n\nACCELERATION PROGRAMS\n1. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n2. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n3. takes turns during structured activities (Social Behavior)\n Method: PRT\n4. copies simple words from model (Writing)\n Method: DTT\n\nDECELERATION TARGETS\n1. Verbal aggression \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-12 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 12/14 correct (87%); latency 2.1s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d74\n indicating 'all done' when an activity is complete: 7/8 correct (86%); latency 1.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n takes turns during structured activities: 7/8 correct (87%); latency 1.9s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n copies simple words from model: 8/9 correct (84%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n Verbal aggression: freq 1\n\nSession 2 \u2014 2026-04-14 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (39%); latency 4.1s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d74\n indicating 'all done' when an activity is complete: 4/13 correct (32%); latency 4.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d711\n takes turns during structured activities: 3/9 correct (39%); latency 4.4s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d77\n copies simple words from model: 5/10 correct (45%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n Verbal aggression: freq 1\n\nSession 3 \u2014 2026-04-16 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 11/13 correct (85%); latency 2.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d77\n indicating 'all done' when an activity is complete: 11/15 correct (77%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d75, I\u00d79\n takes turns during structured activities: 8/9 correct (85%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n copies simple words from model: 12/15 correct (82%); latency 2.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d714\n Verbal aggression: freq 0\n\nSession 4 \u2014 2026-04-18 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/15 correct (42%); latency 4.4s; prompts FP\u00d71, PP\u00d75, G\u00d72, I\u00d77\n indicating 'all done' when an activity is complete: 3/10 correct (33%); latency 4.8s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n takes turns during structured activities: 5/14 correct (38%); latency 4.3s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d77\n copies simple words from model: 5/12 correct (45%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d79\n Verbal aggression: freq 0\n\nSession 5 \u2014 2026-04-20 \u2014 IOA SESSION \u2014 2 observers\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 92% (primary); IOA 89% agreement\n indicating 'all done' when an activity is complete: 83% (primary); IOA 89% agreement\n takes turns during structured activities: 91% (primary); IOA 89% agreement\n copies simple words from model: 78% (primary); IOA 89% agreement\n Verbal aggression: freq 0; IOA 89% agreement\n\nSession 6 \u2014 2026-04-22 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/13 correct (35%); latency 4.2s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d74\n indicating 'all done' when an activity is complete: 4/11 correct (33%); latency 4.7s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n takes turns during structured activities: 5/13 correct (36%); latency 4.1s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d75\n copies simple words from model: 3/8 correct (43%); latency 4.1s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n Verbal aggression: freq 1\n\nSession 7 \u2014 2026-04-24 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 12/14 correct (85%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d79\n indicating 'all done' when an activity is complete: 10/13 correct (79%); latency 2.4s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d78\n takes turns during structured activities: 11/13 correct (86%); latency 2.2s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n copies simple words from model: 6/8 correct (78%); latency 2.7s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n Verbal aggression: freq 0\n\nSession 8 \u2014 2026-04-26 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (43%); latency 4.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n indicating 'all done' when an activity is complete: 3/9 correct (37%); latency 4.1s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n takes turns during structured activities: 5/11 correct (42%); latency 4.0s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d76\n copies simple words from model: 6/12 correct (48%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d78\n Verbal aggression: freq 0\n\nSession 9 \u2014 2026-04-28 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/10 correct (87%); latency 1.8s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d78\n indicating 'all done' when an activity is complete: 11/14 correct (82%); latency 2.4s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d75\n takes turns during structured activities: 9/11 correct (82%); latency 2.5s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n copies simple words from model: 7/8 correct (86%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n Verbal aggression: freq 0\n\nSession 10 \u2014 2026-04-30 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/8 correct (44%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n indicating 'all done' when an activity is complete: 5/11 correct (41%); latency 4.3s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n takes turns during structured activities: 6/13 correct (44%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d710\n copies simple words from model: 6/14 correct (41%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d711\n Verbal aggression: freq 1\n\nSession 11 \u2014 2026-05-02 \u2014 60 min \u2014 1 observer\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 11/13 correct (88%); latency 2.2s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d710\n indicating 'all done' when an activity is complete: 11/14 correct (78%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d76\n takes turns during structured activities: 13/15 correct (90%); latency 2.1s; prompts FP\u00d70, PP\u00d72, G\u00d75, I\u00d78\n copies simple words from model: 10/13 correct (77%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d74\n Verbal aggression: freq 1\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Delayed responding (>5 seconds consistently)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Behavior Function Hypothesis\nVerbal aggression: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 11 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 66.2%.\n- Trend direction: upward (first session: 87%, last session: 88%).\n- Verbal aggression: mean 0.5/session (early-window mean 0.7 -> late-window mean 0.7).\n- IOA data: 89% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "a61de0f2c5761341", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {"Verbal aggression": "escape"}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "school_age", "n_sessions": 11, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["verbal_aggression"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "4269"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: spontaneously greets familiar people\nCurriculum Reference: Spontaneous Vocal Behavior L1\nLearner Profile: Early Learner\nCurrent Mastery: Near mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously greets familiar people\n- Curriculum: Spontaneous Vocal Behavior L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nUse the natural beginning/ending of an established routine (morning arrival, mealtime, departure) as the moment for the target response.\nPrimary natural context: departure.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's departure routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the near mastery stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: adult returns the greeting warmly.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "7a8b6a280f60c544", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously greets familiar people", "mo_category": "spontaneous_greeting", "mo_arrangement": "routine_lead_in", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "44373"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: identifies basic shapes in math context\nCurriculum: Math L1\nLearner Level: Early Learner\nBaseline: Approaching mastery\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies basic shapes in math context\n- Curriculum: Math L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What number is this?\"\nVariations: \"Which number?\"; \"Tell me the number\"\nPresentation: Present the numeral card.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: heart, star, circle\nDistractor stimuli: diamond, triangle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "245293d827f46696", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies basic shapes in math context", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "crf", "error_correction": "simple_correction", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "35263"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4405\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Mand + Reading + Self-Care + Tolerating Denied Access\nDate range: Sessions 1\u20138 across 16 days (2026-05-06 to 2026-05-22)\n\nACCELERATION PROGRAMS\n1. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n2. requesting preferred items using AAC device (Mand)\n Method: NET\n3. indicating 'all done' with a step or activity (Mand)\n Method: NET\n4. brushing teeth independently (Self-Care)\n Method: Task Analysis\n5. sounds out CVC words (Reading)\n Method: DTT\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-06 \u2014 48 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 4/11 correct (39%); latency 4.5s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d77\n requesting preferred items using AAC device: 8/15 correct (54%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d712\n indicating 'all done' with a step or activity: 5/14 correct (36%); latency 4.5s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d710\n brushing teeth independently: 6/12 correct (47%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d78\n sounds out CVC words: 3/9 correct (38%); latency 4.5s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d73\n\nSession 2 \u2014 2026-05-08 \u2014 48 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/15 correct (51%); latency 3.7s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d77\n requesting preferred items using AAC device: 4/8 correct (54%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n indicating 'all done' with a step or activity: 3/8 correct (33%); latency 4.7s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n brushing teeth independently: 8/15 correct (54%); latency 3.7s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d78\n sounds out CVC words: 6/15 correct (39%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d79\n\nSession 3 \u2014 2026-05-10 \u2014 48 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 6/11 correct (53%); latency 3.4s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n requesting preferred items using AAC device: 8/14 correct (59%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d78\n indicating 'all done' with a step or activity: 4/9 correct (44%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n brushing teeth independently: 5/9 correct (52%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n sounds out CVC words: 4/10 correct (45%); latency 3.9s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d76\n\nSession 4 \u2014 2026-05-12 \u2014 48 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 5/9 correct (57%); latency 3.4s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n requesting preferred items using AAC device: 7/11 correct (63%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d79\n indicating 'all done' with a step or activity: 6/14 correct (44%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d77\n brushing teeth independently: 5/9 correct (59%); latency 3.2s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n sounds out CVC words: 6/11 correct (53%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n\nSession 5 \u2014 2026-05-14 \u2014 48 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 6/10 correct (62%); latency 3.4s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n requesting preferred items using AAC device: 10/14 correct (70%); latency 2.7s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d73\n indicating 'all done' with a step or activity: 8/15 correct (51%); latency 3.6s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d75\n brushing teeth independently: 8/12 correct (64%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d712\n sounds out CVC words: 4/8 correct (55%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n\nSession 6 \u2014 2026-05-16 \u2014 48 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 11/15 correct (72%); latency 2.8s; prompts FP\u00d75, PP\u00d74, G\u00d75, I\u00d71\n requesting preferred items using AAC device: 7/11 correct (66%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n indicating 'all done' with a step or activity: 7/12 correct (56%); latency 3.2s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d74\n brushing teeth independently: 6/8 correct (72%); latency 2.6s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n sounds out CVC words: 6/10 correct (58%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d78\n\nSession 7 \u2014 2026-05-18 \u2014 48 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 7/9 correct (78%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n requesting preferred items using AAC device: 10/14 correct (74%); latency 2.9s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d75\n indicating 'all done' with a step or activity: 9/15 correct (57%); latency 3.5s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d76\n brushing teeth independently: 11/14 correct (76%); latency 2.5s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d711\n sounds out CVC words: 7/10 correct (71%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n\nSession 8 \u2014 2026-05-20 \u2014 48 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/10 correct (78%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n requesting preferred items using AAC device: 11/14 correct (80%); latency 2.5s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n indicating 'all done' with a step or activity: 8/13 correct (61%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d77\n brushing teeth independently: 11/12 correct (88%); latency 2.2s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d79\n sounds out CVC words: 11/15 correct (74%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d711\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Eye contact maintained throughout trials\n- Appropriate sitting posture maintained\n- Requesting more trials verbally\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- Steady improvement: accuracy rose from 39% to 78% across 8 sessions.\n- No clinical concerns at this time; mastery criteria should be reachable within a few additional sessions.\n\n## Pattern Classification\nmastery_progression\n\nAccuracy is ascending cleanly across sessions with no interfering behaviors, consistent with a mastery-progression trajectory.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Continue current teaching procedure \u2014 it is effective for this learner.\n- Maintain current stimulus arrangement; begin planning next skill in sequence.\n\n### Consequence strategies\n- Begin thinning reinforcement from CRF to FR-2 as accuracy stabilizes above 85%.\n- Continue differential reinforcement for independent responses.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 61.2%.\n- Trend direction: upward (first session: 39%, last session: 78%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "5315591797aed264", "gold_labels": {"pattern_class": "mastery_progression", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "mastery_progression", "learner_profile": "adolescent", "n_sessions": 8, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "5794"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: engages in social games (peek-a-boo, tickle)\nCurriculum: Social Behavior & Social Play L1\nLearner Level: Early Learner\nBaseline: Generalization phase\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: engages in social games (peek-a-boo, tickle)\n- Curriculum: Social Behavior & Social Play L1\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: circle time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's circle time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the generalization stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use with a peer in unstructured free play across 2 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "df0b036de2688cb5", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L1", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "engages in social games (peek-a-boo, tickle)", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_peer_initiation"}, "teacher_model": null, "seed_tag": "67055"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: solves simple word problems\nCurriculum: Math L3\nLearner: School-Age Learner\nMastery Status: Generalization phase\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: solves simple word problems\n- Curriculum: Math L3\n- Learner: School-Age Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"How many?\"\nVariations: \"Count these\"; \"What number is this?\"\nPresentation: Present the numeral card or a set of objects to count.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: bottle, ball, apple\nDistractor stimuli: book, towel, spoon, glue, hat\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nToken economy \u2014 Tokens delivered per correct response; exchanged at session end for a back-up reinforcer appropriate to the learner (for children: candy, cookies, brief leisure-time access, preferred activity, screen time, or a favorite sensory item). Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "963fc2aabc513c65", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L3", "learner_profile": "school_age", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "solves simple word problems", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "token_economy", "error_correction": "backstep", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "69141"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-2052\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math\nDate range: Sessions 1\u20139 across 18 days (2026-09-24 to 2026-10-12)\n\nACCELERATION PROGRAMS\n1. single-word requests for preferred items (Mand)\n Method: NET\n2. requesting preferred items using a full sentence (Mand)\n Method: NET\n3. counts objects 1\u201320 (Math)\n Method: DTT\n4. identifies numerals 1\u201320 (Math)\n Method: DTT\n\nDECELERATION TARGETS\n1. Motor stereotypy \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-24 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 4/9 correct (43%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n requesting preferred items using a full sentence: 4/9 correct (46%); latency 4.0s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n counts objects 1\u201320: 6/15 correct (42%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d77\n identifies numerals 1\u201320: 6/15 correct (41%); latency 3.9s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d76\n Motor stereotypy: freq 1; PIR 13%\n\nSession 2 \u2014 2026-09-26 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 6/14 correct (44%); latency 4.2s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d79\n requesting preferred items using a full sentence: 7/14 correct (47%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d79\n counts objects 1\u201320: 7/14 correct (48%); latency 3.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d77\n identifies numerals 1\u201320: 5/10 correct (51%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n Motor stereotypy: freq 0; PIR 7%\n\nSession 3 \u2014 2026-09-28 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 6/11 correct (58%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n requesting preferred items using a full sentence: 4/8 correct (54%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n counts objects 1\u201320: 8/14 correct (57%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d710\n identifies numerals 1\u201320: 9/14 correct (62%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d78\n Motor stereotypy: freq 1; PIR 5%\n\nSession 4 \u2014 2026-09-30 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 5/9 correct (59%); latency 3.5s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d72\n requesting preferred items using a full sentence: 5/8 correct (68%); latency 3.0s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n counts objects 1\u201320: 8/12 correct (66%); latency 3.0s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d76\n identifies numerals 1\u201320: 9/13 correct (66%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d72\n Motor stereotypy: freq 1; PIR 5%\n\nSession 5 \u2014 2026-10-02 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 8/12 correct (70%); latency 2.9s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d72\n requesting preferred items using a full sentence: 7/9 correct (72%); latency 2.6s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n counts objects 1\u201320: 8/11 correct (76%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n identifies numerals 1\u201320: 8/11 correct (74%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n Motor stereotypy: freq 0; PIR 10%\n\nSession 6 \u2014 2026-10-04 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 9/11 correct (78%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n requesting preferred items using a full sentence: 10/12 correct (84%); latency 2.4s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d76\n counts objects 1\u201320: 12/15 correct (79%); latency 2.5s; prompts FP\u00d70, PP\u00d75, G\u00d75, I\u00d75\n identifies numerals 1\u201320: 6/8 correct (77%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n Motor stereotypy: freq 2; PIR 12%\n\nSession 7 \u2014 2026-10-06 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 12/15 correct (80%); latency 2.2s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d78\n requesting preferred items using a full sentence: 7/8 correct (90%); latency 1.8s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n counts objects 1\u201320: 8/9 correct (87%); latency 2.0s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d74\n identifies numerals 1\u201320: 13/15 correct (84%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d711\n Motor stereotypy: freq 1; PIR 11%\n\nSession 8 \u2014 2026-10-08 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 9/10 correct (92%); latency 1.9s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d76\n requesting preferred items using a full sentence: 14/15 correct (95%); latency 1.8s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d710\n counts objects 1\u201320: 14/15 correct (95%); latency 1.7s; prompts FP\u00d73, PP\u00d75, G\u00d72, I\u00d75\n identifies numerals 1\u201320: 8/9 correct (93%); latency 1.5s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n Motor stereotypy: freq 0; PIR 3%\n\nSession 9 \u2014 2026-10-10 \u2014 59 min \u2014 1 observer\n single-word requests for preferred items: 8/8 correct (95%); latency 1.7s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n requesting preferred items using a full sentence: 11/12 correct (95%); latency 1.5s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d75\n counts objects 1\u201320: 13/14 correct (95%); latency 1.8s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d77\n identifies numerals 1\u201320: 8/8 correct (95%); latency 1.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n Motor stereotypy: freq 0; PIR 2%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Appropriate sitting posture maintained\n- Smiling during reinforcement delivery\n- Eye contact maintained throughout trials\n- Reaching for materials proactively"}, {"role": "assistant", "content": "## Clinical Concerns\n- Steady improvement: accuracy rose from 43% to 95% across 9 sessions.\n- No clinical concerns at this time; mastery criteria should be reachable within a few additional sessions.\n\n## Pattern Classification\nmastery_progression\n\nAccuracy is ascending cleanly across sessions with no interfering behaviors, consistent with a mastery-progression trajectory.\n\n## Behavior Function Hypothesis\nMotor stereotypy: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Continue current teaching procedure \u2014 it is effective for this learner.\n- Maintain current stimulus arrangement; begin planning next skill in sequence.\n\n### Consequence strategies\n- Begin thinning reinforcement from CRF to FR-2 as accuracy stabilizes above 85%.\n- Continue differential reinforcement for independent responses.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 68.7%.\n- Trend direction: upward (first session: 43%, last session: 95%).\n- Motor stereotypy: mean 0.7/session (early-window mean 0.7 -> late-window mean 0.3).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "8a4557cc64117938", "gold_labels": {"pattern_class": "mastery_progression", "behavior_functions": {"Motor stereotypy": "automatic"}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "mastery_progression", "learner_profile": "school_age", "n_sessions": 9, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["motor_stereotypy"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "97400"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: selects correct item from an array of 2\nCurriculum Reference: Listener Responding L1\nLearner Profile: Early Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects correct item from an array of 2\n- Curriculum: Listener Responding L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: crayon, hat, napkin\nDistractor stimuli: block, key\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "543a505338f0e98c", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects correct item from an array of 2", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "fr2", "error_correction": "backstep", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "93657"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: answers hypothetical questions\nCurriculum Reference: Intraverbal L3\nLearner Profile: Adolescent Learner\nCurrent Mastery: Generalization phase\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: answers hypothetical questions\n- Curriculum: Intraverbal L3\n- Learner: Adolescent Learner\n- Current mastery: Generalization phase\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: post-activity debrief.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's post-activity debrief routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the generalization stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "d9deb6595de84cb9", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L3", "learner_profile": "adolescent", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "answers hypothetical questions", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "time_delay", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "30191"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5878\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Tolerating Denied Access\nDate range: Sessions 1\u201310 across 20 days (2026-06-03 to 2026-06-23)\n\nACCELERATION PROGRAMS\n1. doing laundry (Home Skills)\n Method: Task Analysis\n2. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n3. simple meal preparation (Home Skills)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Elopement \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-03 \u2014 50 min \u2014 1 observer\n doing laundry: 8/10 correct (78%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d74\n wait calmly when a preferred activity is denied: 7/9 correct (81%); latency 2.5s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n simple meal preparation: 6/8 correct (79%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n Elopement: freq 1\n\nSession 2 \u2014 2026-06-05 \u2014 50 min \u2014 1 observer\n doing laundry: 12/15 correct (80%); latency 2.3s; prompts FP\u00d71, PP\u00d74, G\u00d75, I\u00d75\n wait calmly when a preferred activity is denied: 6/9 correct (69%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n simple meal preparation: 6/8 correct (79%); latency 2.3s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n Elopement: freq 3\n\nSession 3 \u2014 2026-06-07 \u2014 50 min \u2014 1 observer\n doing laundry: 7/10 correct (69%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d77\n wait calmly when a preferred activity is denied: 7/11 correct (68%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n simple meal preparation: 8/13 correct (64%); latency 3.4s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d72\n Elopement: freq 2\n\nSession 4 \u2014 2026-06-09 \u2014 50 min \u2014 1 observer\n doing laundry: 7/11 correct (62%); latency 3.0s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n wait calmly when a preferred activity is denied: 6/10 correct (60%); latency 3.3s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n simple meal preparation: 6/10 correct (63%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n Elopement: freq 3\n\nSession 5 \u2014 2026-06-11 \u2014 50 min \u2014 1 observer\n doing laundry: 8/12 correct (63%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d78\n wait calmly when a preferred activity is denied: 5/8 correct (56%); latency 3.5s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n simple meal preparation: 5/10 correct (51%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d73\n Elopement: freq 4\n\nSession 6 \u2014 2026-06-13 \u2014 50 min \u2014 1 observer\n doing laundry: 9/15 correct (59%); latency 3.0s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d710\n wait calmly when a preferred activity is denied: 7/14 correct (50%); latency 3.8s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d76\n simple meal preparation: 4/8 correct (46%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n Elopement: freq 5\n\nSession 7 \u2014 2026-06-15 \u2014 50 min \u2014 1 observer\n doing laundry: 6/10 correct (58%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n wait calmly when a preferred activity is denied: 4/10 correct (44%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n simple meal preparation: 3/8 correct (38%); latency 4.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n Elopement: freq 4\n\nSession 8 \u2014 2026-06-17 \u2014 50 min \u2014 1 observer\n doing laundry: 7/14 correct (51%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d78\n wait calmly when a preferred activity is denied: 3/8 correct (41%); latency 4.0s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n simple meal preparation: 3/12 correct (27%); latency 5.1s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d75\n Elopement: freq 6\n\nSession 9 \u2014 2026-06-19 \u2014 50 min \u2014 1 observer\n doing laundry: 4/9 correct (42%); latency 4.1s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n wait calmly when a preferred activity is denied: 4/11 correct (38%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d711\n simple meal preparation: 2/9 correct (19%); latency 5.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n Elopement: freq 6\n\nSession 10 \u2014 2026-06-21 \u2014 50 min \u2014 1 observer\n doing laundry: 5/13 correct (41%); latency 4.1s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n wait calmly when a preferred activity is denied: 4/12 correct (34%); latency 4.7s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d710\n simple meal preparation: 2/15 correct (10%); latency 5.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d714\n Elopement: freq 8\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Turning away from task or staff\n- Crying during demand presentation\n- Vocal refusal ('no', 'I don't want to')"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (78% -> 41%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nElopement: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 60.3%.\n- Trend direction: downward (first session: 78%, last session: 41%).\n- Elopement: mean 4.2/session (early-window mean 2.0 -> late-window mean 6.7).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "92ba46c1f5e394ad", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Elopement": "escape"}, "escalation_level": 4, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "adult", "n_sessions": 10, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["elopement"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "8458"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a chaining program for the following.\n\nSkill: unloading the dishwasher\nCurriculum: AFLS Home Skills\nLearner Level: Adolescent Learner\nBaseline: Near mastery\n\nInclude the full Task Analysis structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: unloading the dishwasher\n- Curriculum: AFLS Home Skills\n- Learner: Adolescent Learner\n- Current mastery: Near mastery\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Open the dishwasher once the cycle is complete. <- Learner-taught step (forward chaining starts here)\n2. Unload the top rack first (cups, glasses, small items).\n3. Put cups and glasses away in the correct cabinet.\n4. Unload the utensil basket.\n5. Put utensils away in the drawer.\n6. Unload the bottom rack (plates, bowls, larger items).\n7. Put plates and bowls away in the correct cabinet.\n8. Close the dishwasher door.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the near mastery stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nToken economy \u2014 One token per correctly-completed step; token exchange at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 90s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "ac15d726f8d8b745", "gold_labels": {"method": "task_analysis", "domain": "AFLS.home", "skill": "unloading the dishwasher", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "near", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "unloading the dishwasher", "module": "home", "mastery_criterion": "mc_fluent_chain", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "44637"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: mands for information using \"what\"\nCurriculum: Mand L2\nLearner: School-Age Learner\nMastery Status: Generalization phase\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands for information using \"what\"\n- Curriculum: Mand L2\n- Learner: School-Age Learner\n- Current mastery: Generalization phase\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: morning greeting.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's morning greeting routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the generalization stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: adult answers the question informatively.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nAverage rate of \u2265 3 spontaneous responses per 30-minute session across 3 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "9bc65664e489d56c", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L2", "learner_profile": "school_age", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands for information using \"what\"", "mo_category": "mand_info_what", "mo_arrangement": "unexpected_change", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_spontaneous_rate"}, "teacher_model": null, "seed_tag": "40151"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: spontaneously initiates conversation with peers\nCurriculum: Spontaneous Vocal Behavior L2\nLearner Level: School-Age Learner\nBaseline: Generalization phase\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously initiates conversation with peers\n- Curriculum: Spontaneous Vocal Behavior L2\n- Learner: School-Age Learner\n- Current mastery: Generalization phase\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: room transition.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's room transition routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Verbal fill-in\nDeliver a partial phrase and pause; learner completes the vocal response.\nCurrent prompt level: At the generalization stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use with a peer in unstructured free play across 2 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "5fd6bd510eb6da06", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L2", "learner_profile": "school_age", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously initiates conversation with peers", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "verbal_fill_in", "mastery_criterion": "mc_peer_initiation"}, "teacher_model": null, "seed_tag": "40151"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: matches non-identical items by category\nCurriculum: Visual Perceptual Skills & Matching-to-Sample L2\nLearner Level: School-Age Learner\nBaseline: Near mastery\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: matches non-identical items by category\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L2\n- Learner: School-Age Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: sock, shoe, hat\nDistractor stimuli: brush, phone, jacket, towel\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "c9be181d3e3812d2", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L2", "learner_profile": "school_age", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "matches non-identical items by category", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "fr2", "error_correction": "simple_correction", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "17197"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: selects correct item from an array of 2\nCurriculum Reference: Listener Responding L1\nLearner Profile: Early Learner\nCurrent Mastery: Emerging\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects correct item from an array of 2\n- Curriculum: Listener Responding L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: apple, bottle, brush\nDistractor stimuli: spoon, glue\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy at independent prompt level across 3 sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "38ef29638c95b0c1", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects correct item from an array of 2", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "crf", "error_correction": "simple_correction", "mastery_criterion": "mc_80_independent"}, "teacher_model": null, "seed_tag": "75131"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: tolerating tooth brushing by caregiver\nCurriculum Reference: AFLS Basic Living Skills\nLearner Profile: Adult Learner\nCurrent Mastery: Emerging\nTeaching Method: Toleration / Systematic Desensitization\n\nThe goal is for the learner to allow the activity to be performed (not to perform it independently). Provide the full program structure including shaping steps and refusal/safety procedures."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating tooth brushing by caregiver\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Emerging\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for tooth brushing performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nfull 2-minute tooth-brushing routine completed by caregiver without refusal, crying, SIB, or aggression\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1-second toothbrush contact with teeth\n2. 3 seconds of brushing\n3. 5 seconds of brushing\n4. 15 seconds of brushing\n5. 30 seconds of brushing\n6. 60 seconds of brushing\n7. Full 2-minute brushing routine\n\nCurrent shaping step: At the emerging stage, begin at shaping step 1 (\"1-second toothbrush contact with teeth\") and advance through step 2 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal activity tolerated across 2 different settings (e.g., home and clinic) across 2 consecutive weeks without safety behaviors.\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 3 different settings and with 2 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "fd02b7c9fec2c31c", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating tooth brushing by caregiver", "program_type": "toleration", "learner_profile": "adult", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating tooth brushing by caregiver", "module": "basic_living", "mastery_criterion": "mc_toleration_settings", "shaping_n_steps": 7}, "teacher_model": null, "seed_tag": "50550"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7450\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Social Behavior\nDate range: Sessions 1\u201310 across 20 days (2026-04-26 to 2026-05-16)\n\nACCELERATION PROGRAMS\n1. counts objects 1\u201320 (Math)\n Method: DTT\n2. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n3. takes turns during structured activities (Social Behavior)\n Method: PRT\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-26 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 7/12 correct (55%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d76\n indicating 'all done' when an activity is complete: 10/14 correct (69%); latency 3.1s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d75\n takes turns during structured activities: 9/14 correct (64%); latency 3.1s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d75\n\nSession 2 \u2014 2026-04-28 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 8/13 correct (63%); latency 3.0s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d75\n indicating 'all done' when an activity is complete: 5/8 correct (68%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n takes turns during structured activities: 9/14 correct (63%); latency 2.9s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d79\n\nSession 3 \u2014 2026-04-30 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 9/14 correct (64%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d710\n indicating 'all done' when an activity is complete: 8/12 correct (67%); latency 3.0s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d76\n takes turns during structured activities: 5/9 correct (59%); latency 3.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n\nSession 4 \u2014 2026-05-02 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 9/15 correct (61%); latency 3.4s; prompts FP\u00d70, PP\u00d75, G\u00d73, I\u00d77\n indicating 'all done' when an activity is complete: 5/8 correct (64%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n takes turns during structured activities: 8/14 correct (60%); latency 3.4s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d79\n\nSession 5 \u2014 2026-05-04 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 3/12 correct (27%); latency 4.5s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d74\n indicating 'all done' when an activity is complete: 4/9 correct (42%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n takes turns during structured activities: 4/13 correct (27%); latency 4.6s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d76\n\nSession 6 \u2014 2026-05-06 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 4/13 correct (32%); latency 4.7s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d78\n indicating 'all done' when an activity is complete: 7/14 correct (50%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d710\n takes turns during structured activities: 3/9 correct (36%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n\nSession 7 \u2014 2026-05-08 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 5/12 correct (41%); latency 4.3s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d76\n indicating 'all done' when an activity is complete: 5/9 correct (54%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n takes turns during structured activities: 3/8 correct (41%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n\nSession 8 \u2014 2026-05-10 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 7/15 correct (49%); latency 3.7s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d76\n indicating 'all done' when an activity is complete: 9/14 correct (62%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d711\n takes turns during structured activities: 7/15 correct (44%); latency 3.9s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d711\n\nSession 9 \u2014 2026-05-12 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 7/13 correct (54%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d711\n indicating 'all done' when an activity is complete: 10/15 correct (65%); latency 2.8s; prompts FP\u00d75, PP\u00d72, G\u00d72, I\u00d76\n takes turns during structured activities: 8/14 correct (54%); latency 3.6s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d76\n\nSession 10 \u2014 2026-05-14 \u2014 39 min \u2014 1 observer\n counts objects 1\u201320: 9/15 correct (59%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d77\n indicating 'all done' when an activity is complete: 8/12 correct (65%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d78\n takes turns during structured activities: 5/9 correct (60%); latency 3.3s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Delayed responding (>5 seconds consistently)\n- Leaving seat without permission\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 50.5%.\n- Trend direction: upward (first session: 55%, last session: 59%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "01a9a4d0e97c76a1", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "school_age", "n_sessions": 10, "n_programs": 3, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "53478"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: clocking in at start of shift\nCurriculum Reference: AFLS Vocational Skills\nLearner Profile: Adult Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: Task Analysis / Chaining\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: clocking in at start of shift\n- Curriculum: AFLS Vocational Skills\n- Learner: Adult Learner\n- Current mastery: Mastered at current level\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Arrive at the workplace by the scheduled time.\n2. Locate the time clock or digital system.\n3. Enter identification (ID card / badge / code).\n4. Confirm the clock-in timestamp.\n5. Notify the supervisor or check the day's task list.\n6. Proceed to the assigned workstation.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the mastered stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\n100% of steps completed independently (no prompts) across 3 consecutive trials of the full chain.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "f2ffda94885d3bc3", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "clocking in at start of shift", "program_type": "independence", "learner_profile": "adult", "mastery_state": "mastered", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "clocking in at start of shift", "module": "vocational", "mastery_criterion": "mc_all_steps_independent", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "39765"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1849\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Reading + Social Behavior\nDate range: Sessions 1\u20138 across 16 days (2026-07-05 to 2026-07-21)\n\nACCELERATION PROGRAMS\n1. reads 10\u201320 sight words (Reading)\n Method: DTT\n2. requesting a break during non-preferred tasks (Mand)\n Method: NET\n3. takes turns during structured activities (Social Behavior)\n Method: PRT\n4. requesting preferred items using AAC device (e.g., \"I want cookie please\") (Mand)\n Method: NET\n5. counts objects 1\u201320 (Math)\n Method: DTT\n\nDECELERATION TARGETS\n1. Elopement \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-05 \u2014 55 min \u2014 1 observer\n reads 10\u201320 sight words: 7/9 correct (77%); latency 2.8s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n requesting a break during non-preferred tasks: 9/11 correct (82%); latency 2.5s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d77\n takes turns during structured activities: 6/8 correct (70%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 9/11 correct (79%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n counts objects 1\u201320: 9/11 correct (85%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d77\n Elopement: freq 2\n\nSession 2 \u2014 2026-07-07 \u2014 55 min \u2014 1 observer\n reads 10\u201320 sight words: 10/12 correct (82%); latency 2.1s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d78\n requesting a break during non-preferred tasks: 7/9 correct (75%); latency 2.8s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n takes turns during structured activities: 10/13 correct (74%); latency 2.6s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d71\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 13/15 correct (85%); latency 2.3s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d77\n counts objects 1\u201320: 8/9 correct (84%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d73\n Elopement: freq 2\n ABC (elopement): A = quiet unstructured moment between trials; B = engaged in hand-flapping; C = no social consequence; self-terminated after 30s\n\nSession 3 \u2014 2026-07-09 \u2014 55 min \u2014 1 observer\n reads 10\u201320 sight words: 4/10 correct (41%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n requesting a break during non-preferred tasks: 5/12 correct (44%); latency 4.3s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d77\n takes turns during structured activities: 6/15 correct (37%); latency 4.2s; prompts FP\u00d75, PP\u00d73, G\u00d70, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 5/10 correct (55%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n counts objects 1\u201320: 5/11 correct (45%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d77\n Elopement: freq 3\n\nSession 4 \u2014 2026-07-11 \u2014 55 min \u2014 1 observer\n reads 10\u201320 sight words: 3/8 correct (39%); latency 4.1s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n requesting a break during non-preferred tasks: 5/11 correct (47%); latency 3.8s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n takes turns during structured activities: 4/10 correct (42%); latency 4.1s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 6/12 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d78\n counts objects 1\u201320: 4/9 correct (45%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n Elopement: freq 3\n\nSession 5 \u2014 2026-07-13 \u2014 55 min \u2014 1 observer\n reads 10\u201320 sight words: 4/10 correct (44%); latency 4.1s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d79\n requesting a break during non-preferred tasks: 6/14 correct (45%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d76\n takes turns during structured activities: 5/13 correct (36%); latency 4.2s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 4/9 correct (48%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n counts objects 1\u201320: 5/10 correct (51%); latency 3.9s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n Elopement: freq 2\n ABC (elopement): A = quiet unstructured moment between trials; B = engaged in hand-flapping; C = no social consequence; self-terminated after 30s\n\nSession 6 \u2014 2026-07-15 \u2014 55 min \u2014 1 observer\n reads 10\u201320 sight words: 6/14 correct (39%); latency 4.2s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d73\n requesting a break during non-preferred tasks: 6/14 correct (45%); latency 3.9s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d79\n takes turns during structured activities: 6/14 correct (41%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d712\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 4/8 correct (48%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n counts objects 1\u201320: 6/14 correct (43%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n Elopement: freq 3\n\nSession 7 \u2014 2026-07-17 \u2014 55 min \u2014 1 observer\n reads 10\u201320 sight words: 6/14 correct (45%); latency 4.2s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d710\n requesting a break during non-preferred tasks: 6/12 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n takes turns during structured activities: 4/9 correct (48%); latency 3.8s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/14 correct (52%); latency 3.8s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n counts objects 1\u201320: 8/15 correct (53%); latency 3.7s; prompts FP\u00d75, PP\u00d73, G\u00d71, I\u00d76\n Elopement: freq 3\n\nSession 8 \u2014 2026-07-19 \u2014 55 min \u2014 1 observer\n reads 10\u201320 sight words: 5/10 correct (51%); latency 3.5s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n requesting a break during non-preferred tasks: 5/9 correct (60%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n takes turns during structured activities: 5/9 correct (57%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 6/11 correct (59%); latency 3.5s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n counts objects 1\u201320: 5/9 correct (59%); latency 3.1s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n Elopement: freq 3\n ABC (elopement): A = quiet unstructured moment between trials; B = engaged in hand-flapping; C = no social consequence; self-terminated after 30s\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Playing with non-task materials\n- Looking away during SD presentation\n- Leaving seat without permission"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Behavior Function Hypothesis\nElopement: automatic\n Evidence: ABC events in the log support the automatic function; behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 52.2%.\n- Trend direction: downward (first session: 77%, last session: 51%).\n- Elopement: mean 2.6/session (early-window mean 2.0 -> late-window mean 3.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "7b64026b8d55d001", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {"Elopement": "automatic"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "school_age", "n_sessions": 8, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["elopement"], "behavior_functions": ["automatic"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "87536"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3922\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Mand + Tolerating Denied Access\nDate range: Sessions 1\u201310 across 20 days (2026-09-02 to 2026-09-22)\n\nACCELERATION PROGRAMS\n1. doing laundry (Home Skills)\n Method: Task Analysis\n2. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n3. requesting a break during extended tasks (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Aggression \u2014 function hypothesized: escape\n2. Pica \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-02 \u2014 39 min \u2014 1 observer\n doing laundry: 10/14 correct (68%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d710\n wait calmly when a preferred activity is denied: 8/14 correct (57%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n requesting a break during extended tasks: 6/8 correct (75%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n Aggression: freq 0\n Pica: attempts 2 (1 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 2 \u2014 2026-09-04 \u2014 39 min \u2014 1 observer\n doing laundry: 7/12 correct (62%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d76\n wait calmly when a preferred activity is denied: 7/11 correct (59%); latency 3.3s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n requesting a break during extended tasks: 5/8 correct (68%); latency 3.2s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n Aggression: freq 2\n Pica: attempts 3 (0 unsuccessful \u2014 staff retrieved item before ingestion; 3 successful \u2014 item ingested)\n\nSession 3 \u2014 2026-09-06 \u2014 39 min \u2014 1 observer\n doing laundry: 7/11 correct (64%); latency 3.2s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d77\n wait calmly when a preferred activity is denied: 5/10 correct (52%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n requesting a break during extended tasks: 8/12 correct (66%); latency 2.9s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d78\n Aggression: freq 0\n Pica: attempts 2 (2 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 4 \u2014 2026-09-08 \u2014 39 min \u2014 1 observer\n doing laundry: 6/9 correct (68%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d76\n wait calmly when a preferred activity is denied: 5/9 correct (56%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n requesting a break during extended tasks: 8/12 correct (68%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d79\n Aggression: freq 2\n Pica: attempts 3 (2 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 5 \u2014 2026-09-10 \u2014 39 min \u2014 1 observer\n doing laundry: 3/9 correct (33%); latency 4.3s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n wait calmly when a preferred activity is denied: 4/14 correct (29%); latency 4.8s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d76\n requesting a break during extended tasks: 4/8 correct (50%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n Aggression: freq 4\n Pica: attempts 7 (7 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 6 \u2014 2026-09-12 \u2014 39 min \u2014 1 observer\n doing laundry: 4/9 correct (41%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n wait calmly when a preferred activity is denied: 3/10 correct (33%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n requesting a break during extended tasks: 7/12 correct (57%); latency 3.3s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d78\n Aggression: freq 4\n Pica: attempts 7 (6 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 7 \u2014 2026-09-14 \u2014 39 min \u2014 1 observer\n doing laundry: 5/13 correct (41%); latency 4.3s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n wait calmly when a preferred activity is denied: 3/8 correct (41%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n requesting a break during extended tasks: 7/10 correct (68%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n Aggression: freq 0\n Pica: attempts 2 (2 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 8 \u2014 2026-09-16 \u2014 39 min \u2014 1 observer\n doing laundry: 6/13 correct (45%); latency 4.2s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d78\n wait calmly when a preferred activity is denied: 5/12 correct (44%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d77\n requesting a break during extended tasks: 7/10 correct (70%); latency 2.8s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n Aggression: freq 1\n Pica: attempts 2 (1 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 9 \u2014 2026-09-18 \u2014 39 min \u2014 1 observer\n doing laundry: 6/12 correct (53%); latency 3.6s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d72\n wait calmly when a preferred activity is denied: 5/9 correct (50%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n requesting a break during extended tasks: 11/15 correct (71%); latency 3.0s; prompts FP\u00d75, PP\u00d71, G\u00d73, I\u00d76\n Aggression: freq 2\n Pica: attempts 3 (1 unsuccessful \u2014 staff retrieved item before ingestion; 2 successful \u2014 item ingested)\n\nSession 10 \u2014 2026-09-20 \u2014 39 min \u2014 1 observer\n doing laundry: 8/13 correct (60%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d77\n wait calmly when a preferred activity is denied: 5/9 correct (56%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n requesting a break during extended tasks: 10/14 correct (71%); latency 2.8s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d79\n Aggression: freq 0\n Pica: attempts 2 (2 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Leaving seat without permission\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Behavior Function Hypothesis\nAggression: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\nPica: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n### Crisis plan\n- If the setting event involves a medical concern (seizure-like activity, injury, illness): stop the program immediately, follow the facility's medical-incident protocol, and refer to the appropriate medical professional. Medical events are NOT behavioral targets and must not be treated as ABA programming issues.\n- If behavior escalates during the setting-event window: use verbal de-escalation and environmental safety first; do not add demand. Only staff currently certified in the facility's crisis-prevention framework may use physical intervention, and only if imminent safety risk warrants it AND the learner's BIP specifically authorizes it (contraindications and BIP restrictions may rule it out).\n- Coordinate with caregivers, the medical team, and the supervising BCBA; document the setting event and the associated behavior for pattern analysis. Review the BIP in light of the setting-event data.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 53.5%.\n- Trend direction: downward (first session: 68%, last session: 60%).\n- Aggression: mean 1.5/session (early-window mean 0.7 -> late-window mean 1.0).\n- Pica: mean 3.3/session (early-window mean 2.3 -> late-window mean 2.3).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "1101c5df682a1f90", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {"Aggression": "escape", "Pica": "automatic"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "adult", "n_sessions": 10, "n_programs": 3, "n_behaviors": 2, "behavior_ids": ["aggression", "pica"], "behavior_functions": ["escape", "automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "86328"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: unloading the dishwasher\nCurriculum: AFLS Home Skills\nLearner: Adolescent Learner\nMastery Status: Generalization phase\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: unloading the dishwasher\n- Curriculum: AFLS Home Skills\n- Learner: Adolescent Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Open the dishwasher once the cycle is complete. <- Learner-taught step (forward chaining starts here)\n2. Unload the top rack first (cups, glasses, small items).\n3. Put cups and glasses away in the correct cabinet.\n4. Unload the utensil basket.\n5. Put utensils away in the drawer.\n6. Unload the bottom rack (plates, bowls, larger items).\n7. Put plates and bowls away in the correct cabinet.\n8. Close the dishwasher door.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 180s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "a9114ef5b73f2211", "gold_labels": {"method": "task_analysis", "domain": "AFLS.home", "skill": "unloading the dishwasher", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "generalization", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "unloading the dishwasher", "module": "home", "mastery_criterion": "mc_fluent_chain", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "92010"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5711\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Mand + Reading + Self-Care\nDate range: Sessions 1\u201312 across 24 days (2026-08-17 to 2026-09-10)\n\nACCELERATION PROGRAMS\n1. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n2. ordering in a restaurant (Community)\n Method: Task Analysis\n3. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n4. reads 10\u201320 sight words (Reading)\n Method: DTT\n5. sounds out CVC words (Reading)\n Method: DTT\n6. requesting preferred items using AAC device (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-17 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 10/12 correct (81%); latency 2.1s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d75\n ordering in a restaurant: 11/14 correct (80%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d711\n meal cleanup after eating: 8/10 correct (76%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n reads 10\u201320 sight words: 7/9 correct (77%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d73\n sounds out CVC words: 8/10 correct (76%); latency 2.8s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n requesting preferred items using AAC device: 7/9 correct (77%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n Self-injurious behavior (SIB): freq 2\n\nSession 2 \u2014 2026-08-19 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 9/12 correct (77%); latency 2.8s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d78\n ordering in a restaurant: 8/10 correct (78%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d77\n meal cleanup after eating: 5/8 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n reads 10\u201320 sight words: 7/10 correct (72%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n sounds out CVC words: 7/10 correct (72%); latency 3.0s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d77\n requesting preferred items using AAC device: 9/13 correct (72%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d74\n Self-injurious behavior (SIB): freq 2\n\nSession 3 \u2014 2026-08-21 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 8/12 correct (70%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d75\n ordering in a restaurant: 7/9 correct (73%); latency 3.0s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d75\n meal cleanup after eating: 8/14 correct (58%); latency 3.6s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d74\n reads 10\u201320 sight words: 7/10 correct (67%); latency 3.0s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d78\n sounds out CVC words: 5/9 correct (59%); latency 3.5s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d75\n requesting preferred items using AAC device: 7/10 correct (69%); latency 2.8s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n Self-injurious behavior (SIB): freq 2\n\nSession 4 \u2014 2026-08-23 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 6/10 correct (60%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n ordering in a restaurant: 5/8 correct (65%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n meal cleanup after eating: 7/12 correct (56%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d710\n reads 10\u201320 sight words: 5/8 correct (57%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n sounds out CVC words: 6/12 correct (53%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d77\n requesting preferred items using AAC device: 6/9 correct (70%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n Self-injurious behavior (SIB): freq 2\n\nSession 5 \u2014 2026-08-25 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 9/15 correct (61%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d712\n ordering in a restaurant: 5/9 correct (52%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n meal cleanup after eating: 7/15 correct (48%); latency 4.1s; prompts FP\u00d71, PP\u00d73, G\u00d75, I\u00d76\n reads 10\u201320 sight words: 4/8 correct (54%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n sounds out CVC words: 6/12 correct (53%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d75\n requesting preferred items using AAC device: 8/13 correct (65%); latency 2.8s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d76\n Self-injurious behavior (SIB): freq 4\n\nSession 6 \u2014 2026-08-27 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 6/12 correct (52%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d73\n ordering in a restaurant: 6/12 correct (53%); latency 3.5s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d75\n meal cleanup after eating: 4/12 correct (37%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d79\n reads 10\u201320 sight words: 5/11 correct (45%); latency 4.1s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d78\n sounds out CVC words: 3/8 correct (44%); latency 4.3s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n requesting preferred items using AAC device: 6/11 correct (59%); latency 3.5s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d75\n Self-injurious behavior (SIB): freq 3\n\nSession 7 \u2014 2026-08-29 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 6/14 correct (46%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d711\n ordering in a restaurant: 5/12 correct (40%); latency 4.2s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d78\n meal cleanup after eating: 4/10 correct (38%); latency 4.3s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 4/8 correct (46%); latency 4.2s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n sounds out CVC words: 4/11 correct (37%); latency 4.6s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d75\n requesting preferred items using AAC device: 8/15 correct (53%); latency 3.6s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d77\n Self-injurious behavior (SIB): freq 4\n\nSession 8 \u2014 2026-08-31 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 4/12 correct (37%); latency 4.6s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d75\n ordering in a restaurant: 5/15 correct (35%); latency 4.4s; prompts FP\u00d71, PP\u00d71, G\u00d75, I\u00d78\n meal cleanup after eating: 4/15 correct (30%); latency 4.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d710\n reads 10\u201320 sight words: 3/8 correct (40%); latency 4.0s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n sounds out CVC words: 2/9 correct (22%); latency 4.8s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n requesting preferred items using AAC device: 7/13 correct (50%); latency 3.6s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d75\n Self-injurious behavior (SIB): freq 5\n\nSession 9 \u2014 2026-09-02 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 4/12 correct (36%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d78\n ordering in a restaurant: 3/10 correct (33%); latency 4.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n meal cleanup after eating: 1/8 correct (17%); latency 5.1s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n reads 10\u201320 sight words: 3/11 correct (31%); latency 4.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d77\n sounds out CVC words: 2/11 correct (14%); latency 5.3s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n requesting preferred items using AAC device: 4/8 correct (46%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n Self-injurious behavior (SIB): freq 4\n\nSession 10 \u2014 2026-09-04 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 4/13 correct (31%); latency 4.5s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d78\n ordering in a restaurant: 3/12 correct (25%); latency 4.7s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d75\n meal cleanup after eating: 1/12 correct (11%); latency 5.4s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 2/9 correct (25%); latency 5.1s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d75\n sounds out CVC words: 1/9 correct (11%); latency 5.5s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n requesting preferred items using AAC device: 6/13 correct (43%); latency 4.3s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d78\n Self-injurious behavior (SIB): freq 5\n\nSession 11 \u2014 2026-09-06 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 2/10 correct (20%); latency 5.0s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n ordering in a restaurant: 3/14 correct (19%); latency 5.3s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d77\n meal cleanup after eating: 2/14 correct (12%); latency 5.5s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d712\n reads 10\u201320 sight words: 2/14 correct (18%); latency 5.5s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d712\n sounds out CVC words: 1/8 correct (10%); latency 5.4s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n requesting preferred items using AAC device: 5/15 correct (36%); latency 4.2s; prompts FP\u00d72, PP\u00d74, G\u00d75, I\u00d74\n Self-injurious behavior (SIB): freq 5\n\nSession 12 \u2014 2026-09-08 \u2014 37 min \u2014 1 observer\n dressing (pants, shirt): 2/15 correct (13%); latency 5.3s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d78\n ordering in a restaurant: 2/14 correct (12%); latency 5.2s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d79\n meal cleanup after eating: 1/11 correct (10%); latency 5.3s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d79\n reads 10\u201320 sight words: 2/10 correct (18%); latency 5.3s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n sounds out CVC words: 1/14 correct (10%); latency 5.3s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d79\n requesting preferred items using AAC device: 4/11 correct (34%); latency 4.4s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n Self-injurious behavior (SIB): freq 5\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Crying during demand presentation\n- Peer aggression (hitting or pushing peers during group activities)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 81% to 13% across 12 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 48.6%.\n- Trend direction: downward (first session: 81%, last session: 13%).\n- Self-injurious behavior (SIB): mean 3.6/session (early-window mean 2.0 -> late-window mean 4.8).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "963373482b529468", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Self-injurious behavior (SIB)": "attention"}, "escalation_level": 4, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "adolescent", "n_sessions": 12, "n_programs": 6, "n_behaviors": 1, "behavior_ids": ["sib"], "behavior_functions": ["attention"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "44149"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: sorts by multiple attributes simultaneously\nCurriculum: Visual Perceptual Skills & Matching-to-Sample L3\nLearner: School-Age Learner\nMastery Status: Approaching mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: sorts by multiple attributes simultaneously\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L3\n- Learner: School-Age Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: scissors, napkin, block\nDistractor stimuli: sock, ball, backpack, glue, jacket\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "4e0130eb311b49fb", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L3", "learner_profile": "school_age", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "sorts by multiple attributes simultaneously", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "5667"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: tacts colors of objects\nCurriculum: Tact L2\nLearner: Early Learner\nMastery Status: Generalization phase\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts colors of objects\n- Curriculum: Tact L2\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What color?\"\nVariations: \"What color is this?\"; \"Tell me the color\"\nPresentation: Present a single-color object and ask while pointing to it.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: pink, black, green\nDistractor stimuli: brown, purple, white, orange\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "28293e5b40be667e", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L2", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts colors of objects", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "vr3", "error_correction": "backstep", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "87673"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: maintains friendships over time\nCurriculum: Social Behavior & Social Play L3\nLearner: School-Age Learner\nMastery Status: Emerging\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: maintains friendships over time\n- Curriculum: Social Behavior & Social Play L3\n- Learner: School-Age Learner\n- Current mastery: Emerging\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: shared snack.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's shared snack routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the emerging stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "70c3671e3d3a2db7", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L3", "learner_profile": "school_age", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "maintains friendships over time", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "46838"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1511\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Echoic + Mand + Reading + Tact + Tolerating Denied Access\nDate range: Sessions 1\u20138 across 16 days (2026-08-14 to 2026-08-30)\n\nACCELERATION PROGRAMS\n1. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n2. sounds out CVC words (Reading)\n Method: DTT\n3. tacts colors of objects (Tact)\n Method: DTT\n4. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n5. reads 10\u201320 sight words (Reading)\n Method: DTT\n6. echoes 2-word phrases (Echoic)\n Method: DTT variant\n\nDECELERATION TARGETS\n1. Fecal smearing (scatolia) \u2014 function hypothesized: attention\n2. Tantrum \u2014 function hypothesized: tangible\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-14 \u2014 43 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 5/8 correct (65%); latency 2.8s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n sounds out CVC words: 7/11 correct (62%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n tacts colors of objects: 8/12 correct (68%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d710\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/12 correct (56%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d76\n reads 10\u201320 sight words: 6/9 correct (63%); latency 3.0s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d75\n echoes 2-word phrases: 7/12 correct (62%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d711\n Fecal smearing (scatolia): attempts 3 (1 intercepted \u2014 staff redirected before smearing; 2 completed \u2014 feces transferred to skin, clothing, or surface)\n Tantrum: freq 2, duration 8m total\n\nSession 2 \u2014 2026-08-16 \u2014 43 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/13 correct (61%); latency 3.3s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d76\n sounds out CVC words: 5/9 correct (59%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n tacts colors of objects: 6/8 correct (70%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/9 correct (50%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n reads 10\u201320 sight words: 7/10 correct (66%); latency 3.0s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d77\n echoes 2-word phrases: 7/12 correct (58%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d78\n Fecal smearing (scatolia): attempts 3 (2 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n Tantrum: freq 2, duration 6m total\n\nSession 3 \u2014 2026-08-18 \u2014 43 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 7/11 correct (63%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n sounds out CVC words: 9/15 correct (59%); latency 3.5s; prompts FP\u00d75, PP\u00d72, G\u00d74, I\u00d74\n tacts colors of objects: 10/14 correct (71%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/14 correct (55%); latency 3.6s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d79\n reads 10\u201320 sight words: 8/11 correct (69%); latency 2.8s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d79\n echoes 2-word phrases: 5/9 correct (56%); latency 3.7s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n Fecal smearing (scatolia): attempts 8 (5 intercepted \u2014 staff redirected before smearing; 3 completed \u2014 feces transferred to skin, clothing, or surface)\n Tantrum: freq 8, duration 24m total\n\nSession 4 \u2014 2026-08-20 \u2014 43 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 7/11 correct (64%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n sounds out CVC words: 6/10 correct (65%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d77\n tacts colors of objects: 7/9 correct (74%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/13 correct (56%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d710\n reads 10\u201320 sight words: 6/8 correct (70%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n echoes 2-word phrases: 6/11 correct (58%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n Fecal smearing (scatolia): attempts 8 (4 intercepted \u2014 staff redirected before smearing; 4 completed \u2014 feces transferred to skin, clothing, or surface)\n Tantrum: freq 7, duration 35m total\n\nSession 5 \u2014 2026-08-22 \u2014 43 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 7/10 correct (69%); latency 2.8s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d75\n sounds out CVC words: 10/14 correct (68%); latency 3.2s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n tacts colors of objects: 9/12 correct (77%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/9 correct (59%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d75\n reads 10\u201320 sight words: 10/15 correct (65%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d711\n echoes 2-word phrases: 5/8 correct (61%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n Fecal smearing (scatolia): attempts 3 (1 intercepted \u2014 staff redirected before smearing; 2 completed \u2014 feces transferred to skin, clothing, or surface)\n Tantrum: freq 3, duration 12m total\n\nSession 6 \u2014 2026-08-24 \u2014 43 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 7/11 correct (66%); latency 3.0s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d77\n sounds out CVC words: 10/15 correct (68%); latency 3.0s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d79\n tacts colors of objects: 10/14 correct (71%); latency 2.7s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/13 correct (59%); latency 3.3s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d710\n reads 10\u201320 sight words: 6/8 correct (70%); latency 2.6s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n echoes 2-word phrases: 8/14 correct (56%); latency 3.7s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n Fecal smearing (scatolia): attempts 3 (1 intercepted \u2014 staff redirected before smearing; 2 completed \u2014 feces transferred to skin, clothing, or surface)\n Tantrum: freq 3, duration 6m total\n\nSession 7 \u2014 2026-08-26 \u2014 43 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 10/14 correct (71%); latency 2.6s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d76\n sounds out CVC words: 8/11 correct (73%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n tacts colors of objects: 11/14 correct (75%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/11 correct (71%); latency 3.0s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d73\n reads 10\u201320 sight words: 10/14 correct (69%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d711\n echoes 2-word phrases: 8/14 correct (56%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d75\n Fecal smearing (scatolia): attempts 2 (1 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n Tantrum: freq 2, duration 10m total\n\nSession 8 \u2014 2026-08-28 \u2014 43 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/12 correct (65%); latency 2.8s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d72\n sounds out CVC words: 12/15 correct (78%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d79\n tacts colors of objects: 12/14 correct (84%); latency 2.5s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 10/15 correct (70%); latency 2.8s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d79\n reads 10\u201320 sight words: 7/10 correct (73%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n echoes 2-word phrases: 6/11 correct (54%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n Fecal smearing (scatolia): attempts 3 (2 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n Tantrum: freq 3, duration 6m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Crying during demand presentation\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Increased response latency (3\u20135\u00d7 baseline)\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nFecal smearing (scatolia): attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\nTantrum: tangible\n Evidence: behavior occurs when preferred items are restricted and is followed by access to the item.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n### Crisis plan\n- If problem-behavior intensity or topography exceeds the learner's baseline safety threshold (SIB causing tissue damage, aggression causing injury, imminent elopement into hazard): pause the extinction procedure and implement the facility's tiered crisis-prevention protocol (e.g., Safety-Care, CPI, or equivalent).\n- De-escalation and environmental safety first; physical intervention is last resort and only by staff currently certified in the facility's framework. Least-restrictive option appropriate to the risk level applies at every step. Physical intervention is used only when specifically authorized for this learner in the BIP \u2014 contraindications (medical, developmental, trauma history) may restrict the procedures available, in which case the plan is de-escalation + environmental safety + supervisor contact only.\n- Contact the supervising BCBA immediately; do not resume the extinction procedure without BCBA review. Document duration, intensity, antecedent, staff response, and post-incident state.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 65.5%.\n- Trend direction: downward (first session: 65%, last session: 65%).\n- Fecal smearing (scatolia): mean 4.1/session (early-window mean 3.0 -> late-window mean 2.5).\n- Tantrum: mean 3.8/session (early-window mean 2.0 -> late-window mean 2.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "af653837865a040f", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Fecal smearing (scatolia)": "attention", "Tantrum": "tangible"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "early", "n_sessions": 8, "n_programs": 6, "n_behaviors": 2, "behavior_ids": ["fecal_smearing", "tantrum"], "behavior_functions": ["attention", "tangible"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "89331"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6823\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Mand + Motor Imitation + Reading + Tact + Tolerating Denied Access\nDate range: Sessions 1\u201310 across 20 days (2026-10-07 to 2026-10-27)\n\nACCELERATION PROGRAMS\n1. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n2. reads 10\u201320 sight words (Reading)\n Method: DTT\n3. tacts common objects (Tact)\n Method: DTT\n4. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n5. imitates 3-step motor sequences (Motor Imitation)\n Method: DTT variant\n6. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-07 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 5/15 correct (33%); latency 4.5s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d78\n reads 10\u201320 sight words: 5/14 correct (39%); latency 4.3s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d74\n tacts common objects: 4/8 correct (45%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 5/13 correct (39%); latency 4.1s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d78\n imitates 3-step motor sequences: 5/14 correct (38%); latency 4.5s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d713\n follows 1-step motor instructions: 4/11 correct (37%); latency 4.2s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n\nSession 2 \u2014 2026-10-09 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 6/14 correct (43%); latency 4.2s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n reads 10\u201320 sight words: 4/8 correct (48%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n tacts common objects: 7/13 correct (52%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d79\n requesting a break ('break please' or AAC 'I need a break'): 6/14 correct (46%); latency 4.1s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d77\n imitates 3-step motor sequences: 6/15 correct (41%); latency 4.4s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d77\n follows 1-step motor instructions: 6/13 correct (43%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d77\n\nSession 3 \u2014 2026-10-11 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 6/15 correct (43%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d75, I\u00d79\n reads 10\u201320 sight words: 6/11 correct (53%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n tacts common objects: 5/9 correct (54%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 6/11 correct (56%); latency 3.5s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n imitates 3-step motor sequences: 5/13 correct (41%); latency 4.5s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d79\n follows 1-step motor instructions: 5/11 correct (41%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n\nSession 4 \u2014 2026-10-13 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 4/8 correct (55%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n reads 10\u201320 sight words: 5/8 correct (58%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n tacts common objects: 9/15 correct (61%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d713\n requesting a break ('break please' or AAC 'I need a break'): 6/10 correct (58%); latency 3.6s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n imitates 3-step motor sequences: 4/8 correct (51%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n follows 1-step motor instructions: 5/10 correct (51%); latency 3.8s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n\nSession 5 \u2014 2026-10-15 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 6/11 correct (58%); latency 3.6s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d75\n reads 10\u201320 sight words: 7/11 correct (59%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n tacts common objects: 7/10 correct (74%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n requesting a break ('break please' or AAC 'I need a break'): 6/10 correct (65%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d76\n imitates 3-step motor sequences: 4/8 correct (54%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n follows 1-step motor instructions: 8/14 correct (56%); latency 3.7s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d79\n\nSession 6 \u2014 2026-10-17 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 7/11 correct (65%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d710\n reads 10\u201320 sight words: 9/14 correct (67%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d710\n tacts common objects: 7/9 correct (78%); latency 2.2s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d72\n requesting a break ('break please' or AAC 'I need a break'): 8/12 correct (68%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d78\n imitates 3-step motor sequences: 4/8 correct (56%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n follows 1-step motor instructions: 6/10 correct (58%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n\nSession 7 \u2014 2026-10-19 \u2014 IOA SESSION \u2014 2 observers\n wait calmly when access to preferred item is denied: 82% (primary); IOA 72% agreement\n reads 10\u201320 sight words: 72% (primary); IOA 72% agreement\n tacts common objects: 87% (primary); IOA 72% agreement\n requesting a break ('break please' or AAC 'I need a break'): 70% (primary); IOA 72% agreement\n imitates 3-step motor sequences: 66% (primary); IOA 72% agreement\n follows 1-step motor instructions: 60% (primary); IOA 72% agreement\n\nSession 8 \u2014 2026-10-21 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 10/11 correct (87%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n reads 10\u201320 sight words: 8/12 correct (68%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d710\n tacts common objects: 11/13 correct (88%); latency 2.1s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 7/9 correct (79%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n imitates 3-step motor sequences: 9/12 correct (73%); latency 2.5s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d72\n follows 1-step motor instructions: 8/11 correct (73%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n\nSession 9 \u2014 2026-10-23 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 13/14 correct (91%); latency 1.7s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d710\n reads 10\u201320 sight words: 11/14 correct (75%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d77\n tacts common objects: 8/8 correct (95%); latency 1.9s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 10/13 correct (80%); latency 2.5s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d78\n imitates 3-step motor sequences: 8/11 correct (75%); latency 2.4s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d74\n follows 1-step motor instructions: 6/8 correct (79%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n\nSession 10 \u2014 2026-10-25 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 11/12 correct (95%); latency 1.6s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d74\n reads 10\u201320 sight words: 8/10 correct (77%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n tacts common objects: 13/14 correct (95%); latency 1.7s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n requesting a break ('break please' or AAC 'I need a break'): 10/12 correct (85%); latency 1.9s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d78\n imitates 3-step motor sequences: 7/9 correct (80%); latency 2.3s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n follows 1-step motor instructions: 9/12 correct (75%); latency 2.7s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Reaching for materials proactively\n- Appropriate sitting posture maintained\n- Smiling during reinforcement delivery\n- Eye contact maintained throughout trials"}, {"role": "assistant", "content": "## Clinical Concerns\n- Steady improvement: accuracy rose from 33% to 95% across 10 sessions.\n- No clinical concerns at this time; mastery criteria should be reachable within a few additional sessions.\n\n## Pattern Classification\nmastery_progression\n\nAccuracy is ascending cleanly across sessions with no interfering behaviors, consistent with a mastery-progression trajectory.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Continue current teaching procedure \u2014 it is effective for this learner.\n- Maintain current stimulus arrangement; begin planning next skill in sequence.\n\n### Consequence strategies\n- Begin thinning reinforcement from CRF to FR-2 as accuracy stabilizes above 85%.\n- Continue differential reinforcement for independent responses.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nhigh\n\nPattern is well-supported: 10 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 65.2%.\n- Trend direction: upward (first session: 33%, last session: 95%).\n- IOA data: 72% agreement on IOA session \u2014 below threshold."}], "meta": {"task_type": "session_interpretation", "example_id": "681c4cb017f3a621", "gold_labels": {"pattern_class": "mastery_progression", "behavior_functions": {}, "escalation_level": 1, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "mastery_progression", "learner_profile": "early", "n_sessions": 10, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "15583"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5982\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Listener Responding + Mand + Reading\nDate range: Sessions 1\u20138 across 16 days (2026-10-05 to 2026-10-21)\n\nACCELERATION PROGRAMS\n1. selects items by feature (Listener Responding)\n Method: DTT\n2. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n3. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n4. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n5. sounds out CVC words (Reading)\n Method: DTT\n\nDECELERATION TARGETS\n1. Elopement \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-05 \u2014 37 min \u2014 1 observer\n selects items by feature: 7/10 correct (68%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d74\n answers WH-questions about familiar topics: 7/10 correct (72%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d72\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 12/15 correct (83%); latency 2.3s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d710\n requesting a break ('break please' or AAC 'I need a break'): 12/14 correct (84%); latency 2.4s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d76\n sounds out CVC words: 10/13 correct (80%); latency 2.3s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d72\n Elopement: freq 3\n\nSession 2 \u2014 2026-10-07 \u2014 37 min \u2014 1 observer\n selects items by feature: 9/13 correct (69%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d75\n answers WH-questions about familiar topics: 9/14 correct (68%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/12 correct (73%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 7/10 correct (74%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n sounds out CVC words: 9/12 correct (75%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d710\n Elopement: freq 2\n\nSession 3 \u2014 2026-10-09 \u2014 37 min \u2014 1 observer\n selects items by feature: 7/11 correct (65%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n answers WH-questions about familiar topics: 9/14 correct (64%); latency 3.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d710\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/11 correct (67%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d711\n requesting a break ('break please' or AAC 'I need a break'): 6/9 correct (70%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n sounds out CVC words: 6/8 correct (79%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n Elopement: freq 3\n\nSession 4 \u2014 2026-10-11 \u2014 37 min \u2014 1 observer\n selects items by feature: 8/13 correct (62%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n answers WH-questions about familiar topics: 6/9 correct (66%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/14 correct (62%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 9/14 correct (62%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d710\n sounds out CVC words: 8/11 correct (70%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d79\n Elopement: freq 5\n\nSession 5 \u2014 2026-10-13 \u2014 37 min \u2014 1 observer\n selects items by feature: 4/9 correct (48%); latency 3.8s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d75\n answers WH-questions about familiar topics: 5/8 correct (57%); latency 3.5s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/12 correct (60%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d77\n requesting a break ('break please' or AAC 'I need a break'): 5/10 correct (52%); latency 3.5s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n sounds out CVC words: 9/14 correct (64%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d710\n Elopement: freq 6\n\nSession 6 \u2014 2026-10-15 \u2014 37 min \u2014 1 observer\n selects items by feature: 7/14 correct (51%); latency 3.8s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d710\n answers WH-questions about familiar topics: 5/9 correct (52%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/15 correct (52%); latency 3.8s; prompts FP\u00d73, PP\u00d75, G\u00d74, I\u00d73\n requesting a break ('break please' or AAC 'I need a break'): 6/12 correct (54%); latency 3.7s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d76\n sounds out CVC words: 5/9 correct (59%); latency 3.5s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n Elopement: freq 6\n\nSession 7 \u2014 2026-10-17 \u2014 37 min \u2014 1 observer\n selects items by feature: 3/8 correct (40%); latency 4.3s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n answers WH-questions about familiar topics: 5/10 correct (47%); latency 4.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/15 correct (43%); latency 4.3s; prompts FP\u00d75, PP\u00d70, G\u00d75, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 5/12 correct (40%); latency 4.5s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d712\n sounds out CVC words: 7/13 correct (54%); latency 3.3s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d73\n Elopement: freq 6\n\nSession 8 \u2014 2026-10-19 \u2014 37 min \u2014 1 observer\n selects items by feature: 5/11 correct (43%); latency 4.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n answers WH-questions about familiar topics: 4/10 correct (43%); latency 3.8s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/13 correct (44%); latency 4.2s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 4/11 correct (32%); latency 4.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n sounds out CVC words: 5/10 correct (49%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d78\n Elopement: freq 6\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Crying during demand presentation\n- Vocal refusal ('no', 'I don't want to')\n- Pushing materials away from the work area\n- Increased response latency (3\u20135\u00d7 baseline)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (68% -> 43%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nElopement: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 55.8%.\n- Trend direction: downward (first session: 68%, last session: 43%).\n- Elopement: mean 4.6/session (early-window mean 2.5 -> late-window mean 6.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "28555857785d8a78", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Elopement": "escape"}, "escalation_level": 4, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "early", "n_sessions": 8, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["elopement"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "35802"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5338\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Social Behavior + Writing\nDate range: Sessions 1\u20139 across 18 days (2026-08-05 to 2026-08-23)\n\nACCELERATION PROGRAMS\n1. copies simple words from model (Writing)\n Method: DTT\n2. identifies numerals 1\u201320 (Math)\n Method: DTT\n3. takes turns during structured activities (Social Behavior)\n Method: PRT\n4. requesting preferred items using AAC device (e.g., \"I want cookie please\") (Mand)\n Method: NET\n5. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Aggression \u2014 function hypothesized: tangible\n2. Non-compliance \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-05 \u2014 54 min \u2014 1 observer\n copies simple words from model: 5/8 correct (58%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n identifies numerals 1\u201320: 5/8 correct (68%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n takes turns during structured activities: 7/14 correct (52%); latency 3.8s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d79\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/12 correct (61%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/8 correct (60%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n Aggression: freq 2\n Non-compliance: freq 2\n\nSession 2 \u2014 2026-08-07 \u2014 54 min \u2014 1 observer\n copies simple words from model: 5/9 correct (59%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n identifies numerals 1\u201320: 10/14 correct (69%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d75\n takes turns during structured activities: 6/11 correct (53%); latency 3.8s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/12 correct (59%); latency 3.2s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/11 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n Aggression: freq 1\n Non-compliance: freq 2\n\nSession 3 \u2014 2026-08-09 \u2014 54 min \u2014 1 observer\n copies simple words from model: 7/11 correct (61%); latency 3.3s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n identifies numerals 1\u201320: 10/13 correct (75%); latency 2.7s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d72\n takes turns during structured activities: 6/11 correct (51%); latency 4.0s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 6/10 correct (65%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/9 correct (64%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n Aggression: freq 4\n Non-compliance: freq 9\n\nSession 4 \u2014 2026-08-11 \u2014 54 min \u2014 1 observer\n copies simple words from model: 6/10 correct (56%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d74\n identifies numerals 1\u201320: 8/12 correct (70%); latency 2.9s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d76\n takes turns during structured activities: 6/10 correct (59%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 9/14 correct (63%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/10 correct (60%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d77\n Aggression: freq 4\n Non-compliance: freq 9\n\nSession 5 \u2014 2026-08-13 \u2014 54 min \u2014 1 observer\n copies simple words from model: 8/13 correct (61%); latency 3.2s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d74\n identifies numerals 1\u201320: 9/13 correct (72%); latency 2.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d77\n takes turns during structured activities: 9/15 correct (57%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d710\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/11 correct (66%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/10 correct (64%); latency 3.2s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n Aggression: freq 1\n Non-compliance: freq 4\n\nSession 6 \u2014 2026-08-15 \u2014 54 min \u2014 1 observer\n copies simple words from model: 10/15 correct (67%); latency 3.1s; prompts FP\u00d74, PP\u00d71, G\u00d75, I\u00d75\n identifies numerals 1\u201320: 9/12 correct (78%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d79\n takes turns during structured activities: 8/14 correct (54%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 8/12 correct (67%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/13 correct (65%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d78\n Aggression: freq 2\n Non-compliance: freq 3\n\nSession 7 \u2014 2026-08-17 \u2014 54 min \u2014 1 observer\n copies simple words from model: 7/11 correct (65%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d711\n identifies numerals 1\u201320: 11/15 correct (71%); latency 3.0s; prompts FP\u00d75, PP\u00d72, G\u00d72, I\u00d76\n takes turns during structured activities: 7/13 correct (58%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d79\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 10/14 correct (70%); latency 2.9s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/12 correct (69%); latency 2.7s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d73\n Aggression: freq 1\n Non-compliance: freq 2\n\nSession 8 \u2014 2026-08-19 \u2014 54 min \u2014 1 observer\n copies simple words from model: 6/8 correct (72%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n identifies numerals 1\u201320: 6/9 correct (71%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d72\n takes turns during structured activities: 9/14 correct (62%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d712\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 11/15 correct (72%); latency 2.9s; prompts FP\u00d75, PP\u00d70, G\u00d70, I\u00d710\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/10 correct (68%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d76\n Aggression: freq 2\n Non-compliance: freq 3\n\nSession 9 \u2014 2026-08-21 \u2014 54 min \u2014 1 observer\n copies simple words from model: 7/10 correct (69%); latency 3.1s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n identifies numerals 1\u201320: 9/12 correct (77%); latency 2.7s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d77\n takes turns during structured activities: 7/12 correct (60%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d78\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 6/8 correct (70%); latency 2.9s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/8 correct (65%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n Aggression: freq 1\n Non-compliance: freq 3\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n- Peer aggression (hitting or pushing peers during group activities)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nAggression: tangible\n Evidence: behavior occurs when preferred items are restricted and is followed by access to the item.\nNon-compliance: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n### Crisis plan\n- If problem-behavior intensity or topography exceeds the learner's baseline safety threshold (SIB causing tissue damage, aggression causing injury, imminent elopement into hazard): pause the extinction procedure and implement the facility's tiered crisis-prevention protocol (e.g., Safety-Care, CPI, or equivalent).\n- De-escalation and environmental safety first; physical intervention is last resort and only by staff currently certified in the facility's framework. Least-restrictive option appropriate to the risk level applies at every step. Physical intervention is used only when specifically authorized for this learner in the BIP \u2014 contraindications (medical, developmental, trauma history) may restrict the procedures available, in which case the plan is de-escalation + environmental safety + supervisor contact only.\n- Contact the supervising BCBA immediately; do not resume the extinction procedure without BCBA review. Document duration, intensity, antecedent, staff response, and post-incident state.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 63.0%.\n- Trend direction: upward (first session: 58%, last session: 69%).\n- Aggression: mean 2.0/session (early-window mean 2.3 -> late-window mean 1.3).\n- Non-compliance: mean 4.1/session (early-window mean 4.3 -> late-window mean 2.7).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "9d3b3b903243d101", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Aggression": "tangible", "Non-compliance": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "school_age", "n_sessions": 9, "n_programs": 5, "n_behaviors": 2, "behavior_ids": ["aggression", "non_compliance"], "behavior_functions": ["tangible", "escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "89484"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: responds to own name\nCurriculum: Social Behavior & Social Play L1\nLearner Level: Early Learner\nBaseline: Mastered at current level\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: responds to own name\n- Curriculum: Social Behavior & Social Play L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: circle time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's circle time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "0ee3cb6bf7eb71a4", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "responds to own name", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "87353"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: selects items by function (What do you drink from?)\nCurriculum: LRFFC L1\nLearner: Early Learner\nMastery Status: Near mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by function (What do you drink from?)\n- Curriculum: LRFFC L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: ball, napkin, brush\nDistractor stimuli: glue, phone\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "e75c0e20c67cd9a1", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by function (What do you drink from?)", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "fr2", "error_correction": "backstep", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "60118"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: spontaneously tells stories or narratives\nCurriculum: Spontaneous Vocal Behavior L3\nLearner: School-Age Learner\nMastery Status: Emerging\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously tells stories or narratives\n- Curriculum: Spontaneous Vocal Behavior L3\n- Learner: School-Age Learner\n- Current mastery: Emerging\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: morning greeting.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's morning greeting routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Verbal fill-in\nDeliver a partial phrase and pause; learner completes the vocal response.\nCurrent prompt level: At the emerging stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nAverage rate of \u2265 3 spontaneous responses per 30-minute session across 3 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "9207dde2f9f1ddb0", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L3", "learner_profile": "school_age", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously tells stories or narratives", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "verbal_fill_in", "mastery_criterion": "mc_spontaneous_rate"}, "teacher_model": null, "seed_tag": "75835"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4656\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Reading + Self-Care + Writing\nDate range: Sessions 1\u201310 across 20 days (2026-06-10 to 2026-06-30)\n\nACCELERATION PROGRAMS\n1. sounds out CVC words (Reading)\n Method: DTT\n2. copies simple words from model (Writing)\n Method: DTT\n3. identifying community safety signs (Community)\n Method: DTT\n4. tolerating tooth brushing by caregiver (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-10 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 7/9 correct (80%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d74\n copies simple words from model: 8/10 correct (82%); latency 2.1s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d72\n identifying community safety signs: 11/14 correct (79%); latency 2.4s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d75\n tolerating tooth brushing by caregiver: 9/13 correct (71%); latency 3.0s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d74\n Self-injurious behavior (SIB): freq 2\n\nSession 2 \u2014 2026-06-12 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 9/12 correct (77%); latency 2.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n copies simple words from model: 9/11 correct (81%); latency 2.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d77\n identifying community safety signs: 9/11 correct (79%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n tolerating tooth brushing by caregiver: 10/15 correct (69%); latency 3.0s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d76\n Self-injurious behavior (SIB): freq 3\n\nSession 3 \u2014 2026-06-14 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 9/11 correct (80%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d74\n copies simple words from model: 12/14 correct (84%); latency 2.2s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d73\n identifying community safety signs: 10/12 correct (84%); latency 2.1s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d72\n tolerating tooth brushing by caregiver: 7/11 correct (68%); latency 2.8s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n Self-injurious behavior (SIB): freq 2\n\nSession 4 \u2014 2026-06-16 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 6/13 correct (47%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n copies simple words from model: 5/11 correct (43%); latency 4.2s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n identifying community safety signs: 5/10 correct (45%); latency 3.8s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n tolerating tooth brushing by caregiver: 5/14 correct (39%); latency 4.4s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d75\n Self-injurious behavior (SIB): freq 2\n\nSession 5 \u2014 2026-06-18 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 5/11 correct (49%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n copies simple words from model: 6/13 correct (44%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d74\n identifying community safety signs: 5/13 correct (42%); latency 4.3s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d79\n tolerating tooth brushing by caregiver: 5/12 correct (38%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d78\n Self-injurious behavior (SIB): freq 2\n\nSession 6 \u2014 2026-06-20 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 6/11 correct (50%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d79\n copies simple words from model: 6/14 correct (40%); latency 4.3s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d712\n identifying community safety signs: 3/8 correct (42%); latency 3.8s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n tolerating tooth brushing by caregiver: 4/9 correct (39%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d79\n Self-injurious behavior (SIB): freq 3\n\nSession 7 \u2014 2026-06-22 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 7/13 correct (55%); latency 3.8s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n copies simple words from model: 7/15 correct (45%); latency 4.1s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d710\n identifying community safety signs: 4/8 correct (45%); latency 3.8s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n tolerating tooth brushing by caregiver: 4/9 correct (44%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n Self-injurious behavior (SIB): freq 3\n\nSession 8 \u2014 2026-06-24 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 9/15 correct (60%); latency 3.3s; prompts FP\u00d75, PP\u00d72, G\u00d72, I\u00d76\n copies simple words from model: 7/13 correct (51%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d74\n identifying community safety signs: 6/13 correct (48%); latency 4.0s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d79\n tolerating tooth brushing by caregiver: 7/13 correct (54%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d75\n Self-injurious behavior (SIB): freq 2\n ABC (self-injurious behavior (sib)): A = quiet unstructured moment between trials; B = engaged in hand-flapping; C = no social consequence; self-terminated after 30s\n\nSession 9 \u2014 2026-06-26 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 8/12 correct (68%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d73\n copies simple words from model: 5/8 correct (56%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n identifying community safety signs: 7/13 correct (57%); latency 3.7s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n tolerating tooth brushing by caregiver: 5/8 correct (64%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n Self-injurious behavior (SIB): freq 2\n ABC (self-injurious behavior (sib)): A = waiting in line transition; B = mouthed own hand; C = staff redirected to task materials\n\nSession 10 \u2014 2026-06-28 \u2014 32 min \u2014 1 observer\n sounds out CVC words: 9/11 correct (77%); latency 2.3s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n copies simple words from model: 7/11 correct (65%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n identifying community safety signs: 5/9 correct (61%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d77\n tolerating tooth brushing by caregiver: 8/11 correct (71%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n Self-injurious behavior (SIB): freq 2\n ABC (self-injurious behavior (sib)): A = waiting in line transition; B = mouthed own hand; C = staff redirected to task materials\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Echolalic responding (repeating SD rather than answering)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): automatic\n Evidence: ABC events in the log support the automatic function; behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 64.3%.\n- Trend direction: downward (first session: 80%, last session: 77%).\n- Self-injurious behavior (SIB): mean 2.3/session (early-window mean 2.3 -> late-window mean 2.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "d4ab433eabbf7259", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {"Self-injurious behavior (SIB)": "automatic"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "adolescent", "n_sessions": 10, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["sib"], "behavior_functions": ["automatic"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "76861"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: tacts common animals\nCurriculum: Tact L1\nLearner Level: Early Learner\nBaseline: Generalization phase\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts common animals\n- Curriculum: Tact L1\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What animal is this?\"\nVariations: \"What is this?\"; \"Name this animal\"\nPresentation: Present an animal picture card and ask while pointing.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: bear, cow, frog\nDistractor stimuli: duck, dog\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nToken economy \u2014 Tokens delivered per correct response; exchanged at session end for a back-up reinforcer appropriate to the learner (for children: candy, cookies, brief leisure-time access, preferred activity, screen time, or a favorite sensory item). Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "ed95cdbf660ddf42", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L1", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts common animals", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "four_step", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "15203"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5464\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math\nDate range: Sessions 1\u201310 across 20 days (2026-06-24 to 2026-07-14)\n\nACCELERATION PROGRAMS\n1. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n2. single-word requests for preferred items (Mand)\n Method: NET\n3. counts objects 1\u201320 (Math)\n Method: DTT\n4. requesting preferred items using a full sentence (Mand)\n Method: NET\n5. identifies numerals 1\u201320 (Math)\n Method: DTT\n6. requesting a break during non-preferred tasks (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Toileting accident (urine or bowel) \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-24 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/10 correct (39%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n single-word requests for preferred items: 3/10 correct (33%); latency 4.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n counts objects 1\u201320: 3/8 correct (31%); latency 4.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n requesting preferred items using a full sentence: 5/11 correct (44%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d75\n identifies numerals 1\u201320: 3/9 correct (30%); latency 4.6s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n requesting a break during non-preferred tasks: 4/11 correct (41%); latency 4.2s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n Toileting accident (urine or bowel): urine: 3 in-toilet / 1 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 2 \u2014 2026-06-26 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/12 correct (44%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d77\n single-word requests for preferred items: 3/9 correct (36%); latency 4.4s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n counts objects 1\u201320: 6/15 correct (42%); latency 4.1s; prompts FP\u00d75, PP\u00d75, G\u00d72, I\u00d73\n requesting preferred items using a full sentence: 6/12 correct (51%); latency 3.9s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d75\n identifies numerals 1\u201320: 4/9 correct (42%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d75\n requesting a break during non-preferred tasks: 6/13 correct (47%); latency 3.7s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d75\n Toileting accident (urine or bowel): urine: 4 in-toilet / 1 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 3 \u2014 2026-06-28 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/12 correct (49%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d76\n single-word requests for preferred items: 4/11 correct (38%); latency 4.5s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n counts objects 1\u201320: 5/12 correct (42%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d79\n requesting preferred items using a full sentence: 5/8 correct (63%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n identifies numerals 1\u201320: 6/13 correct (44%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d77\n requesting a break during non-preferred tasks: 5/11 correct (48%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d79\n Toileting accident (urine or bowel): urine: 5 in-toilet / 1 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 4 \u2014 2026-06-30 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/14 correct (60%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d77\n single-word requests for preferred items: 5/11 correct (46%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n counts objects 1\u201320: 5/11 correct (50%); latency 3.7s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n requesting preferred items using a full sentence: 8/11 correct (68%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d77\n identifies numerals 1\u201320: 5/11 correct (48%); latency 4.0s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n requesting a break during non-preferred tasks: 8/14 correct (57%); latency 3.2s; prompts FP\u00d70, PP\u00d74, G\u00d72, I\u00d78\n Toileting accident (urine or bowel): urine: 5 in-toilet / 2 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 5 \u2014 2026-07-02 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/11 correct (58%); latency 3.7s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d79\n single-word requests for preferred items: 7/13 correct (57%); latency 3.2s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n counts objects 1\u201320: 6/13 correct (50%); latency 4.0s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d75\n requesting preferred items using a full sentence: 10/14 correct (73%); latency 2.5s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d74\n identifies numerals 1\u201320: 9/15 correct (57%); latency 3.2s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d711\n requesting a break during non-preferred tasks: 5/8 correct (60%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n Toileting accident (urine or bowel): urine: 4 in-toilet / 1 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 6 \u2014 2026-07-04 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/9 correct (65%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n single-word requests for preferred items: 9/15 correct (59%); latency 3.5s; prompts FP\u00d70, PP\u00d74, G\u00d75, I\u00d76\n counts objects 1\u201320: 5/9 correct (51%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n requesting preferred items using a full sentence: 10/13 correct (77%); latency 2.4s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d75\n identifies numerals 1\u201320: 9/14 correct (64%); latency 3.2s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d77\n requesting a break during non-preferred tasks: 8/13 correct (62%); latency 2.9s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d75\n Toileting accident (urine or bowel): urine: 4 in-toilet / 1 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 7 \u2014 2026-07-06 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/12 correct (75%); latency 2.5s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d74\n single-word requests for preferred items: 9/15 correct (61%); latency 3.0s; prompts FP\u00d72, PP\u00d75, G\u00d71, I\u00d77\n counts objects 1\u201320: 8/13 correct (58%); latency 3.4s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d73\n requesting preferred items using a full sentence: 8/10 correct (85%); latency 1.9s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n identifies numerals 1\u201320: 6/9 correct (62%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d77\n requesting a break during non-preferred tasks: 8/11 correct (77%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n Toileting accident (urine or bowel): urine: 3 in-toilet / 1 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 8 \u2014 2026-07-08 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 10/13 correct (80%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d79\n single-word requests for preferred items: 9/14 correct (67%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d78\n counts objects 1\u201320: 6/10 correct (62%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n requesting preferred items using a full sentence: 9/10 correct (92%); latency 2.1s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n identifies numerals 1\u201320: 6/8 correct (75%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n requesting a break during non-preferred tasks: 11/14 correct (76%); latency 2.8s; prompts FP\u00d70, PP\u00d74, G\u00d72, I\u00d78\n Toileting accident (urine or bowel): urine: 2 in-toilet / 1 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 9 \u2014 2026-07-10 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 13/14 correct (93%); latency 1.7s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d79\n single-word requests for preferred items: 6/8 correct (70%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n counts objects 1\u201320: 7/10 correct (69%); latency 2.7s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n requesting preferred items using a full sentence: 10/11 correct (95%); latency 1.8s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n identifies numerals 1\u201320: 6/8 correct (80%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n requesting a break during non-preferred tasks: 11/13 correct (81%); latency 2.1s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d76\n Toileting accident (urine or bowel): urine: 1 in-toilet / 3 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 10 \u2014 2026-07-12 \u2014 54 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 10/10 correct (95%); latency 2.0s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n single-word requests for preferred items: 9/11 correct (82%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n counts objects 1\u201320: 7/9 correct (79%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n requesting preferred items using a full sentence: 11/12 correct (95%); latency 1.7s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d79\n identifies numerals 1\u201320: 8/9 correct (87%); latency 2.3s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n requesting a break during non-preferred tasks: 11/13 correct (86%); latency 2.1s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n Toileting accident (urine or bowel): urine: 3 in-toilet / 2 accidents; BM: 1 in-toilet / 0 accidents\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Eye contact maintained throughout trials\n- Quick response latency (within 2\u20133 seconds)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- Steady improvement: accuracy rose from 39% to 95% across 10 sessions.\n- No clinical concerns at this time; mastery criteria should be reachable within a few additional sessions.\n\n## Pattern Classification\nmastery_progression\n\nAccuracy is ascending cleanly across sessions with no interfering behaviors, consistent with a mastery-progression trajectory.\n\n## Behavior Function Hypothesis\nToileting accident (urine or bowel): automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Continue current teaching procedure \u2014 it is effective for this learner.\n- Maintain current stimulus arrangement; begin planning next skill in sequence.\n\n### Consequence strategies\n- Begin thinning reinforcement from CRF to FR-2 as accuracy stabilizes above 85%.\n- Continue differential reinforcement for independent responses.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 65.8%.\n- Trend direction: upward (first session: 39%, last session: 95%).\n- Toileting accident (urine or bowel): mean 1.5/session (early-window mean 1.0 -> late-window mean 2.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "a9bd3c2f58eee9d8", "gold_labels": {"pattern_class": "mastery_progression", "behavior_functions": {"Toileting accident (urine or bowel)": "automatic"}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "mastery_progression", "learner_profile": "school_age", "n_sessions": 10, "n_programs": 6, "n_behaviors": 1, "behavior_ids": ["toileting_accident"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "68883"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9052\nProfile: Adult Learner (18+ years)\nCurricula: Community + Home Skills + Independent Living + Mand + Vocational\nDate range: Sessions 1\u201311 across 22 days (2026-08-11 to 2026-09-02)\n\nACCELERATION PROGRAMS\n1. using public transportation (Community)\n Method: Task Analysis\n2. managing a budget (Independent Living)\n Method: Task Analysis\n3. simple meal preparation (Home Skills)\n Method: Task Analysis\n4. requesting assistance using AAC device (Mand)\n Method: NET\n5. clocking in at start of shift (Vocational)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-11 \u2014 31 min \u2014 1 observer\n using public transportation: 13/15 correct (88%); latency 2.1s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d75\n managing a budget: 11/15 correct (73%); latency 3.0s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d74\n simple meal preparation: 12/15 correct (78%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d710\n requesting assistance using AAC device: 12/15 correct (81%); latency 2.4s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d710\n clocking in at start of shift: 8/9 correct (86%); latency 2.3s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n Tantrum: freq 3, duration 6m total\n\nSession 2 \u2014 2026-08-13 \u2014 31 min \u2014 1 observer\n using public transportation: 3/14 correct (21%); latency 5.1s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d78\n managing a budget: 6/13 correct (43%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d77\n simple meal preparation: 5/13 correct (35%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d710\n requesting assistance using AAC device: 6/15 correct (43%); latency 4.1s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d712\n clocking in at start of shift: 3/11 correct (30%); latency 4.9s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d75\n Tantrum: freq 3, duration 15m total\n\nSession 3 \u2014 2026-08-15 \u2014 31 min \u2014 1 observer\n using public transportation: 7/8 correct (87%); latency 2.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n managing a budget: 8/10 correct (78%); latency 2.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n simple meal preparation: 8/9 correct (86%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d75\n requesting assistance using AAC device: 12/14 correct (84%); latency 2.4s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d76\n clocking in at start of shift: 10/11 correct (90%); latency 2.1s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n Tantrum: freq 3, duration 6m total\n\nSession 4 \u2014 2026-08-17 \u2014 31 min \u2014 1 observer\n using public transportation: 3/13 correct (23%); latency 4.9s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d77\n managing a budget: 3/10 correct (35%); latency 4.1s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d72\n simple meal preparation: 5/15 correct (33%); latency 4.4s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d77\n requesting assistance using AAC device: 4/9 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d73\n clocking in at start of shift: 4/11 correct (37%); latency 4.0s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n Tantrum: freq 2, duration 4m total\n\nSession 5 \u2014 2026-08-19 \u2014 31 min \u2014 1 observer\n using public transportation: 12/14 correct (85%); latency 2.2s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d76\n managing a budget: 11/15 correct (74%); latency 2.4s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d74\n simple meal preparation: 7/9 correct (80%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d74\n requesting assistance using AAC device: 7/9 correct (80%); latency 2.6s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d76\n clocking in at start of shift: 9/11 correct (83%); latency 2.0s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n Tantrum: freq 2, duration 6m total\n\nSession 6 \u2014 2026-08-21 \u2014 31 min \u2014 1 observer\n using public transportation: 2/9 correct (27%); latency 5.0s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n managing a budget: 6/15 correct (39%); latency 4.1s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d79\n simple meal preparation: 3/9 correct (34%); latency 4.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n requesting assistance using AAC device: 5/13 correct (40%); latency 4.1s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n clocking in at start of shift: 4/12 correct (35%); latency 4.6s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d79\n Tantrum: freq 3, duration 6m total\n\nSession 7 \u2014 2026-08-23 \u2014 31 min \u2014 1 observer\n using public transportation: 7/8 correct (86%); latency 2.0s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n managing a budget: 8/10 correct (79%); latency 2.2s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d79\n simple meal preparation: 9/11 correct (83%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n requesting assistance using AAC device: 10/12 correct (80%); latency 2.5s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d73\n clocking in at start of shift: 7/8 correct (89%); latency 2.3s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n Tantrum: freq 2, duration 4m total\n\nSession 8 \u2014 2026-08-25 \u2014 31 min \u2014 1 observer\n using public transportation: 2/9 correct (21%); latency 5.2s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n managing a budget: 6/14 correct (40%); latency 4.0s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d710\n simple meal preparation: 4/11 correct (33%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n requesting assistance using AAC device: 6/15 correct (43%); latency 4.2s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d711\n clocking in at start of shift: 5/15 correct (35%); latency 4.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d710\n Tantrum: freq 2, duration 8m total\n\nSession 9 \u2014 2026-08-27 \u2014 31 min \u2014 1 observer\n using public transportation: 13/14 correct (95%); latency 1.7s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d73\n managing a budget: 6/8 correct (74%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n simple meal preparation: 7/9 correct (77%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d78\n requesting assistance using AAC device: 10/13 correct (78%); latency 2.3s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d77\n clocking in at start of shift: 8/9 correct (84%); latency 2.2s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n Tantrum: freq 2, duration 10m total\n\nSession 10 \u2014 2026-08-29 \u2014 31 min \u2014 1 observer\n using public transportation: 3/11 correct (24%); latency 4.6s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n managing a budget: 5/13 correct (35%); latency 4.5s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d73\n simple meal preparation: 4/11 correct (32%); latency 4.4s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d79\n requesting assistance using AAC device: 5/12 correct (42%); latency 4.0s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d76\n clocking in at start of shift: 4/11 correct (38%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d78\n Tantrum: freq 3, duration 12m total\n\nSession 11 \u2014 2026-08-31 \u2014 31 min \u2014 1 observer\n using public transportation: 7/8 correct (91%); latency 1.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n managing a budget: 9/12 correct (73%); latency 3.0s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d75\n simple meal preparation: 7/8 correct (83%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n requesting assistance using AAC device: 7/8 correct (82%); latency 2.6s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n clocking in at start of shift: 8/9 correct (89%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d76\n Tantrum: freq 1, duration 3m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Playing with non-task materials\n- Delayed responding (>5 seconds consistently)\n- Leaving seat without permission"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Behavior Function Hypothesis\nTantrum: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 58.9%.\n- Trend direction: upward (first session: 88%, last session: 91%).\n- Tantrum: mean 2.4/session (early-window mean 3.0 -> late-window mean 2.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "e6ba83392341f144", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {"Tantrum": "escape"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "adult", "n_sessions": 11, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["tantrum"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "85192"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-2389\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Home Skills + Mand + Self-Care\nDate range: Sessions 1\u20138 across 16 days (2026-05-06 to 2026-05-22)\n\nACCELERATION PROGRAMS\n1. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n2. requesting preferred items using AAC device (Mand)\n Method: NET\n3. making the bed (Home Skills)\n Method: Task Analysis\n4. tolerating tooth brushing by caregiver (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-06 \u2014 57 min \u2014 1 observer\n dressing (pants, shirt): 5/13 correct (42%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d711\n requesting preferred items using AAC device: 6/12 correct (48%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d76\n making the bed: 7/12 correct (57%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n tolerating tooth brushing by caregiver: 7/15 correct (48%); latency 4.0s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d75\n Self-injurious behavior (SIB): freq 1\n\nSession 2 \u2014 2026-05-08 \u2014 57 min \u2014 1 observer\n dressing (pants, shirt): 7/14 correct (51%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d76\n requesting preferred items using AAC device: 4/9 correct (50%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n making the bed: 5/8 correct (68%); latency 2.8s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n tolerating tooth brushing by caregiver: 6/12 correct (54%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d75\n Self-injurious behavior (SIB): freq 1\n\nSession 3 \u2014 2026-05-10 \u2014 57 min \u2014 1 observer\n dressing (pants, shirt): 6/10 correct (59%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n requesting preferred items using AAC device: 5/9 correct (58%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n making the bed: 7/9 correct (76%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d73\n tolerating tooth brushing by caregiver: 6/9 correct (62%); latency 3.3s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d78\n Self-injurious behavior (SIB): freq 1\n\nSession 4 \u2014 2026-05-12 \u2014 57 min \u2014 1 observer\n dressing (pants, shirt): 10/14 correct (69%); latency 2.6s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d75\n requesting preferred items using AAC device: 9/14 correct (65%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d77\n making the bed: 11/13 correct (84%); latency 2.1s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n tolerating tooth brushing by caregiver: 11/15 correct (71%); latency 2.5s; prompts FP\u00d70, PP\u00d75, G\u00d70, I\u00d710\n Self-injurious behavior (SIB): freq 2\n\nSession 5 \u2014 2026-05-14 \u2014 57 min \u2014 1 observer\n dressing (pants, shirt): 6/8 correct (71%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n requesting preferred items using AAC device: 10/15 correct (68%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d714\n making the bed: 8/10 correct (84%); latency 2.2s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n tolerating tooth brushing by caregiver: 10/13 correct (76%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d710\n Self-injurious behavior (SIB): freq 3\n\nSession 6 \u2014 2026-05-16 \u2014 57 min \u2014 1 observer\n dressing (pants, shirt): 7/10 correct (71%); latency 3.1s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n requesting preferred items using AAC device: 9/13 correct (73%); latency 3.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d77\n making the bed: 8/9 correct (84%); latency 2.3s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n tolerating tooth brushing by caregiver: 11/14 correct (80%); latency 2.4s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n Self-injurious behavior (SIB): freq 3\n\nSession 7 \u2014 2026-05-18 \u2014 57 min \u2014 1 observer\n dressing (pants, shirt): 8/11 correct (71%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n requesting preferred items using AAC device: 10/13 correct (79%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d76\n making the bed: 10/12 correct (84%); latency 2.3s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d79\n tolerating tooth brushing by caregiver: 10/13 correct (80%); latency 2.3s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d75\n Self-injurious behavior (SIB): freq 1\n\nSession 8 \u2014 2026-05-20 \u2014 57 min \u2014 1 observer\n dressing (pants, shirt): 11/15 correct (71%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d710\n requesting preferred items using AAC device: 9/11 correct (83%); latency 2.3s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d75\n making the bed: 7/8 correct (84%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n tolerating tooth brushing by caregiver: 11/14 correct (80%); latency 2.6s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d77\n Self-injurious behavior (SIB): freq 2\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Playing with non-task materials\n- Stereotypic behavior during inter-trial intervals\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 42% at return, recovering to 71%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 62.8%.\n- Trend direction: upward (first session: 42%, last session: 71%).\n- Self-injurious behavior (SIB): mean 1.8/session (early-window mean 1.0 -> late-window mean 1.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "86a1df0db19c4a24", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {"Self-injurious behavior (SIB)": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "adolescent", "n_sessions": 8, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["sib"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "15986"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: tacts colors of objects\nCurriculum: Tact L2\nLearner Level: Early Learner\nBaseline: Generalization phase\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts colors of objects\n- Curriculum: Tact L2\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What color?\"\nVariations: \"What color is this?\"; \"Tell me the color\"\nPresentation: Present a single-color object and ask while pointing to it.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: purple, yellow, blue\nDistractor stimuli: white, brown, green, black\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "cedb4db27b03394d", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L2", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts colors of objects", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "vr3", "error_correction": "backstep", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "38800"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: traces basic shapes (circle, cross)\nCurriculum Reference: Writing L1\nLearner Profile: Early Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: traces basic shapes (circle, cross)\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: square, diamond, oval\nDistractor stimuli: heart, circle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "8d7b775a0f2b2b88", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "traces basic shapes (circle, cross)", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "fr2", "error_correction": "backstep", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "50881"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: copies simple words from model\nCurriculum: Writing L2\nLearner Level: School-Age Learner\nBaseline: Developing\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: copies simple words from model\n- Curriculum: Writing L2\n- Learner: School-Age Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: backpack, crayon, ball\nDistractor stimuli: jacket, block, glue, apple\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "0bcbe1298ea440d0", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L2", "learner_profile": "school_age", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "copies simple words from model", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "36112"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: completing assigned tasks in order\nCurriculum: AFLS Vocational Skills\nLearner: Adult Learner\nMastery Status: Mastered at current level\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: completing assigned tasks in order\n- Curriculum: AFLS Vocational Skills\n- Learner: Adult Learner\n- Current mastery: Mastered at current level\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Review the task list for the shift. <- Learner-taught step (forward chaining starts here)\n2. Gather needed materials for the first task.\n3. Complete the first task to the specified standard.\n4. Mark the first task complete on the list.\n5. Return materials to storage.\n6. Move to the next task on the list and repeat.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the mastered stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed independently with 2 different adults in 2 different settings across 2 consecutive days.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "22881db4ba09fdc7", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "completing assigned tasks in order", "program_type": "independence", "learner_profile": "adult", "mastery_state": "mastered", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "completing assigned tasks in order", "module": "vocational", "mastery_criterion": "mc_generalization", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "51834"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: mands for a break (e.g., \"break please\", AAC \"I need a break\")\nCurriculum Reference: Mand L1\nLearner Profile: Early Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands for a break (e.g., \"break please\", AAC \"I need a break\")\n- Curriculum: Mand L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nPresent a brief non-preferred task or demand at a level the learner can tolerate but may wish to pause. Wait for a request-for-break topography; honor the request immediately on first acquisition (CRF), thin later.\nPrimary natural context: academic period.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's academic period routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: immediate brief escape from the demand (30\u201360 seconds) to a neutral or preferred activity.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "4f67b13403a98c47", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands for a break (e.g., \"break please\", AAC \"I need a break\")", "mo_category": "mand_break", "mo_arrangement": "break_opportunity", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "44373"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: copies all upper-case letters from model\nCurriculum: Writing L2\nLearner Level: Early Learner\nBaseline: Developing\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: copies all upper-case letters from model\n- Curriculum: Writing L2\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: U, Q, Y\nDistractor stimuli: K, A, T, N\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "46e4e7bed0b015a3", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L2", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "copies all upper-case letters from model", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "28081"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: scheduling a medical appointment\nCurriculum: AFLS Independent Living Skills\nLearner: Adult Learner\nMastery Status: Mastered at current level\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: scheduling a medical appointment\n- Curriculum: AFLS Independent Living Skills\n- Learner: Adult Learner\n- Current mastery: Mastered at current level\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Identify the reason for the appointment. <- Learner-taught step (forward chaining starts here)\n2. Locate the provider's contact information.\n3. Call or use the online system.\n4. Provide name, date of birth, and insurance information.\n5. Request an available appointment time.\n6. Confirm the appointment and save it to the calendar.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the mastered stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "73bab6d8fa853146", "gold_labels": {"method": "task_analysis", "domain": "AFLS.independent_living", "skill": "scheduling a medical appointment", "program_type": "independence", "learner_profile": "adult", "mastery_state": "mastered", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "scheduling a medical appointment", "module": "independent_living", "mastery_criterion": "mc_self_initiation", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "68917"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7704\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Mand + Reading + Self-Care + Tolerating Denied Access\nDate range: Sessions 1\u201310 across 20 days (2026-09-23 to 2026-10-13)\n\nACCELERATION PROGRAMS\n1. requesting a break during non-preferred activities (Mand)\n Method: NET\n2. ordering in a restaurant (Community)\n Method: Task Analysis\n3. tolerating haircut (Self-Care)\n Method: Task Analysis\n4. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n5. reads 10\u201320 sight words (Reading)\n Method: DTT\n6. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-23 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 7/9 correct (74%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n ordering in a restaurant: 10/14 correct (75%); latency 2.4s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d79\n tolerating haircut: 10/15 correct (69%); latency 3.0s; prompts FP\u00d74, PP\u00d74, G\u00d75, I\u00d72\n meal cleanup after eating: 8/10 correct (75%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d74\n reads 10\u201320 sight words: 6/10 correct (62%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n wait calmly when access to preferred item is denied: 10/15 correct (65%); latency 3.3s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d76\n\nSession 2 \u2014 2026-09-25 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 6/9 correct (67%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n ordering in a restaurant: 7/9 correct (75%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n tolerating haircut: 9/13 correct (70%); latency 2.8s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d712\n meal cleanup after eating: 7/10 correct (73%); latency 3.0s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n reads 10\u201320 sight words: 6/10 correct (57%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n wait calmly when access to preferred item is denied: 9/13 correct (68%); latency 3.0s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n\nSession 3 \u2014 2026-09-27 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 10/14 correct (70%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d710\n ordering in a restaurant: 9/12 correct (72%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d78\n tolerating haircut: 8/11 correct (75%); latency 2.5s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d75\n meal cleanup after eating: 11/15 correct (74%); latency 2.6s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d77\n reads 10\u201320 sight words: 5/8 correct (65%); latency 2.9s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n wait calmly when access to preferred item is denied: 10/14 correct (73%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d710\n\nSession 4 \u2014 2026-09-29 \u2014 IOA SESSION \u2014 2 observers\n requesting a break during non-preferred activities: 72% (primary); IOA 88% agreement\n ordering in a restaurant: 69% (primary); IOA 88% agreement\n tolerating haircut: 74% (primary); IOA 88% agreement\n meal cleanup after eating: 70% (primary); IOA 88% agreement\n reads 10\u201320 sight words: 60% (primary); IOA 88% agreement\n wait calmly when access to preferred item is denied: 64% (primary); IOA 88% agreement\n\nSession 5 \u2014 2026-10-01 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 4/9 correct (48%); latency 3.7s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n ordering in a restaurant: 7/15 correct (44%); latency 4.1s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d76\n tolerating haircut: 4/8 correct (55%); latency 3.3s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n meal cleanup after eating: 5/8 correct (57%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n reads 10\u201320 sight words: 6/13 correct (43%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d77\n wait calmly when access to preferred item is denied: 3/9 correct (37%); latency 4.6s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d76\n\nSession 6 \u2014 2026-10-03 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 4/9 correct (49%); latency 3.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n ordering in a restaurant: 5/8 correct (57%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n tolerating haircut: 5/9 correct (58%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d78\n meal cleanup after eating: 7/12 correct (61%); latency 3.3s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d75\n reads 10\u201320 sight words: 4/8 correct (51%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n wait calmly when access to preferred item is denied: 5/12 correct (39%); latency 4.3s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d77\n\nSession 7 \u2014 2026-10-05 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 6/11 correct (56%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n ordering in a restaurant: 8/13 correct (60%); latency 3.3s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d78\n tolerating haircut: 9/15 correct (63%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d75, I\u00d75\n meal cleanup after eating: 7/10 correct (71%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n reads 10\u201320 sight words: 6/9 correct (61%); latency 3.1s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n wait calmly when access to preferred item is denied: 6/14 correct (45%); latency 3.7s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d79\n\nSession 8 \u2014 2026-10-07 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 9/14 correct (62%); latency 3.0s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d79\n ordering in a restaurant: 8/11 correct (71%); latency 3.0s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n tolerating haircut: 7/10 correct (69%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d77\n meal cleanup after eating: 6/8 correct (74%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n reads 10\u201320 sight words: 7/11 correct (61%); latency 3.0s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n wait calmly when access to preferred item is denied: 6/12 correct (52%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d77\n\nSession 9 \u2014 2026-10-09 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 5/8 correct (62%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n ordering in a restaurant: 9/13 correct (72%); latency 2.9s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d77\n tolerating haircut: 11/15 correct (70%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d79\n meal cleanup after eating: 6/8 correct (74%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n reads 10\u201320 sight words: 9/14 correct (61%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d711\n wait calmly when access to preferred item is denied: 8/14 correct (54%); latency 3.8s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d72\n\nSession 10 \u2014 2026-10-11 \u2014 46 min \u2014 1 observer\n requesting a break during non-preferred activities: 8/12 correct (69%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d77\n ordering in a restaurant: 10/14 correct (72%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d75\n tolerating haircut: 8/12 correct (70%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d75\n meal cleanup after eating: 7/9 correct (74%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n reads 10\u201320 sight words: 7/11 correct (61%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n wait calmly when access to preferred item is denied: 4/8 correct (55%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Stereotypic behavior during inter-trial intervals\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 10 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 63.0%.\n- Trend direction: downward (first session: 74%, last session: 69%).\n- IOA data: 88% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "e9a943d58300ff67", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "adolescent", "n_sessions": 10, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "61246"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: tacts common actions (running, eating, sleeping)\nCurriculum Reference: Tact L1\nLearner Profile: Early Learner\nCurrent Mastery: Generalization phase\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts common actions (running, eating, sleeping)\n- Curriculum: Tact L1\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What is he doing?\"\nVariations: \"What action?\"; \"What is she doing?\"; \"What is happening here?\"\nPresentation: Present an action picture, video clip, or live demonstration.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: reading, drawing, pouring\nDistractor stimuli: sleeping, eating\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nToken economy \u2014 Tokens delivered per correct response; exchanged at session end for a back-up reinforcer appropriate to the learner (for children: candy, cookies, brief leisure-time access, preferred activity, screen time, or a favorite sensory item). Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "a56463556b4b2305", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L1", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts common actions (running, eating, sleeping)", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "token_economy", "error_correction": "backstep", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "78310"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: points to named body parts\nCurriculum: Listener Responding L1\nLearner: Early Learner\nMastery Status: Developing\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: points to named body parts\n- Curriculum: Listener Responding L1\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: car, spoon, plate\nDistractor stimuli: jacket, ball\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "54d90740f4fe2e24", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L1", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "points to named body parts", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "87673"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: names items in categories when given the category\nCurriculum Reference: Intraverbal L2\nLearner Profile: School-Age Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: names items in categories when given the category\n- Curriculum: Intraverbal L2\n- Learner: School-Age Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: transition conversation.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's transition conversation routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "e7527886bb53d118", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L2", "learner_profile": "school_age", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "names items in categories when given the category", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "time_delay", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "83467"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: mands for missing items needed to complete an activity\nCurriculum: Mand L1\nLearner: Early Learner\nMastery Status: Mastered at current level\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands for missing items needed to complete an activity\n- Curriculum: Mand L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange an activity that requires a specific item to complete, then omit that item from the available materials. Wait for the learner to notice the gap.\nPrimary natural context: art activity.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's art activity routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: the missing item is provided, activity can continue.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "866b3fe3f8e154a9", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands for missing items needed to complete an activity", "mo_category": "mand_missing", "mo_arrangement": "missing_item_completion", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "75835"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3262\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Listener Responding + Mand + Tact + Tolerating Denied Access\nDate range: Sessions 1\u201312 across 24 days (2026-10-07 to 2026-10-31)\n\nACCELERATION PROGRAMS\n1. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n2. tacts common objects (Tact)\n Method: DTT\n3. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n4. tacts colors of objects (Tact)\n Method: DTT\n5. indicating completion ('all done', 'finished') (Mand)\n Method: NET\n6. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-07 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 7/9 correct (82%); latency 2.1s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d75\n tacts common objects: 11/13 correct (83%); latency 2.5s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d73\n answers WH-questions about familiar topics: 6/8 correct (78%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n tacts colors of objects: 9/12 correct (78%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d77\n indicating completion ('all done', 'finished'): 9/11 correct (84%); latency 2.1s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d76\n wait calmly when access to preferred item is denied: 7/8 correct (82%); latency 2.4s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n\nSession 2 \u2014 2026-10-09 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 7/8 correct (81%); latency 2.1s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n tacts common objects: 9/11 correct (84%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n answers WH-questions about familiar topics: 11/14 correct (77%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d76\n tacts colors of objects: 12/15 correct (78%); latency 2.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d79\n indicating completion ('all done', 'finished'): 7/9 correct (78%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n wait calmly when access to preferred item is denied: 7/9 correct (82%); latency 2.3s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n\nSession 3 \u2014 2026-10-11 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 12/14 correct (84%); latency 2.0s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n tacts common objects: 8/9 correct (87%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n answers WH-questions about familiar topics: 11/14 correct (76%); latency 2.6s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d77\n tacts colors of objects: 11/15 correct (74%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d76\n indicating completion ('all done', 'finished'): 10/12 correct (84%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d75\n wait calmly when access to preferred item is denied: 10/12 correct (84%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d75\n\nSession 4 \u2014 2026-10-13 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 12/14 correct (86%); latency 2.2s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n tacts common objects: 9/11 correct (86%); latency 2.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n answers WH-questions about familiar topics: 11/14 correct (79%); latency 2.5s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d78\n tacts colors of objects: 10/13 correct (80%); latency 2.2s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d710\n indicating completion ('all done', 'finished'): 10/13 correct (80%); latency 2.2s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d76\n wait calmly when access to preferred item is denied: 9/11 correct (80%); latency 2.4s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n\nSession 5 \u2014 2026-10-15 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 6/12 correct (52%); latency 3.4s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d70\n tacts common objects: 5/11 correct (44%); latency 4.1s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d711\n answers WH-questions about familiar topics: 4/9 correct (45%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d73\n tacts colors of objects: 4/9 correct (47%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n indicating completion ('all done', 'finished'): 7/14 correct (50%); latency 3.7s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d74\n wait calmly when access to preferred item is denied: 6/11 correct (56%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d78\n\nSession 6 \u2014 2026-10-17 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 8/15 correct (55%); latency 3.7s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d710\n tacts common objects: 6/13 correct (43%); latency 4.2s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d710\n answers WH-questions about familiar topics: 4/9 correct (44%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d76\n tacts colors of objects: 6/13 correct (46%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d710\n indicating completion ('all done', 'finished'): 5/9 correct (54%); latency 3.8s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n wait calmly when access to preferred item is denied: 9/15 correct (57%); latency 3.6s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d710\n\nSession 7 \u2014 2026-10-19 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 5/8 correct (63%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n tacts common objects: 6/13 correct (49%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d76\n answers WH-questions about familiar topics: 5/11 correct (42%); latency 3.8s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n tacts colors of objects: 3/8 correct (41%); latency 4.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n indicating completion ('all done', 'finished'): 5/8 correct (57%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n wait calmly when access to preferred item is denied: 9/15 correct (59%); latency 3.3s; prompts FP\u00d73, PP\u00d75, G\u00d71, I\u00d76\n\nSession 8 \u2014 2026-10-21 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 9/13 correct (66%); latency 2.8s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d73\n tacts common objects: 5/8 correct (56%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n answers WH-questions about familiar topics: 4/9 correct (43%); latency 4.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d77\n tacts colors of objects: 3/8 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n indicating completion ('all done', 'finished'): 6/10 correct (62%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d77\n wait calmly when access to preferred item is denied: 8/12 correct (68%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d76\n\nSession 9 \u2014 2026-10-23 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 8/11 correct (76%); latency 2.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n tacts common objects: 7/10 correct (67%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n answers WH-questions about familiar topics: 6/13 correct (50%); latency 3.5s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n tacts colors of objects: 4/8 correct (45%); latency 3.7s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n indicating completion ('all done', 'finished'): 5/8 correct (67%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n wait calmly when access to preferred item is denied: 9/12 correct (75%); latency 2.8s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d75\n\nSession 10 \u2014 2026-10-25 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 9/11 correct (84%); latency 2.2s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n tacts common objects: 11/15 correct (71%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d711\n answers WH-questions about familiar topics: 5/8 correct (60%); latency 3.2s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n tacts colors of objects: 6/11 correct (51%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n indicating completion ('all done', 'finished'): 10/14 correct (71%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d79\n wait calmly when access to preferred item is denied: 11/13 correct (81%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d78\n\nSession 11 \u2014 2026-10-27 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 8/10 correct (85%); latency 2.1s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d76\n tacts common objects: 11/14 correct (77%); latency 2.6s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d72\n answers WH-questions about familiar topics: 9/13 correct (69%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d75\n tacts colors of objects: 6/12 correct (54%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d77\n indicating completion ('all done', 'finished'): 9/12 correct (79%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d79\n wait calmly when access to preferred item is denied: 13/15 correct (84%); latency 2.0s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d77\n\nSession 12 \u2014 2026-10-29 \u2014 40 min \u2014 1 observer\n follows 1-step motor instructions: 13/15 correct (85%); latency 2.1s; prompts FP\u00d75, PP\u00d75, G\u00d71, I\u00d74\n tacts common objects: 9/11 correct (84%); latency 2.1s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n answers WH-questions about familiar topics: 10/13 correct (77%); latency 2.3s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d75\n tacts colors of objects: 7/12 correct (59%); latency 3.6s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d75\n indicating completion ('all done', 'finished'): 10/12 correct (80%); latency 2.7s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d72\n wait calmly when access to preferred item is denied: 7/8 correct (84%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Stereotypic behavior during inter-trial intervals\n- Echolalic responding (repeating SD rather than answering)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Motivating-operation shift**: mid-log dip in responding followed by recovery suggests reinforcer-value change.\n- Possible satiation with current reinforcer; preference reassessment indicated.\n\n## Pattern Classification\nmotivating_operation_shift\n\nA mid-log dip followed by recovery maps onto a motivating-operation change rather than a skill issue.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct preference assessment to identify a currently-valued reinforcer.\n- Program MO-establishing operations (deprivation for target reinforcer) before teaching sessions.\n- Rotate reinforcers to prevent satiation.\n\n### Consequence strategies\n- Adjust reinforcement density to match current MO level.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 74.9%.\n- Trend direction: upward (first session: 82%, last session: 85%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "1b5cc587f01f0c10", "gold_labels": {"pattern_class": "motivating_operation_shift", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "motivating_operation_shift", "learner_profile": "early", "n_sessions": 12, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "99371"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: washing hands\nCurriculum: AFLS Basic Living Skills\nLearner: School-Age Learner\nMastery Status: Generalization phase\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: washing hands\n- Curriculum: AFLS Basic Living Skills\n- Learner: School-Age Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Walk to the sink.\n2. Turn on the water.\n3. Wet hands under the water.\n4. Apply soap to hands.\n5. Rub hands together for 15\u201320 seconds, covering fronts, backs, and between fingers.\n6. Rinse hands thoroughly under the water.\n7. Turn off the water.\n8. Dry hands with a towel.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "40e25cab9194baab", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "washing hands", "program_type": "independence", "learner_profile": "school_age", "mastery_state": "generalization", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "washing hands", "module": "basic_living", "mastery_criterion": "mc_self_initiation", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "98892"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-2139\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math\nDate range: Sessions 1\u20135 across 10 days (2026-08-25 to 2026-09-04)\n\nACCELERATION PROGRAMS\n1. identifies numerals 1\u201320 (Math)\n Method: DTT\n2. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n3. single-word requests for preferred items (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-25 \u2014 39 min \u2014 1 observer\n identifies numerals 1\u201320: 4/12 correct (35%); latency 4.2s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/14 correct (27%); latency 5.1s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d79\n single-word requests for preferred items: 4/12 correct (36%); latency 4.5s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d73\n\nSession 2 \u2014 2026-08-27 \u2014 39 min \u2014 1 observer\n identifies numerals 1\u201320: 6/14 correct (43%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d78\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/13 correct (39%); latency 4.5s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d75\n single-word requests for preferred items: 6/13 correct (50%); latency 3.9s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d76\n\nSession 3 \u2014 2026-08-29 \u2014 39 min \u2014 1 observer\n identifies numerals 1\u201320: 4/8 correct (53%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/14 correct (47%); latency 4.0s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n single-word requests for preferred items: 5/9 correct (58%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n\nSession 4 \u2014 2026-08-31 \u2014 39 min \u2014 1 observer\n identifies numerals 1\u201320: 8/13 correct (64%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d713\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/10 correct (53%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n single-word requests for preferred items: 9/13 correct (70%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d710\n\nSession 5 \u2014 2026-09-02 \u2014 39 min \u2014 1 observer\n identifies numerals 1\u201320: 8/10 correct (77%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/14 correct (65%); latency 2.9s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d77\n single-word requests for preferred items: 10/13 correct (77%); latency 2.4s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d78\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Reaching for materials proactively\n- Quick response latency (within 2\u20133 seconds)\n- Smiling during reinforcement delivery"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 35% to 77% across 5 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 5 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 5 sessions: 54.4%.\n- Trend direction: upward (first session: 35%, last session: 77%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "c37d37801c39adf9", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "school_age", "n_sessions": 5, "n_programs": 3, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "83942"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8371\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Mand + Reading + Self-Care\nDate range: Sessions 1\u201311 across 22 days (2026-02-13 to 2026-03-07)\n\nACCELERATION PROGRAMS\n1. sounds out CVC words (Reading)\n Method: DTT\n2. indicating 'all done' with a step or activity (Mand)\n Method: NET\n3. requesting preferred items using AAC device (Mand)\n Method: NET\n4. brushing teeth independently (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Mouthing \u2014 function hypothesized: automatic\n2. Property destruction \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-13 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 6/8 correct (77%); latency 2.2s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n indicating 'all done' with a step or activity: 11/14 correct (75%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d79\n requesting preferred items using AAC device: 13/15 correct (87%); latency 1.9s; prompts FP\u00d71, PP\u00d74, G\u00d75, I\u00d75\n brushing teeth independently: 9/11 correct (84%); latency 2.0s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n Mouthing: freq 1; PIR 5%\n Property destruction: freq 2\n\nSession 2 \u2014 2026-02-15 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 9/12 correct (76%); latency 2.7s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d78\n indicating 'all done' with a step or activity: 10/14 correct (71%); latency 3.0s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d710\n requesting preferred items using AAC device: 7/9 correct (80%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d74\n brushing teeth independently: 9/12 correct (71%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n Mouthing: freq 3; PIR 11%\n Property destruction: freq 1\n\nSession 3 \u2014 2026-02-17 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 6/9 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d72\n indicating 'all done' with a step or activity: 8/13 correct (62%); latency 2.9s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d74\n requesting preferred items using AAC device: 7/9 correct (74%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d76\n brushing teeth independently: 7/10 correct (67%); latency 2.8s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n Mouthing: freq 2; PIR 18%\n Property destruction: freq 2\n ABC (mouthing): A = waiting in line transition; B = mouthed own hand; C = staff redirected to task materials\n\nSession 4 \u2014 2026-02-19 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 6/10 correct (58%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n indicating 'all done' with a step or activity: 10/15 correct (64%); latency 3.4s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d77\n requesting preferred items using AAC device: 5/8 correct (67%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n brushing teeth independently: 9/14 correct (67%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d711\n Mouthing: freq 2; PIR 13%\n Property destruction: freq 2\n ABC (property destruction): A = transition to non-preferred activity; B = dropped to floor, cried; C = transition delayed, preferred item offered\n\nSession 5 \u2014 2026-02-21 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 7/12 correct (60%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d711\n indicating 'all done' with a step or activity: 9/15 correct (57%); latency 3.1s; prompts FP\u00d74, PP\u00d75, G\u00d71, I\u00d75\n requesting preferred items using AAC device: 6/10 correct (58%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d76\n brushing teeth independently: 6/12 correct (53%); latency 3.7s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d77\n Mouthing: freq 3; PIR 21%\n Property destruction: freq 1\n\nSession 6 \u2014 2026-02-23 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 6/12 correct (51%); latency 3.6s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n indicating 'all done' with a step or activity: 5/10 correct (52%); latency 3.6s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n requesting preferred items using AAC device: 4/8 correct (53%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n brushing teeth independently: 6/11 correct (50%); latency 4.0s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d710\n Mouthing: freq 4; PIR 21%\n Property destruction: freq 2\n\nSession 7 \u2014 2026-02-25 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 6/13 correct (45%); latency 4.2s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n indicating 'all done' with a step or activity: 5/12 correct (45%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d75\n requesting preferred items using AAC device: 5/13 correct (40%); latency 4.3s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d79\n brushing teeth independently: 7/15 correct (44%); latency 3.8s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d78\n Mouthing: freq 5; PIR 21%\n Property destruction: freq 3\n\nSession 8 \u2014 2026-02-27 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 4/9 correct (45%); latency 4.0s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d72\n indicating 'all done' with a step or activity: 5/12 correct (42%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d74\n requesting preferred items using AAC device: 5/13 correct (39%); latency 4.0s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d73\n brushing teeth independently: 3/8 correct (40%); latency 4.2s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n Mouthing: freq 5; PIR 20%\n Property destruction: freq 4\n ABC (property destruction): A = worksheet task presented; B = refused + pushed materials away; C = task removed for 2 min\n\nSession 9 \u2014 2026-03-01 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 3/8 correct (32%); latency 4.4s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n indicating 'all done' with a step or activity: 5/13 correct (37%); latency 4.4s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d72\n requesting preferred items using AAC device: 2/8 correct (26%); latency 4.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n brushing teeth independently: 3/9 correct (29%); latency 4.7s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n Mouthing: freq 5; PIR 22%\n Property destruction: freq 4\n\nSession 10 \u2014 2026-03-03 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 4/15 correct (28%); latency 4.8s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d710\n indicating 'all done' with a step or activity: 4/11 correct (35%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d78\n requesting preferred items using AAC device: 2/10 correct (21%); latency 5.0s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d79\n brushing teeth independently: 3/12 correct (29%); latency 4.9s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d712\n Mouthing: freq 5; PIR 22%\n Property destruction: freq 3\n\nSession 11 \u2014 2026-03-05 \u2014 34 min \u2014 1 observer\n sounds out CVC words: 5/15 correct (32%); latency 4.4s; prompts FP\u00d70, PP\u00d75, G\u00d75, I\u00d75\n indicating 'all done' with a step or activity: 3/8 correct (34%); latency 4.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n requesting preferred items using AAC device: 2/13 correct (16%); latency 5.2s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d710\n brushing teeth independently: 1/9 correct (17%); latency 5.0s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n Mouthing: freq 5; PIR 33%\n Property destruction: freq 4\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Attempts at property destruction (throwing materials, swiping items off the surface)\n- Self-stimulatory behavior increase during demand periods"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 77% to 32% across 11 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nMouthing: automatic\n Evidence: ABC events in the log support the automatic function; behavior persists across contexts without clear social mediation.\nProperty destruction: escape\n Evidence: ABC events in the log support the escape function; behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 52.1%.\n- Trend direction: downward (first session: 77%, last session: 32%).\n- Mouthing: mean 3.6/session (early-window mean 2.0 -> late-window mean 5.0).\n- Property destruction: mean 2.5/session (early-window mean 1.7 -> late-window mean 3.7).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "dfb65de9daa9d3b9", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Mouthing": "automatic", "Property destruction": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "adolescent", "n_sessions": 11, "n_programs": 4, "n_behaviors": 2, "behavior_ids": ["mouthing", "property_destruction"], "behavior_functions": ["automatic", "escape"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "90680"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: traces letters of own name\nCurriculum: Writing L1\nLearner: Early Learner\nMastery Status: Near mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: traces letters of own name\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the near mastery stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: O, B, A\nDistractor stimuli: E, Y\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy across 2 consecutive sessions with at least 10 trials each.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "6310a06ef21744ae", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "traces letters of own name", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "vr3", "error_correction": "backstep", "mastery_criterion": "mc_80_2sessions"}, "teacher_model": null, "seed_tag": "60118"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9146\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Math + Reading + Writing\nDate range: Sessions 1\u20138 across 16 days (2026-09-09 to 2026-09-25)\n\nACCELERATION PROGRAMS\n1. copies simple words from model (Writing)\n Method: DTT\n2. reads 10\u201320 sight words (Reading)\n Method: DTT\n3. counts objects 1\u201320 (Math)\n Method: DTT\n\nDECELERATION TARGETS\n1. Property destruction \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-09 \u2014 45 min \u2014 1 observer\n copies simple words from model: 9/11 correct (81%); latency 2.1s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d73\n reads 10\u201320 sight words: 11/14 correct (82%); latency 2.5s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d74\n counts objects 1\u201320: 8/10 correct (80%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n Property destruction: freq 2\n\nSession 2 \u2014 2026-09-11 \u2014 45 min \u2014 1 observer\n copies simple words from model: 7/9 correct (83%); latency 2.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n reads 10\u201320 sight words: 12/15 correct (83%); latency 2.3s; prompts FP\u00d71, PP\u00d74, G\u00d75, I\u00d75\n counts objects 1\u201320: 12/14 correct (86%); latency 1.9s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d713\n Property destruction: freq 2\n\nSession 3 \u2014 2026-09-13 \u2014 45 min \u2014 1 observer\n copies simple words from model: 7/8 correct (84%); latency 2.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n reads 10\u201320 sight words: 9/10 correct (85%); latency 2.0s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d74\n counts objects 1\u201320: 13/15 correct (86%); latency 2.3s; prompts FP\u00d75, PP\u00d72, G\u00d73, I\u00d75\n Property destruction: freq 3\n\nSession 4 \u2014 2026-09-15 \u2014 45 min \u2014 1 observer\n copies simple words from model: 9/11 correct (81%); latency 2.5s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n reads 10\u201320 sight words: 9/11 correct (83%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n counts objects 1\u201320: 7/8 correct (83%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n Property destruction: freq 2\n\nSession 5 \u2014 2026-09-17 \u2014 45 min \u2014 1 observer\n copies simple words from model: 7/9 correct (77%); latency 2.6s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n reads 10\u201320 sight words: 10/12 correct (83%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d712\n counts objects 1\u201320: 7/8 correct (85%); latency 2.0s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n Property destruction: freq 2\n\nSession 6 \u2014 2026-09-19 \u2014 IOA SESSION \u2014 2 observers\n copies simple words from model: 83% (primary); IOA 82% agreement\n reads 10\u201320 sight words: 86% (primary); IOA 82% agreement\n counts objects 1\u201320: 86% (primary); IOA 82% agreement\n Property destruction: freq 2; IOA 82% agreement\n\nSession 7 \u2014 2026-09-21 \u2014 45 min \u2014 1 observer\n copies simple words from model: 10/12 correct (80%); latency 2.2s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d76\n reads 10\u201320 sight words: 9/11 correct (84%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n counts objects 1\u201320: 12/13 correct (90%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d710\n Property destruction: freq 2\n\nSession 8 \u2014 2026-09-23 \u2014 45 min \u2014 1 observer\n copies simple words from model: 12/15 correct (78%); latency 2.7s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d74\n reads 10\u201320 sight words: 9/11 correct (82%); latency 2.5s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n counts objects 1\u201320: 9/10 correct (85%); latency 2.0s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d79\n Property destruction: freq 2\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Playing with non-task materials\n- Stereotypic behavior during inter-trial intervals"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (81%\u201378%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Behavior Function Hypothesis\nProperty destruction: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 8 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 80.9%.\n- Trend direction: downward (first session: 81%, last session: 78%).\n- Property destruction: mean 2.1/session (early-window mean 2.0 -> late-window mean 2.0).\n- IOA data: 82% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "a103fd8f3d78e3c3", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {"Property destruction": "escape"}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "school_age", "n_sessions": 8, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["property_destruction"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "8756"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6092\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Mand + Self-Care + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u201310 across 20 days (2026-07-16 to 2026-08-05)\n\nACCELERATION PROGRAMS\n1. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n2. simple meal preparation (Home Skills)\n Method: Task Analysis\n3. requesting assistance using AAC device (Mand)\n Method: NET\n4. brushing teeth independently (Self-Care)\n Method: Task Analysis\n5. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n6. doing laundry (Home Skills)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Self-injurious behavior (SIB) \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-16 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 9/15 correct (57%); latency 3.2s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d712\n simple meal preparation: 8/12 correct (68%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d78\n requesting assistance using AAC device: 5/11 correct (44%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n brushing teeth independently: 6/11 correct (57%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n wait calmly when a preferred activity is denied: 5/12 correct (44%); latency 4.3s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d77\n doing laundry: 5/8 correct (58%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n Self-injurious behavior (SIB): freq 3\n\nSession 2 \u2014 2026-07-18 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 6/11 correct (50%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n simple meal preparation: 7/14 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n requesting assistance using AAC device: 4/9 correct (43%); latency 3.9s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n brushing teeth independently: 5/8 correct (66%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n wait calmly when a preferred activity is denied: 4/8 correct (45%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n doing laundry: 9/15 correct (57%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d714\n Self-injurious behavior (SIB): freq 2\n\nSession 3 \u2014 2026-07-20 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 6/10 correct (63%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n simple meal preparation: 5/8 correct (59%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n requesting assistance using AAC device: 4/9 correct (50%); latency 3.7s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d73\n brushing teeth independently: 8/13 correct (59%); latency 3.5s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d711\n wait calmly when a preferred activity is denied: 3/8 correct (37%); latency 4.3s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n doing laundry: 7/12 correct (57%); latency 3.3s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d75\n Self-injurious behavior (SIB): freq 3\n\nSession 4 \u2014 2026-07-22 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 7/11 correct (64%); latency 3.0s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n simple meal preparation: 6/10 correct (56%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n requesting assistance using AAC device: 4/8 correct (46%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n brushing teeth independently: 7/10 correct (67%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n wait calmly when a preferred activity is denied: 3/8 correct (33%); latency 4.7s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n doing laundry: 5/8 correct (59%); latency 3.5s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n Self-injurious behavior (SIB): freq 3\n\nSession 5 \u2014 2026-07-24 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 5/10 correct (54%); latency 3.7s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n simple meal preparation: 6/11 correct (59%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n requesting assistance using AAC device: 6/13 correct (50%); latency 3.9s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n brushing teeth independently: 10/14 correct (72%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n wait calmly when a preferred activity is denied: 6/15 correct (39%); latency 4.4s; prompts FP\u00d75, PP\u00d72, G\u00d74, I\u00d74\n doing laundry: 5/8 correct (61%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n Self-injurious behavior (SIB): freq 2\n\nSession 6 \u2014 2026-07-26 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 5/8 correct (66%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n simple meal preparation: 9/13 correct (68%); latency 2.8s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d74\n requesting assistance using AAC device: 7/12 correct (56%); latency 3.3s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d76\n brushing teeth independently: 9/14 correct (67%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d711\n wait calmly when a preferred activity is denied: 4/14 correct (31%); latency 4.8s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d76\n doing laundry: 8/13 correct (59%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d78\n Self-injurious behavior (SIB): freq 3\n\nSession 7 \u2014 2026-07-28 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 9/14 correct (66%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d76\n simple meal preparation: 9/15 correct (62%); latency 2.9s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d77\n requesting assistance using AAC device: 8/15 correct (54%); latency 3.5s; prompts FP\u00d73, PP\u00d75, G\u00d72, I\u00d75\n brushing teeth independently: 8/12 correct (71%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 5/13 correct (40%); latency 4.0s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n doing laundry: 5/8 correct (57%); latency 3.2s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n Self-injurious behavior (SIB): freq 3\n\nSession 8 \u2014 2026-07-30 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 8/15 correct (56%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d713\n simple meal preparation: 6/10 correct (63%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n requesting assistance using AAC device: 6/10 correct (56%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d78\n brushing teeth independently: 5/8 correct (67%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n wait calmly when a preferred activity is denied: 4/10 correct (39%); latency 4.2s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d74\n doing laundry: 7/11 correct (61%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d75\n Self-injurious behavior (SIB): freq 3\n\nSession 9 \u2014 2026-08-01 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 6/11 correct (58%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n simple meal preparation: 9/14 correct (65%); latency 3.3s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d72\n requesting assistance using AAC device: 7/12 correct (57%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d75\n brushing teeth independently: 8/11 correct (74%); latency 2.6s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n wait calmly when a preferred activity is denied: 5/15 correct (35%); latency 4.6s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d710\n doing laundry: 5/8 correct (62%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n Self-injurious behavior (SIB): freq 3\n\nSession 10 \u2014 2026-08-03 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 10/15 correct (69%); latency 2.9s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d74\n simple meal preparation: 8/14 correct (59%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d79\n requesting assistance using AAC device: 6/12 correct (51%); latency 3.7s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d76\n brushing teeth independently: 8/11 correct (74%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n wait calmly when a preferred activity is denied: 5/15 correct (33%); latency 4.5s; prompts FP\u00d72, PP\u00d75, G\u00d70, I\u00d78\n doing laundry: 8/14 correct (54%); latency 3.8s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d77\n Self-injurious behavior (SIB): freq 3\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Leaving seat without permission\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Plateau**: accuracy has remained near 63% for 10 sessions without meaningful improvement.\n- Performance is below mastery criteria; current teaching procedure may not be effective for this learner.\n\n## Pattern Classification\nplateau\n\nResponding has stabilized below mastery criterion without meaningful movement, indicating the current procedure is limiting further acquisition.\n\n## Behavior Function Hypothesis\nSelf-injurious behavior (SIB): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Modify teaching procedure \u2014 switch prompt type (e.g., from most-to-least to time delay).\n- Conduct preference assessment and update reinforcer menu.\n- Break the current skill into smaller component steps if possible.\n- Increase practice opportunities by embedding targets in natural-environment training.\n\n### Consequence strategies\n- Check for inadvertent reinforcement of near-misses; tighten differential reinforcement.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 60.5%.\n- Trend direction: upward (first session: 57%, last session: 69%).\n- Self-injurious behavior (SIB): mean 2.8/session (early-window mean 2.7 -> late-window mean 3.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "b8379739a966e4f3", "gold_labels": {"pattern_class": "plateau", "behavior_functions": {"Self-injurious behavior (SIB)": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "plateau", "learner_profile": "adult", "n_sessions": 10, "n_programs": 6, "n_behaviors": 1, "behavior_ids": ["sib"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "52665"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: tacts common objects (ball, cup, shoe)\nCurriculum: Tact L1\nLearner: Early Learner\nMastery Status: Generalization phase\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts common objects (ball, cup, shoe)\n- Curriculum: Tact L1\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What is this?\"\nVariations: \"Tell me what you see\"; \"What's that?\"; \"Name this\"\nPresentation: Present the target stimulus within visual field and ask while pointing to it.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: phone, pencil, napkin\nDistractor stimuli: hat, backpack\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nToken economy \u2014 Tokens delivered per correct response; exchanged at session end for a back-up reinforcer appropriate to the learner (for children: candy, cookies, brief leisure-time access, preferred activity, screen time, or a favorite sensory item). Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "84ce86cebd1f1cfe", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L1", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts common objects (ball, cup, shoe)", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "token_economy", "error_correction": "four_step", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "93657"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: sorts items into 2\u20133 categories\nCurriculum: Visual Perceptual Skills & Matching-to-Sample L2\nLearner: Early Learner\nMastery Status: Approaching mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: sorts items into 2\u20133 categories\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L2\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: towel, napkin, jacket\nDistractor stimuli: pencil, apple, cup, phone\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nPrevent errors by using high prompts from the start; fade gradually. Paired with most-to-least prompt hierarchy.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "3913a0455c682fe8", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L2", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "sorts items into 2\u20133 categories", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "crf", "error_correction": "errorless", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "85854"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5252\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u20138 across 16 days (2026-03-10 to 2026-03-26)\n\nACCELERATION PROGRAMS\n1. doing laundry (Home Skills)\n Method: Task Analysis\n2. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n3. clocking in at start of shift (Vocational)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-03-10 \u2014 35 min \u2014 1 observer\n doing laundry: 9/11 correct (85%); latency 2.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n wait calmly when a preferred activity is denied: 13/15 correct (87%); latency 2.1s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d74\n clocking in at start of shift: 8/9 correct (85%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d77\n\nSession 2 \u2014 2026-03-12 \u2014 35 min \u2014 1 observer\n doing laundry: 2/8 correct (26%); latency 4.8s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n wait calmly when a preferred activity is denied: 3/9 correct (33%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n clocking in at start of shift: 2/8 correct (28%); latency 4.5s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n\nSession 3 \u2014 2026-03-14 \u2014 IOA SESSION \u2014 2 observers\n doing laundry: 90% (primary); IOA 91% agreement\n wait calmly when a preferred activity is denied: 80% (primary); IOA 91% agreement\n clocking in at start of shift: 81% (primary); IOA 91% agreement\n\nSession 4 \u2014 2026-03-16 \u2014 35 min \u2014 1 observer\n doing laundry: 3/11 correct (26%); latency 5.1s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n wait calmly when a preferred activity is denied: 4/10 correct (37%); latency 4.0s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n clocking in at start of shift: 4/14 correct (30%); latency 4.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n\nSession 5 \u2014 2026-03-18 \u2014 35 min \u2014 1 observer\n doing laundry: 7/8 correct (83%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 8/10 correct (80%); latency 2.1s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n clocking in at start of shift: 11/13 correct (87%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n\nSession 6 \u2014 2026-03-20 \u2014 35 min \u2014 1 observer\n doing laundry: 2/9 correct (28%); latency 5.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n wait calmly when a preferred activity is denied: 3/10 correct (34%); latency 4.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n clocking in at start of shift: 4/14 correct (26%); latency 4.6s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d73\n\nSession 7 \u2014 2026-03-22 \u2014 35 min \u2014 1 observer\n doing laundry: 7/8 correct (85%); latency 1.9s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n wait calmly when a preferred activity is denied: 8/10 correct (79%); latency 2.4s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n clocking in at start of shift: 13/15 correct (87%); latency 2.0s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d711\n\nSession 8 \u2014 2026-03-24 \u2014 35 min \u2014 1 observer\n doing laundry: 3/8 correct (32%); latency 4.3s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 4/11 correct (34%); latency 4.7s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n clocking in at start of shift: 4/15 correct (28%); latency 4.8s; prompts FP\u00d75, PP\u00d74, G\u00d71, I\u00d75\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Stereotypic behavior during inter-trial intervals\n- Leaving seat without permission\n- Echolalic responding (repeating SD rather than answering)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data with IOA evidence.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 56.9%.\n- Trend direction: downward (first session: 85%, last session: 32%).\n- IOA data: 91% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "50f8a62f6f53880e", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "adult", "n_sessions": 8, "n_programs": 3, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "52979"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: mands for missing items needed to complete an activity\nCurriculum: Mand L1\nLearner: Early Learner\nMastery Status: Generalization phase\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands for missing items needed to complete an activity\n- Curriculum: Mand L1\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange an activity that requires a specific item to complete, then omit that item from the available materials. Wait for the learner to notice the gap.\nPrimary natural context: art activity.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's art activity routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the generalization stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: the missing item is provided, activity can continue.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nAverage rate of \u2265 3 spontaneous responses per 30-minute session across 3 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "5e95c63a3261363d", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L1", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands for missing items needed to complete an activity", "mo_category": "mand_missing", "mo_arrangement": "missing_item_completion", "prompt_strategy": "time_delay", "mastery_criterion": "mc_spontaneous_rate"}, "teacher_model": null, "seed_tag": "83467"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: selects items by function when item not visible\nCurriculum: LRFFC L2\nLearner Level: Early Learner\nBaseline: Approaching mastery\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by function when item not visible\n- Curriculum: LRFFC L2\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: jacket, ball, backpack\nDistractor stimuli: apple, plate, block, key\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "ce1403ef1332f36b", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L2", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by function when item not visible", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "crf", "error_correction": "simple_correction", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "17197"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-2005\nProfile: Adult Learner (18+ years)\nCurricula: Mand + Self-Care + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u20137 across 14 days (2026-04-06 to 2026-04-20)\n\nACCELERATION PROGRAMS\n1. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n2. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n3. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n4. requesting a break during extended tasks (Mand)\n Method: NET\n5. washing hands independently (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Aggression \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-06 \u2014 50 min \u2014 1 observer\n dressing (pants, shirt): 6/12 correct (54%); latency 3.5s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d74\n wait calmly when a preferred activity is denied: 6/8 correct (73%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n completing assigned tasks in order: 7/13 correct (53%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d77\n requesting a break during extended tasks: 8/12 correct (65%); latency 3.3s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d73\n washing hands independently: 9/15 correct (58%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d710\n Aggression: freq 1\n\nSession 2 \u2014 2026-04-08 \u2014 50 min \u2014 1 observer\n dressing (pants, shirt): 5/10 correct (52%); latency 3.5s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 8/11 correct (74%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d73\n completing assigned tasks in order: 9/15 correct (59%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d79\n requesting a break during extended tasks: 7/10 correct (74%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n washing hands independently: 5/9 correct (60%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d77\n Aggression: freq 3\n\nSession 3 \u2014 2026-04-10 \u2014 50 min \u2014 1 observer\n dressing (pants, shirt): 7/11 correct (62%); latency 3.2s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n wait calmly when a preferred activity is denied: 6/8 correct (73%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n completing assigned tasks in order: 8/15 correct (51%); latency 3.9s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d79\n requesting a break during extended tasks: 10/14 correct (71%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d79\n washing hands independently: 5/9 correct (51%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n Aggression: freq 5\n\nSession 4 \u2014 2026-04-12 \u2014 50 min \u2014 1 observer\n dressing (pants, shirt): 8/14 correct (61%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d78\n wait calmly when a preferred activity is denied: 8/11 correct (73%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n completing assigned tasks in order: 8/15 correct (53%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d79\n requesting a break during extended tasks: 9/12 correct (75%); latency 2.8s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d76\n washing hands independently: 7/13 correct (56%); latency 3.6s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n Aggression: freq 5\n\nSession 5 \u2014 2026-04-14 \u2014 50 min \u2014 1 observer\n dressing (pants, shirt): 6/11 correct (56%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 6/8 correct (79%); latency 2.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n completing assigned tasks in order: 5/10 correct (53%); latency 3.4s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d77\n requesting a break during extended tasks: 10/14 correct (74%); latency 3.0s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d76\n washing hands independently: 7/13 correct (53%); latency 3.8s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d79\n Aggression: freq 2\n\nSession 6 \u2014 2026-04-16 \u2014 50 min \u2014 1 observer\n dressing (pants, shirt): 6/9 correct (61%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d72\n wait calmly when a preferred activity is denied: 11/15 correct (76%); latency 2.9s; prompts FP\u00d72, PP\u00d75, G\u00d75, I\u00d73\n completing assigned tasks in order: 7/11 correct (61%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d79\n requesting a break during extended tasks: 6/8 correct (74%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n washing hands independently: 6/11 correct (53%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n Aggression: freq 2\n\nSession 7 \u2014 2026-04-18 \u2014 50 min \u2014 1 observer\n dressing (pants, shirt): 7/11 correct (67%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d77\n wait calmly when a preferred activity is denied: 6/8 correct (78%); latency 2.2s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n completing assigned tasks in order: 7/13 correct (56%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d75\n requesting a break during extended tasks: 12/15 correct (83%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d711\n washing hands independently: 6/11 correct (56%); latency 3.4s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d710\n Aggression: freq 1\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Peer aggression (hitting or pushing peers during group activities)\n- Turning away from task or staff\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)\n- Crying during demand presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nAggression: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n### Crisis plan\n- If problem-behavior intensity or topography exceeds the learner's baseline safety threshold (SIB causing tissue damage, aggression causing injury, imminent elopement into hazard): pause the extinction procedure and implement the facility's tiered crisis-prevention protocol (e.g., Safety-Care, CPI, or equivalent).\n- De-escalation and environmental safety first; physical intervention is last resort and only by staff currently certified in the facility's framework. Least-restrictive option appropriate to the risk level applies at every step. Physical intervention is used only when specifically authorized for this learner in the BIP \u2014 contraindications (medical, developmental, trauma history) may restrict the procedures available, in which case the plan is de-escalation + environmental safety + supervisor contact only.\n- Contact the supervising BCBA immediately; do not resume the extinction procedure without BCBA review. Document duration, intensity, antecedent, staff response, and post-incident state.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 58.9%.\n- Trend direction: upward (first session: 54%, last session: 67%).\n- Aggression: mean 2.7/session (early-window mean 2.0 -> late-window mean 1.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "6ad02e6384b6d574", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Aggression": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "adult", "n_sessions": 7, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["aggression"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "54431"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9867\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Independent Living + Self-Care + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u20138 across 16 days (2026-04-02 to 2026-04-18)\n\nACCELERATION PROGRAMS\n1. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n2. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n3. washing hands independently (Self-Care)\n Method: Task Analysis\n4. self-advocacy statements (Independent Living)\n Method: BST\n5. simple meal preparation (Home Skills)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-02 \u2014 58 min \u2014 1 observer\n completing assigned tasks in order: 12/14 correct (86%); latency 2.2s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d75\n wait calmly when a preferred activity is denied: 10/11 correct (87%); latency 1.9s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d79\n washing hands independently: 9/12 correct (79%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d72\n self-advocacy statements: 9/10 correct (86%); latency 1.9s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d75\n simple meal preparation: 7/8 correct (91%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n\nSession 2 \u2014 2026-04-04 \u2014 58 min \u2014 1 observer\n completing assigned tasks in order: 3/9 correct (35%); latency 4.1s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n wait calmly when a preferred activity is denied: 5/14 correct (37%); latency 4.6s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d710\n washing hands independently: 2/9 correct (25%); latency 5.0s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n self-advocacy statements: 5/11 correct (41%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n simple meal preparation: 5/11 correct (47%); latency 3.8s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d74\n\nSession 3 \u2014 2026-04-06 \u2014 58 min \u2014 1 observer\n completing assigned tasks in order: 13/15 correct (90%); latency 1.7s; prompts FP\u00d75, PP\u00d73, G\u00d74, I\u00d73\n wait calmly when a preferred activity is denied: 11/13 correct (84%); latency 2.4s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d76\n washing hands independently: 9/11 correct (80%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n self-advocacy statements: 12/14 correct (86%); latency 2.1s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d710\n simple meal preparation: 12/14 correct (84%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n\nSession 4 \u2014 2026-04-08 \u2014 58 min \u2014 1 observer\n completing assigned tasks in order: 3/10 correct (34%); latency 4.4s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d76\n wait calmly when a preferred activity is denied: 3/9 correct (32%); latency 4.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n washing hands independently: 3/13 correct (23%); latency 5.2s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d76\n self-advocacy statements: 6/15 correct (37%); latency 4.5s; prompts FP\u00d72, PP\u00d74, G\u00d75, I\u00d74\n simple meal preparation: 5/12 correct (45%); latency 3.8s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d75\n\nSession 5 \u2014 2026-04-10 \u2014 58 min \u2014 1 observer\n completing assigned tasks in order: 12/14 correct (84%); latency 2.3s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d73\n wait calmly when a preferred activity is denied: 8/9 correct (89%); latency 2.2s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n washing hands independently: 11/13 correct (81%); latency 2.4s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d72\n self-advocacy statements: 13/15 correct (89%); latency 2.0s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d715\n simple meal preparation: 11/13 correct (87%); latency 2.3s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n\nSession 6 \u2014 2026-04-12 \u2014 58 min \u2014 1 observer\n completing assigned tasks in order: 3/8 correct (34%); latency 4.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 5/11 correct (42%); latency 3.9s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d73\n washing hands independently: 3/11 correct (27%); latency 5.0s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d76\n self-advocacy statements: 5/13 correct (40%); latency 4.1s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d75\n simple meal preparation: 3/8 correct (43%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n\nSession 7 \u2014 2026-04-14 \u2014 58 min \u2014 1 observer\n completing assigned tasks in order: 9/10 correct (93%); latency 2.0s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 14/15 correct (92%); latency 1.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d712\n washing hands independently: 11/14 correct (76%); latency 2.7s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d79\n self-advocacy statements: 7/8 correct (89%); latency 2.3s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n simple meal preparation: 12/14 correct (84%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n\nSession 8 \u2014 2026-04-16 \u2014 58 min \u2014 1 observer\n completing assigned tasks in order: 3/9 correct (39%); latency 4.0s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 4/11 correct (40%); latency 4.0s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d77\n washing hands independently: 2/8 correct (28%); latency 4.7s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n self-advocacy statements: 5/12 correct (42%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d79\n simple meal preparation: 4/11 correct (41%); latency 4.4s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Looking away during SD presentation\n- Echolalic responding (repeating SD rather than answering)\n- Delayed responding (>5 seconds consistently)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 61.9%.\n- Trend direction: downward (first session: 86%, last session: 39%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "2a430140599afd91", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "adult", "n_sessions": 8, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "27450"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: traces letters of own name\nCurriculum: Writing L1\nLearner: Early Learner\nMastery Status: Generalization phase\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: traces letters of own name\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: Z, R, J\nDistractor stimuli: C, S\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy across 2 consecutive sessions with at least 10 trials each.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "97dacbc1748705d0", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "traces letters of own name", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "vr3", "error_correction": "simple_correction", "mastery_criterion": "mc_80_2sessions"}, "teacher_model": null, "seed_tag": "69141"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: tacts body parts\nCurriculum: Tact L1\nLearner Level: Early Learner\nBaseline: Emerging\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts body parts\n- Curriculum: Tact L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What is this?\"\nVariations: \"Tell me\"; \"Name this body part\"\nPresentation: Point to the target body part (on self, learner, or doll) and ask.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: sock, cup, phone\nDistractor stimuli: block, glue\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "51df15c5d8b1e0d3", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts body parts", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "crf", "error_correction": "simple_correction", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "36112"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: mands to indicate completion of a step or activity (\"all done with this one\")\nCurriculum Reference: Mand L2\nLearner Profile: Early Learner\nCurrent Mastery: Near mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands to indicate completion of a step or activity (\"all done with this one\")\n- Curriculum: Mand L2\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nSet up a clearly-bounded activity with a visible endpoint (e.g., a worksheet, a puzzle, a sorting task). Wait for the learner to indicate completion verbally or via AAC; honor the indication immediately.\nPrimary natural context: meal.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's meal routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the near mastery stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: the activity ends immediately and the learner transitions to the next preferred activity.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "1293c2195a8abcc4", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L2", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands to indicate completion of a step or activity (\"all done with this one\")", "mo_category": "mand_completion", "mo_arrangement": "completion_opportunity", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "36908"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: engages in social games (peek-a-boo, tickle)\nCurriculum: Social Behavior & Social Play L1\nLearner: Early Learner\nMastery Status: Emerging\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: engages in social games (peek-a-boo, tickle)\n- Curriculum: Social Behavior & Social Play L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: shared snack.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's shared snack routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Verbal fill-in\nDeliver a partial phrase and pause; learner completes the vocal response.\nCurrent prompt level: At the emerging stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use with a peer in unstructured free play across 2 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "bd75fe66d23005e4", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "engages in social games (peek-a-boo, tickle)", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "verbal_fill_in", "mastery_criterion": "mc_peer_initiation"}, "teacher_model": null, "seed_tag": "54871"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a systematic desensitization / toleration program for the following.\n\nSkill: tolerating nail clipping\nCurriculum: AFLS Basic Living Skills\nLearner Level: Adult Learner\nBaseline: Generalization phase\n\nThe learner currently refuses or exhibits safety behaviors during the activity; the program should build tolerance gradually."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating nail clipping\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adult Learner\n- Current mastery: Generalization phase\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for nail clipping performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nall 10 fingernails (and optionally toenails) clipped by caregiver without refusal, pulling hand away, or safety behaviors\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 1 fingernail clipped\n2. 2 fingernails clipped in one sitting\n3. 5 fingernails clipped (one hand)\n4. All 10 fingernails clipped\n5. All 10 fingernails + 10 toenails clipped\n\nCurrent shaping step: At the generalization stage, begin at shaping step 5 (\"All 10 fingernails + 10 toenails clipped\") and advance through step 5 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal activity tolerated with 2 different caregivers (primary caregiver + one other) across 2 consecutive weeks.\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 2 different settings and with 2 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "5ec50cf81011767a", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating nail clipping", "program_type": "toleration", "learner_profile": "adult", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating nail clipping", "module": "basic_living", "mastery_criterion": "mc_toleration_caregivers", "shaping_n_steps": 5}, "teacher_model": null, "seed_tag": "97806"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6485\nProfile: Adult Learner (18+ years)\nCurricula: Mand + Self-Care + Tolerating Denied Access\nDate range: Sessions 1\u201310 across 20 days (2026-02-10 to 2026-03-02)\n\nACCELERATION PROGRAMS\n1. requesting a break during extended tasks (Mand)\n Method: NET\n2. brushing teeth independently (Self-Care)\n Method: Task Analysis\n3. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-10 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 5/12 correct (44%); latency 4.1s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d73\n brushing teeth independently: 3/8 correct (34%); latency 4.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n wait calmly when a preferred activity is denied: 3/8 correct (42%); latency 4.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n\nSession 2 \u2014 2026-02-12 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 6/11 correct (53%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n brushing teeth independently: 4/10 correct (43%); latency 4.0s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n wait calmly when a preferred activity is denied: 7/15 correct (50%); latency 3.5s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d76\n\nSession 3 \u2014 2026-02-14 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 8/13 correct (62%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d79\n brushing teeth independently: 8/15 correct (51%); latency 3.9s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d75\n wait calmly when a preferred activity is denied: 6/10 correct (57%); latency 3.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d79\n\nSession 4 \u2014 2026-02-16 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 7/10 correct (71%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n brushing teeth independently: 6/10 correct (56%); latency 3.4s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n wait calmly when a preferred activity is denied: 7/10 correct (67%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n\nSession 5 \u2014 2026-02-18 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 12/15 correct (81%); latency 2.3s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d77\n brushing teeth independently: 5/8 correct (62%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n wait calmly when a preferred activity is denied: 9/13 correct (72%); latency 3.0s; prompts FP\u00d74, PP\u00d72, G\u00d70, I\u00d77\n\nSession 6 \u2014 2026-02-20 \u2014 IOA SESSION \u2014 2 observers\n requesting a break during extended tasks: 81% (primary); IOA 70% agreement\n brushing teeth independently: 69% (primary); IOA 70% agreement\n wait calmly when a preferred activity is denied: 72% (primary); IOA 70% agreement\n\nSession 7 \u2014 2026-02-22 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 12/15 correct (81%); latency 2.1s; prompts FP\u00d75, PP\u00d73, G\u00d70, I\u00d77\n brushing teeth independently: 6/9 correct (71%); latency 2.9s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d72\n wait calmly when a preferred activity is denied: 7/10 correct (72%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n\nSession 8 \u2014 2026-02-24 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 8/10 correct (81%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n brushing teeth independently: 9/13 correct (71%); latency 2.8s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d74\n wait calmly when a preferred activity is denied: 6/8 correct (72%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n\nSession 9 \u2014 2026-02-26 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 7/9 correct (81%); latency 2.5s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n brushing teeth independently: 6/9 correct (71%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n wait calmly when a preferred activity is denied: 9/13 correct (72%); latency 2.5s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d78\n\nSession 10 \u2014 2026-02-28 \u2014 51 min \u2014 1 observer\n requesting a break during extended tasks: 8/10 correct (81%); latency 2.3s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d73\n brushing teeth independently: 6/8 correct (71%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n wait calmly when a preferred activity is denied: 6/8 correct (72%); latency 2.8s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Playing with non-task materials\n- Delayed responding (>5 seconds consistently)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 44% at return, recovering to 81%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 10 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 71.5%.\n- Trend direction: upward (first session: 44%, last session: 81%).\n- IOA data: 70% agreement on IOA session \u2014 below threshold."}], "meta": {"task_type": "session_interpretation", "example_id": "ceb8b81cd0e690c7", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "adult", "n_sessions": 10, "n_programs": 3, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "70409"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6673\nProfile: Adult Learner (18+ years)\nCurricula: Community + Mand + Self-Care + Vocational\nDate range: Sessions 1\u20139 across 18 days (2026-01-25 to 2026-02-12)\n\nACCELERATION PROGRAMS\n1. requesting assistance using AAC device (Mand)\n Method: NET\n2. washing hands independently (Self-Care)\n Method: Task Analysis\n3. clocking in at start of shift (Vocational)\n Method: Task Analysis\n4. requesting a break during extended tasks (Mand)\n Method: NET\n5. using public transportation (Community)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Property destruction \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-25 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 11/14 correct (78%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d76\n washing hands independently: 7/9 correct (80%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n clocking in at start of shift: 8/9 correct (89%); latency 2.0s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d72\n requesting a break during extended tasks: 14/15 correct (93%); latency 2.1s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d75\n using public transportation: 7/8 correct (82%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n Property destruction: freq 1\n\nSession 2 \u2014 2026-01-27 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 3/10 correct (27%); latency 4.8s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d78\n washing hands independently: 6/14 correct (40%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d710\n clocking in at start of shift: 5/15 correct (34%); latency 4.5s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d77\n requesting a break during extended tasks: 6/15 correct (37%); latency 4.3s; prompts FP\u00d75, PP\u00d70, G\u00d71, I\u00d79\n using public transportation: 3/10 correct (34%); latency 4.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n Property destruction: freq 1\n\nSession 3 \u2014 2026-01-29 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 7/9 correct (77%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n washing hands independently: 6/8 correct (71%); latency 2.9s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n clocking in at start of shift: 10/12 correct (87%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d76\n requesting a break during extended tasks: 9/10 correct (93%); latency 2.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n using public transportation: 8/10 correct (83%); latency 2.5s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n Property destruction: freq 2\n\nSession 4 \u2014 2026-01-31 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 3/9 correct (33%); latency 4.5s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n washing hands independently: 3/9 correct (31%); latency 4.4s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n clocking in at start of shift: 4/13 correct (34%); latency 4.5s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d710\n requesting a break during extended tasks: 5/13 correct (39%); latency 4.5s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d72\n using public transportation: 4/12 correct (37%); latency 4.1s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d71\n Property destruction: freq 3\n\nSession 5 \u2014 2026-02-02 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 9/11 correct (78%); latency 2.4s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n washing hands independently: 10/14 correct (71%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d711\n clocking in at start of shift: 12/14 correct (85%); latency 2.0s; prompts FP\u00d70, PP\u00d74, G\u00d72, I\u00d78\n requesting a break during extended tasks: 9/10 correct (86%); latency 2.2s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d72\n using public transportation: 10/11 correct (89%); latency 2.0s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n Property destruction: freq 1\n\nSession 6 \u2014 2026-02-04 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 3/9 correct (29%); latency 4.6s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n washing hands independently: 3/10 correct (34%); latency 4.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n clocking in at start of shift: 5/14 correct (38%); latency 4.1s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d75\n requesting a break during extended tasks: 5/12 correct (39%); latency 4.3s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d70\n using public transportation: 3/11 correct (27%); latency 5.0s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d77\n Property destruction: freq 2\n ABC (property destruction): A = transition to non-preferred activity; B = dropped to floor, cried; C = transition delayed, preferred item offered\n\nSession 7 \u2014 2026-02-06 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 6/8 correct (77%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n washing hands independently: 11/14 correct (76%); latency 2.5s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d711\n clocking in at start of shift: 12/13 correct (91%); latency 1.7s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d72\n requesting a break during extended tasks: 11/12 correct (89%); latency 2.1s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d78\n using public transportation: 8/9 correct (90%); latency 2.1s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d75\n Property destruction: freq 2\n\nSession 8 \u2014 2026-02-08 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 4/15 correct (24%); latency 5.2s; prompts FP\u00d71, PP\u00d75, G\u00d73, I\u00d76\n washing hands independently: 3/10 correct (34%); latency 4.4s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n clocking in at start of shift: 5/15 correct (33%); latency 4.4s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d79\n requesting a break during extended tasks: 3/8 correct (43%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n using public transportation: 2/8 correct (30%); latency 4.6s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n Property destruction: freq 2\n\nSession 9 \u2014 2026-02-10 \u2014 49 min \u2014 1 observer\n requesting assistance using AAC device: 7/9 correct (81%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d72\n washing hands independently: 9/11 correct (80%); latency 2.2s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n clocking in at start of shift: 10/11 correct (94%); latency 1.9s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n requesting a break during extended tasks: 8/9 correct (94%); latency 1.6s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d77\n using public transportation: 12/13 correct (89%); latency 2.3s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d79\n Property destruction: freq 2\n ABC (property destruction): A = asked to finish dressing task; B = kicked at materials; C = task paused for 3 min\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Playing with non-task materials\n- Stereotypic behavior during inter-trial intervals\n- Looking away during SD presentation\n- Delayed responding (>5 seconds consistently)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Behavior Function Hypothesis\nProperty destruction: escape\n Evidence: ABC events in the log support the escape function; behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 56.0%.\n- Trend direction: upward (first session: 78%, last session: 81%).\n- Property destruction: mean 1.8/session (early-window mean 1.3 -> late-window mean 2.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "681f21eb7e5e1e1d", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {"Property destruction": "escape"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "adult", "n_sessions": 9, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["property_destruction"], "behavior_functions": ["escape"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "27525"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: selects items by multiple features (round and red)\nCurriculum: LRFFC L2\nLearner Level: Early Learner\nBaseline: Emerging\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by multiple features (round and red)\n- Curriculum: LRFFC L2\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: apple, plate, glue\nDistractor stimuli: towel, ball, car, book\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "44ae267c347689ef", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L2", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by multiple features (round and red)", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "crf", "error_correction": "four_step", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "55121"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3587\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Reading\nDate range: Sessions 1\u20138 across 16 days (2026-01-20 to 2026-02-05)\n\nACCELERATION PROGRAMS\n1. sounds out CVC words (Reading)\n Method: DTT\n2. requesting preferred items using a full sentence (Mand)\n Method: NET\n3. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n4. requesting a break during non-preferred tasks (Mand)\n Method: NET\n5. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: tangible\n2. Self-injurious behavior (SIB) \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-20 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 10/13 correct (74%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d79\n requesting preferred items using a full sentence: 7/13 correct (54%); latency 3.8s; prompts FP\u00d70, PP\u00d74, G\u00d73, I\u00d76\n indicating 'all done' when an activity is complete: 8/15 correct (56%); latency 3.2s; prompts FP\u00d75, PP\u00d75, G\u00d72, I\u00d73\n requesting a break during non-preferred tasks: 8/14 correct (59%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/8 correct (62%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n Tantrum: freq 2, duration 8m total\n Self-injurious behavior (SIB): freq 4\n\nSession 2 \u2014 2026-01-22 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 9/13 correct (70%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d76\n requesting preferred items using a full sentence: 7/12 correct (56%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n indicating 'all done' when an activity is complete: 6/11 correct (54%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n requesting a break during non-preferred tasks: 7/11 correct (61%); latency 3.4s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/9 correct (61%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n Tantrum: freq 2, duration 8m total\n Self-injurious behavior (SIB): freq 4\n\nSession 3 \u2014 2026-01-24 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 7/10 correct (66%); latency 2.9s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d76\n requesting preferred items using a full sentence: 7/13 correct (56%); latency 3.2s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n indicating 'all done' when an activity is complete: 7/13 correct (56%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d78\n requesting a break during non-preferred tasks: 5/8 correct (56%); latency 3.7s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/10 correct (60%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d76\n Tantrum: freq 7, duration 35m total\n Self-injurious behavior (SIB): freq 9\n\nSession 4 \u2014 2026-01-26 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 9/13 correct (71%); latency 2.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d77\n requesting preferred items using a full sentence: 8/13 correct (59%); latency 3.6s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d73\n indicating 'all done' when an activity is complete: 5/8 correct (61%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n requesting a break during non-preferred tasks: 9/14 correct (67%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d714\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/13 correct (69%); latency 2.8s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d78\n Tantrum: freq 7, duration 21m total\n Self-injurious behavior (SIB): freq 9\n\nSession 5 \u2014 2026-01-28 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 9/13 correct (70%); latency 3.1s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d74\n requesting preferred items using a full sentence: 5/10 correct (54%); latency 3.4s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n indicating 'all done' when an activity is complete: 9/15 correct (60%); latency 3.5s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d76\n requesting a break during non-preferred tasks: 10/15 correct (67%); latency 2.7s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/10 correct (70%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n Tantrum: freq 3, duration 6m total\n Self-injurious behavior (SIB): freq 3\n\nSession 6 \u2014 2026-01-30 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 7/9 correct (75%); latency 2.4s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d76\n requesting preferred items using a full sentence: 8/15 correct (54%); latency 3.6s; prompts FP\u00d72, PP\u00d75, G\u00d73, I\u00d75\n indicating 'all done' when an activity is complete: 5/8 correct (64%); latency 3.0s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n requesting a break during non-preferred tasks: 10/15 correct (69%); latency 2.8s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/9 correct (67%); latency 3.0s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n Tantrum: freq 3, duration 9m total\n Self-injurious behavior (SIB): freq 3\n\nSession 7 \u2014 2026-02-01 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 9/13 correct (72%); latency 2.8s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d74\n requesting preferred items using a full sentence: 5/9 correct (53%); latency 3.5s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n indicating 'all done' when an activity is complete: 5/9 correct (61%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d74\n requesting a break during non-preferred tasks: 6/9 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/14 correct (73%); latency 2.7s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d76\n Tantrum: freq 2, duration 8m total\n Self-injurious behavior (SIB): freq 4\n\nSession 8 \u2014 2026-02-03 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 12/15 correct (81%); latency 2.6s; prompts FP\u00d74, PP\u00d72, G\u00d75, I\u00d74\n requesting preferred items using a full sentence: 6/10 correct (62%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n indicating 'all done' when an activity is complete: 6/10 correct (59%); latency 3.4s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n requesting a break during non-preferred tasks: 8/12 correct (69%); latency 2.8s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d72\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/12 correct (74%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d75\n Tantrum: freq 2, duration 4m total\n Self-injurious behavior (SIB): freq 3\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Peer aggression (hitting or pushing peers during group activities)\n- Vocal refusal ('no', 'I don't want to')\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nTantrum: tangible\n Evidence: behavior occurs when preferred items are restricted and is followed by access to the item.\nSelf-injurious behavior (SIB): attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n### Crisis plan\n- If problem-behavior intensity or topography exceeds the learner's baseline safety threshold (SIB causing tissue damage, aggression causing injury, imminent elopement into hazard): pause the extinction procedure and implement the facility's tiered crisis-prevention protocol (e.g., Safety-Care, CPI, or equivalent).\n- De-escalation and environmental safety first; physical intervention is last resort and only by staff currently certified in the facility's framework. Least-restrictive option appropriate to the risk level applies at every step. Physical intervention is used only when specifically authorized for this learner in the BIP \u2014 contraindications (medical, developmental, trauma history) may restrict the procedures available, in which case the plan is de-escalation + environmental safety + supervisor contact only.\n- Contact the supervising BCBA immediately; do not resume the extinction procedure without BCBA review. Document duration, intensity, antecedent, staff response, and post-incident state.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 72.2%.\n- Trend direction: upward (first session: 74%, last session: 81%).\n- Tantrum: mean 3.5/session (early-window mean 2.0 -> late-window mean 2.0).\n- Self-injurious behavior (SIB): mean 4.9/session (early-window mean 4.0 -> late-window mean 3.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "3a35ed7991f57d89", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Tantrum": "tangible", "Self-injurious behavior (SIB)": "attention"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "school_age", "n_sessions": 8, "n_programs": 5, "n_behaviors": 2, "behavior_ids": ["tantrum", "sib"], "behavior_functions": ["tangible", "attention"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "20202"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: completes 8\u201312 piece puzzles\nCurriculum Reference: Visual Perceptual Skills & Matching-to-Sample L2\nLearner Profile: School-Age Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: completes 8\u201312 piece puzzles\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L2\n- Learner: School-Age Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: jacket, blanket, book\nDistractor stimuli: car, bottle, crayon, glue\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "df2e926d82f29b0f", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L2", "learner_profile": "school_age", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "completes 8\u201312 piece puzzles", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "fr2", "error_correction": "simple_correction", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "26013"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5628\nProfile: Adult Learner (18+ years)\nCurricula: Community + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u201312 across 24 days (2026-10-22 to 2026-11-15)\n\nACCELERATION PROGRAMS\n1. clocking in at start of shift (Vocational)\n Method: Task Analysis\n2. using public transportation (Community)\n Method: Task Analysis\n3. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n\nDECELERATION TARGETS\n1. Verbal aggression \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-22 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 7/9 correct (75%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d74\n using public transportation: 9/10 correct (85%); latency 2.1s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n wait calmly when a preferred activity is denied: 12/14 correct (87%); latency 2.3s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d79\n Verbal aggression: freq 0\n\nSession 2 \u2014 2026-10-24 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 2/8 correct (28%); latency 4.9s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n using public transportation: 3/9 correct (36%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d73\n wait calmly when a preferred activity is denied: 4/8 correct (47%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n Verbal aggression: freq 1\n\nSession 3 \u2014 2026-10-26 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 9/12 correct (78%); latency 2.7s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d76\n using public transportation: 9/10 correct (87%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d78\n wait calmly when a preferred activity is denied: 10/12 correct (82%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d76\n Verbal aggression: freq 1\n ABC (verbal aggression): A = adult attention diverted to another learner; B = vocalized loudly + approached staff; C = staff turned to address behavior\n\nSession 4 \u2014 2026-10-28 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 3/13 correct (25%); latency 5.1s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d76\n using public transportation: 4/8 correct (44%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n wait calmly when a preferred activity is denied: 6/12 correct (48%); latency 4.0s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d77\n Verbal aggression: freq 0\n\nSession 5 \u2014 2026-10-30 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 8/10 correct (76%); latency 2.8s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d76\n using public transportation: 11/13 correct (87%); latency 2.1s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d78\n wait calmly when a preferred activity is denied: 7/8 correct (86%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n Verbal aggression: freq 0\n\nSession 6 \u2014 2026-11-01 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 4/12 correct (35%); latency 4.2s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d711\n using public transportation: 4/11 correct (36%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 6/15 correct (41%); latency 4.4s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d79\n Verbal aggression: freq 0\n\nSession 7 \u2014 2026-11-03 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 7/9 correct (77%); latency 2.2s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n using public transportation: 13/15 correct (84%); latency 1.9s; prompts FP\u00d70, PP\u00d74, G\u00d72, I\u00d79\n wait calmly when a preferred activity is denied: 11/13 correct (87%); latency 2.1s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d78\n Verbal aggression: freq 1\n ABC (verbal aggression): A = adult attention diverted to another learner; B = vocalized loudly + approached staff; C = staff turned to address behavior\n\nSession 8 \u2014 2026-11-05 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 3/8 correct (32%); latency 4.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n using public transportation: 6/14 correct (42%); latency 4.0s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d77\n wait calmly when a preferred activity is denied: 6/13 correct (43%); latency 4.3s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d71\n Verbal aggression: freq 0\n\nSession 9 \u2014 2026-11-07 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 10/14 correct (75%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d710\n using public transportation: 8/10 correct (84%); latency 2.2s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 7/8 correct (90%); latency 1.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n Verbal aggression: freq 0\n\nSession 10 \u2014 2026-11-09 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 3/13 correct (26%); latency 4.8s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d77\n using public transportation: 6/15 correct (42%); latency 4.3s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d712\n wait calmly when a preferred activity is denied: 7/15 correct (45%); latency 3.8s; prompts FP\u00d75, PP\u00d71, G\u00d74, I\u00d75\n Verbal aggression: freq 0\n\nSession 11 \u2014 2026-11-11 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 6/8 correct (72%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n using public transportation: 8/10 correct (82%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n wait calmly when a preferred activity is denied: 11/12 correct (89%); latency 2.1s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d74\n Verbal aggression: freq 0\n\nSession 12 \u2014 2026-11-13 \u2014 44 min \u2014 1 observer\n clocking in at start of shift: 4/11 correct (33%); latency 4.6s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d75\n using public transportation: 6/13 correct (44%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d77\n wait calmly when a preferred activity is denied: 4/8 correct (49%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n Verbal aggression: freq 0\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Looking away during SD presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Generalization failure**: strong performance in training context but failure to generalize to novel conditions.\n- Skill may be under restricted stimulus control.\n\n## Pattern Classification\ngeneralization_failure\n\nAlternation between strong training performance and poor novel-condition performance indicates restricted stimulus control.\n\n## Behavior Function Hypothesis\nVerbal aggression: attention\n Evidence: ABC events in the log support the attention function; behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement structured generalization training: vary therapists, settings, and materials systematically.\n- Use multiple-exemplar training \u2014 teach with 3\u20135 different stimulus sets.\n- Program common stimuli across training and generalization settings.\n\n### Consequence strategies\n- Consider natural-environment training (NET) to supplement DTT for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 52.8%.\n- Trend direction: downward (first session: 75%, last session: 33%).\n- Verbal aggression: mean 0.2/session (early-window mean 0.5 -> late-window mean 0.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "528ab18e07269e19", "gold_labels": {"pattern_class": "generalization_failure", "behavior_functions": {"Verbal aggression": "attention"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "generalization_failure", "learner_profile": "adult", "n_sessions": 12, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["verbal_aggression"], "behavior_functions": ["attention"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "43875"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: identifies all upper-case letters\nCurriculum: Reading L2\nLearner Level: Early Learner\nBaseline: Approaching mastery\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies all upper-case letters\n- Curriculum: Reading L2\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What letter is this?\"\nVariations: \"Read this letter\"; \"What does this say?\"\nPresentation: Present the letter flashcard.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: Q, C, V\nDistractor stimuli: T, J, R, E\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "c5030be1cf3f140d", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L2", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies all upper-case letters", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "fr2", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "67967"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: tolerating hair washing by caregiver\nCurriculum Reference: AFLS Basic Living Skills\nLearner Profile: Adolescent Learner\nCurrent Mastery: Near mastery\nTeaching Method: Toleration / Systematic Desensitization\n\nThe goal is for the learner to allow the activity to be performed (not to perform it independently). Provide the full program structure including shaping steps and refusal/safety procedures."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tolerating hair washing by caregiver\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adolescent Learner\n- Current mastery: Near mastery\n- Approach: Toleration / systematic desensitization (caregiver-delivered activity)\n\nThis program builds tolerance for hair washing / shampooing performed by caregiver through systematic shaping. The learner is not being taught to perform the skill independently \u2014 the goal is to allow the caregiver or staff to perform it across an incrementally increasing duration, without refusal, crying, self-injurious behavior, or aggression.\n\n## Toleration End Goal\nfull hair-washing routine completed by caregiver without refusal or safety behaviors\n\n## Shaping Progression\nTeach by moving through these shaping steps in order. Advance to the next step only when the current step is tolerated for 3 consecutive sessions without safety behaviors.\n\n1. 5 seconds of water on hair\n2. 15 seconds of water on hair\n3. Shampoo applied without lathering\n4. 30 seconds of gentle lathering\n5. 60 seconds of lathering\n6. Full rinse\n7. Full routine: wet -> shampoo -> lather -> rinse\n\nCurrent shaping step: At the near mastery stage, begin at shaping step 4 (\"30 seconds of gentle lathering\") and advance through step 5 across sessions as tolerance stabilizes.\n\n## Antecedent Strategies\n- Pre-warn the learner before the activity begins (verbal or visual schedule).\n- Offer a preferred item or sensory tool to hold during the activity.\n- Where possible, offer a choice of position, location, or starting point.\n- Keep the environment calm and predictable; avoid other demands immediately before or after.\n\n## Reinforcement\nDeliver high-magnitude, high-preference reinforcement contingent on successful toleration of the target duration. Pair with effusive praise. Reinforcement is continuous (CRF) during acquisition of each shaping step.\n\n## Refusal and Safety Procedures\n- If the learner refuses or turns away: pause briefly (5\u201310 seconds), re-present the activity at the current or previous shaping step.\n- If problem behavior (crying, property destruction, SIB, aggression, peer aggression) emerges: stop the activity immediately, implement the facility crisis plan, and document the incident.\n- Do NOT remove the activity contingent on safety behaviors in a way that establishes an escape-maintained pattern \u2014 consult supervising BCBA for the specific escape-extinction protocol appropriate to this learner.\n\n## Mastery Criteria\nEnd-goal duration tolerated across 3 consecutive sessions with no safety behaviors (refusal, crying, SIB, aggression, property destruction).\n\n## Data Collection\nPer-trial: duration tolerated before refusal, presence / absence of safety behaviors (crying, property destruction, SIB, aggression), staff support level, and shaping step attempted. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full routine across 3 different settings and with 2 different adults (including the primary caregiver if relevant). Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "ca0ed5017900e8bb", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "tolerating hair washing by caregiver", "program_type": "toleration", "learner_profile": "adolescent", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_toleration_v1", "taxonomy_cells": {"skill_target": "tolerating hair washing by caregiver", "module": "basic_living", "mastery_criterion": "mc_toleration_full_duration", "shaping_n_steps": 7}, "teacher_model": null, "seed_tag": "6035"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: selects items by negative features (not round, not food)\nCurriculum: LRFFC L3\nLearner: Adolescent Learner\nMastery Status: Mastered at current level\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by negative features (not round, not food)\n- Curriculum: LRFFC L3\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: spoon, block, scissors\nDistractor stimuli: car, blanket, glue, phone, hat\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "415529e159dc7106", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L3", "learner_profile": "adolescent", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by negative features (not round, not food)", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "vr3", "error_correction": "simple_correction", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "89319"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: completing assigned tasks in order\nCurriculum: AFLS Vocational Skills\nLearner: Adolescent Learner\nMastery Status: Near mastery\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: completing assigned tasks in order\n- Curriculum: AFLS Vocational Skills\n- Learner: Adolescent Learner\n- Current mastery: Near mastery\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Backward chaining\nComplete all steps for the learner except the last; teach the last step first, then work backward. The final reinforcer (task completion) is always present for the learner.\n\nSteps:\n1. Review the task list for the shift.\n2. Gather needed materials for the first task.\n3. Complete the first task to the specified standard.\n4. Mark the first task complete on the list.\n5. Return materials to storage.\n6. Move to the next task on the list and repeat. <- Learner-taught step (backward chaining starts here)\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the near mastery stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nToken economy \u2014 One token per correctly-completed step; token exchange at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "64242a99c9db119a", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "completing assigned tasks in order", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "near", "chain_type": "backward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "completing assigned tasks in order", "module": "vocational", "mastery_criterion": "mc_self_initiation", "chain_type": "backward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "6490"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: selects items by feature (find something red)\nCurriculum: Listener Responding L2\nLearner: Early Learner\nMastery Status: Approaching mastery\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by feature (find something red)\n- Curriculum: Listener Responding L2\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: sock, hat, glue\nDistractor stimuli: backpack, block, car, book\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "192bece913e456b9", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L2", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by feature (find something red)", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "fr2", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "70400"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: selects items by class with exclusion (animal but not a pet)\nCurriculum: LRFFC L3\nLearner: Adolescent Learner\nMastery Status: Mastered at current level\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by class with exclusion (animal but not a pet)\n- Curriculum: LRFFC L3\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: cow, dog, horse\nDistractor stimuli: lion, cat, frog, bird, pig\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% first-trial-correct across 5 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "73c028cd108ed571", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L3", "learner_profile": "adolescent", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by class with exclusion (animal but not a pet)", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "vr3", "error_correction": "transfer_trial", "mastery_criterion": "mc_90_first_trial"}, "teacher_model": null, "seed_tag": "87673"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: initiates social interactions with peers\nCurriculum Reference: Social Behavior & Social Play L2\nLearner Profile: Early Learner\nCurrent Mastery: Generalization phase\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: initiates social interactions with peers\n- Curriculum: Social Behavior & Social Play L2\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: shared snack.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's shared snack routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the generalization stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "384001046494b09e", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L2", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "initiates social interactions with peers", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "75835"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5920\nProfile: Adult Learner (18+ years)\nCurricula: Community + Independent Living + Self-Care + Vocational\nDate range: Sessions 1\u20139 across 18 days (2026-02-04 to 2026-02-22)\n\nACCELERATION PROGRAMS\n1. self-advocacy statements (Independent Living)\n Method: BST\n2. scheduling medical appointments (Independent Living)\n Method: Task Analysis\n3. washing hands independently (Self-Care)\n Method: Task Analysis\n4. clocking in at start of shift (Vocational)\n Method: Task Analysis\n5. using public transportation (Community)\n Method: Task Analysis\n6. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-04 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 5/11 correct (49%); latency 4.1s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n scheduling medical appointments: 7/15 correct (45%); latency 3.9s; prompts FP\u00d75, PP\u00d73, G\u00d73, I\u00d74\n washing hands independently: 7/15 correct (45%); latency 3.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d713\n clocking in at start of shift: 6/14 correct (43%); latency 4.2s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d78\n using public transportation: 3/8 correct (34%); latency 4.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n completing assigned tasks in order: 6/14 correct (42%); latency 4.3s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d76\n\nSession 2 \u2014 2026-02-06 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 5/9 correct (53%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d76\n scheduling medical appointments: 6/13 correct (49%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d711\n washing hands independently: 5/9 correct (55%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n clocking in at start of shift: 7/15 correct (50%); latency 3.9s; prompts FP\u00d75, PP\u00d74, G\u00d70, I\u00d76\n using public transportation: 3/8 correct (37%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n completing assigned tasks in order: 8/15 correct (51%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d714\n\nSession 3 \u2014 2026-02-08 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 7/12 correct (58%); latency 3.5s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d77\n scheduling medical appointments: 7/12 correct (57%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d77\n washing hands independently: 6/10 correct (61%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n clocking in at start of shift: 6/11 correct (55%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n using public transportation: 6/12 correct (47%); latency 4.0s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d76\n completing assigned tasks in order: 4/8 correct (56%); latency 3.7s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n\nSession 4 \u2014 2026-02-10 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 8/12 correct (65%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d73\n scheduling medical appointments: 9/15 correct (62%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d711\n washing hands independently: 9/12 correct (71%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d77\n clocking in at start of shift: 6/9 correct (65%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n using public transportation: 7/14 correct (50%); latency 3.8s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d710\n completing assigned tasks in order: 6/11 correct (57%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n\nSession 5 \u2014 2026-02-12 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 6/8 correct (74%); latency 2.4s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n scheduling medical appointments: 9/13 correct (69%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d76\n washing hands independently: 7/9 correct (76%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n clocking in at start of shift: 6/9 correct (71%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d72\n using public transportation: 5/8 correct (59%); latency 3.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n completing assigned tasks in order: 8/12 correct (67%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d78\n\nSession 6 \u2014 2026-02-14 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 11/14 correct (79%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d711\n scheduling medical appointments: 10/14 correct (71%); latency 2.7s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d77\n washing hands independently: 11/13 correct (83%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d79\n clocking in at start of shift: 6/8 correct (76%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n using public transportation: 7/10 correct (65%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d79\n completing assigned tasks in order: 10/15 correct (66%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d75, I\u00d78\n\nSession 7 \u2014 2026-02-16 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 11/13 correct (82%); latency 2.1s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d712\n scheduling medical appointments: 8/11 correct (75%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n washing hands independently: 10/11 correct (93%); latency 1.6s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n clocking in at start of shift: 10/12 correct (84%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d75\n using public transportation: 9/14 correct (67%); latency 3.1s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d74\n completing assigned tasks in order: 7/9 correct (75%); latency 2.7s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n\nSession 8 \u2014 2026-02-18 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 9/9 correct (95%); latency 1.4s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n scheduling medical appointments: 12/15 correct (83%); latency 2.5s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d710\n washing hands independently: 12/13 correct (95%); latency 1.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d711\n clocking in at start of shift: 14/15 correct (91%); latency 2.2s; prompts FP\u00d74, PP\u00d73, G\u00d75, I\u00d73\n using public transportation: 8/11 correct (77%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d76\n completing assigned tasks in order: 7/9 correct (73%); latency 2.6s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d75\n\nSession 9 \u2014 2026-02-20 \u2014 51 min \u2014 1 observer\n self-advocacy statements: 8/8 correct (95%); latency 1.9s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n scheduling medical appointments: 9/11 correct (86%); latency 2.0s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d76\n washing hands independently: 10/11 correct (95%); latency 1.8s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n clocking in at start of shift: 10/10 correct (95%); latency 1.8s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d76\n using public transportation: 7/9 correct (80%); latency 2.6s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n completing assigned tasks in order: 9/11 correct (82%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d73\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Smiling during reinforcement delivery\n- Appropriate sitting posture maintained"}, {"role": "assistant", "content": "## Clinical Concerns\n- Steady improvement: accuracy rose from 49% to 95% across 9 sessions.\n- No clinical concerns at this time; mastery criteria should be reachable within a few additional sessions.\n\n## Pattern Classification\nmastery_progression\n\nAccuracy is ascending cleanly across sessions with no interfering behaviors, consistent with a mastery-progression trajectory.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Continue current teaching procedure \u2014 it is effective for this learner.\n- Maintain current stimulus arrangement; begin planning next skill in sequence.\n\n### Consequence strategies\n- Begin thinning reinforcement from CRF to FR-2 as accuracy stabilizes above 85%.\n- Continue differential reinforcement for independent responses.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 72.4%.\n- Trend direction: upward (first session: 49%, last session: 95%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "ada523a1b619f056", "gold_labels": {"pattern_class": "mastery_progression", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "mastery_progression", "learner_profile": "adult", "n_sessions": 9, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "82738"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4848\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Reading + Social Behavior\nDate range: Sessions 1\u20138 across 16 days (2026-09-28 to 2026-10-14)\n\nACCELERATION PROGRAMS\n1. identifies numerals 1\u201320 (Math)\n Method: DTT\n2. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n3. takes turns during structured activities (Social Behavior)\n Method: PRT\n4. requesting a break during non-preferred tasks (Mand)\n Method: NET\n5. requesting preferred items using a full sentence (Mand)\n Method: NET\n6. reads 10\u201320 sight words (Reading)\n Method: DTT\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-28 \u2014 37 min \u2014 1 observer\n identifies numerals 1\u201320: 7/9 correct (74%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/9 correct (86%); latency 2.0s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n takes turns during structured activities: 9/12 correct (78%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d79\n requesting a break during non-preferred tasks: 12/15 correct (77%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d710\n requesting preferred items using a full sentence: 13/15 correct (84%); latency 2.3s; prompts FP\u00d75, PP\u00d71, G\u00d72, I\u00d77\n reads 10\u201320 sight words: 9/12 correct (74%); latency 2.8s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d76\n\nSession 2 \u2014 2026-09-30 \u2014 37 min \u2014 1 observer\n identifies numerals 1\u201320: 9/12 correct (77%); latency 2.8s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 11/13 correct (88%); latency 2.0s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d79\n takes turns during structured activities: 9/11 correct (81%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n requesting a break during non-preferred tasks: 12/15 correct (81%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d714\n requesting preferred items using a full sentence: 12/14 correct (84%); latency 2.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d711\n reads 10\u201320 sight words: 11/14 correct (78%); latency 2.2s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d74\n\nSession 3 \u2014 2026-10-02 \u2014 37 min \u2014 1 observer\n identifies numerals 1\u201320: 10/14 correct (75%); latency 2.8s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/10 correct (85%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d78\n takes turns during structured activities: 6/8 correct (78%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n requesting a break during non-preferred tasks: 9/10 correct (85%); latency 2.0s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d76\n requesting preferred items using a full sentence: 8/9 correct (85%); latency 2.5s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n reads 10\u201320 sight words: 11/14 correct (79%); latency 2.3s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d79\n\nSession 4 \u2014 2026-10-04 \u2014 37 min \u2014 1 observer\n identifies numerals 1\u201320: 10/13 correct (78%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d711\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/10 correct (88%); latency 2.2s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n takes turns during structured activities: 10/12 correct (82%); latency 2.2s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d73\n requesting a break during non-preferred tasks: 8/9 correct (86%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d76\n requesting preferred items using a full sentence: 8/9 correct (91%); latency 1.7s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n reads 10\u201320 sight words: 8/10 correct (80%); latency 2.5s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n\nSession 5 \u2014 2026-10-06 \u2014 37 min \u2014 1 observer\n identifies numerals 1\u201320: 8/11 correct (77%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/8 correct (81%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n takes turns during structured activities: 9/11 correct (82%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n requesting a break during non-preferred tasks: 8/10 correct (84%); latency 2.3s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d72\n requesting preferred items using a full sentence: 7/8 correct (93%); latency 1.8s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n reads 10\u201320 sight words: 12/15 correct (81%); latency 2.5s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d76\n\nSession 6 \u2014 2026-10-08 \u2014 37 min \u2014 1 observer\n identifies numerals 1\u201320: 7/8 correct (82%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/11 correct (81%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d77\n takes turns during structured activities: 11/13 correct (81%); latency 2.5s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d74\n requesting a break during non-preferred tasks: 7/8 correct (86%); latency 2.3s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n requesting preferred items using a full sentence: 8/9 correct (91%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d76\n reads 10\u201320 sight words: 6/8 correct (80%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n\nSession 7 \u2014 2026-10-10 \u2014 37 min \u2014 1 observer\n identifies numerals 1\u201320: 6/8 correct (81%); latency 2.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/12 correct (83%); latency 2.2s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n takes turns during structured activities: 12/14 correct (84%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d78\n requesting a break during non-preferred tasks: 12/14 correct (88%); latency 2.3s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d75\n requesting preferred items using a full sentence: 8/9 correct (89%); latency 2.3s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n reads 10\u201320 sight words: 7/8 correct (84%); latency 2.2s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n\nSession 8 \u2014 2026-10-12 \u2014 37 min \u2014 1 observer\n identifies numerals 1\u201320: 9/11 correct (81%); latency 2.4s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 11/13 correct (81%); latency 2.3s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d79\n takes turns during structured activities: 7/8 correct (86%); latency 1.9s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n requesting a break during non-preferred tasks: 10/11 correct (92%); latency 1.9s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n requesting preferred items using a full sentence: 11/12 correct (93%); latency 2.0s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d77\n reads 10\u201320 sight words: 8/10 correct (83%); latency 2.0s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d78\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Stereotypic behavior during inter-trial intervals\n- Looking away during SD presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (74%\u201381%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 78.1%.\n- Trend direction: upward (first session: 74%, last session: 81%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "74a6988f11847ff8", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "school_age", "n_sessions": 8, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "83942"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: spontaneously asks questions about the environment\nCurriculum: Spontaneous Vocal Behavior L2\nLearner: Early Learner\nMastery Status: Mastered at current level\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously asks questions about the environment\n- Curriculum: Spontaneous Vocal Behavior L2\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: activity setup.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's activity setup routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the mastered stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nAverage rate of \u2265 3 spontaneous responses per 30-minute session across 3 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "93d21e0d53ad53eb", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L2", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously asks questions about the environment", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_spontaneous_rate"}, "teacher_model": null, "seed_tag": "77480"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9879\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Mand + Motor Imitation + Writing\nDate range: Sessions 1\u20139 across 18 days (2026-05-03 to 2026-05-21)\n\nACCELERATION PROGRAMS\n1. copies simple words from model (Writing)\n Method: DTT\n2. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n3. selects items by feature (Listener Responding)\n Method: DTT\n4. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n5. imitates 3-step motor sequences (Motor Imitation)\n Method: DTT variant\n\nDECELERATION TARGETS\n1. Elopement \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-03 \u2014 47 min \u2014 1 observer\n copies simple words from model: 12/15 correct (81%); latency 2.4s; prompts FP\u00d74, PP\u00d75, G\u00d74, I\u00d72\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/8 correct (87%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n selects items by feature: 10/12 correct (82%); latency 2.1s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 8/11 correct (76%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n imitates 3-step motor sequences: 10/13 correct (79%); latency 2.7s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d72\n Elopement: freq 2\n\nSession 2 \u2014 2026-05-05 \u2014 47 min \u2014 1 observer\n copies simple words from model: 7/10 correct (74%); latency 2.5s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/10 correct (82%); latency 2.1s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d77\n selects items by feature: 6/9 correct (72%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d77\n requesting a break ('break please' or AAC 'I need a break'): 9/12 correct (74%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d78\n imitates 3-step motor sequences: 8/11 correct (77%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n Elopement: freq 2\n\nSession 3 \u2014 2026-05-07 \u2014 47 min \u2014 1 observer\n copies simple words from model: 5/8 correct (68%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/11 correct (78%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n selects items by feature: 7/10 correct (67%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 5/8 correct (67%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n imitates 3-step motor sequences: 8/12 correct (66%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d74\n Elopement: freq 3\n\nSession 4 \u2014 2026-05-09 \u2014 47 min \u2014 1 observer\n copies simple words from model: 7/10 correct (66%); latency 3.3s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d74\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/8 correct (69%); latency 2.8s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n selects items by feature: 7/12 correct (57%); latency 3.6s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 6/10 correct (55%); latency 3.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d78\n imitates 3-step motor sequences: 10/15 correct (68%); latency 2.8s; prompts FP\u00d74, PP\u00d75, G\u00d74, I\u00d72\n Elopement: freq 3\n\nSession 5 \u2014 2026-05-11 \u2014 47 min \u2014 1 observer\n copies simple words from model: 5/9 correct (59%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/13 correct (63%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d79\n selects items by feature: 5/11 correct (49%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 4/9 correct (48%); latency 3.8s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n imitates 3-step motor sequences: 7/13 correct (53%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d711\n Elopement: freq 5\n\nSession 6 \u2014 2026-05-13 \u2014 47 min \u2014 1 observer\n copies simple words from model: 6/12 correct (49%); latency 4.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d79\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 8/14 correct (58%); latency 3.5s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d710\n selects items by feature: 6/15 correct (40%); latency 4.2s; prompts FP\u00d75, PP\u00d71, G\u00d73, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 5/11 correct (42%); latency 3.9s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d79\n imitates 3-step motor sequences: 6/12 correct (52%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d79\n Elopement: freq 4\n\nSession 7 \u2014 2026-05-15 \u2014 47 min \u2014 1 observer\n copies simple words from model: 3/8 correct (43%); latency 4.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/9 correct (58%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n selects items by feature: 3/10 correct (32%); latency 4.7s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 6/15 correct (39%); latency 4.3s; prompts FP\u00d73, PP\u00d74, G\u00d72, I\u00d76\n imitates 3-step motor sequences: 4/8 correct (51%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n Elopement: freq 4\n\nSession 8 \u2014 2026-05-17 \u2014 47 min \u2014 1 observer\n copies simple words from model: 4/11 correct (38%); latency 4.1s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/14 correct (51%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d77\n selects items by feature: 3/9 correct (33%); latency 4.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 4/12 correct (30%); latency 4.4s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d76\n imitates 3-step motor sequences: 4/9 correct (46%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n Elopement: freq 5\n\nSession 9 \u2014 2026-05-19 \u2014 47 min \u2014 1 observer\n copies simple words from model: 3/8 correct (35%); latency 4.3s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/13 correct (46%); latency 4.0s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d77\n selects items by feature: 3/14 correct (18%); latency 5.1s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d76\n requesting a break ('break please' or AAC 'I need a break'): 3/11 correct (26%); latency 4.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n imitates 3-step motor sequences: 3/9 correct (37%); latency 4.4s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n Elopement: freq 6\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Attempts at property destruction (throwing materials, swiping items off the surface)\n- Elopement from the work area\n- Pushing materials away from the work area"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (81% -> 35%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nElopement: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 57.1%.\n- Trend direction: downward (first session: 81%, last session: 35%).\n- Elopement: mean 3.8/session (early-window mean 2.3 -> late-window mean 5.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "cbdf4b89769de62b", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Elopement": "escape"}, "escalation_level": 4, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "early", "n_sessions": 9, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["elopement"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "20942"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: taking medication as prescribed\nCurriculum Reference: AFLS Independent Living Skills\nLearner Profile: Adult Learner\nCurrent Mastery: Generalization phase\nTeaching Method: Task Analysis / Chaining\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: taking medication as prescribed\n- Curriculum: AFLS Independent Living Skills\n- Learner: Adult Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Check the medication schedule at the scheduled time. <- Learner-taught step (forward chaining starts here)\n2. Collect the correct medication bottle.\n3. Confirm the dose against the label.\n4. Measure or count the correct dose.\n5. Take the medication with water.\n6. Log the dose in the medication tracker.\n7. Return the bottle to its storage location.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "fe5e7f4a54c58cfb", "gold_labels": {"method": "task_analysis", "domain": "AFLS.independent_living", "skill": "taking medication as prescribed", "program_type": "independence", "learner_profile": "adult", "mastery_state": "generalization", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "taking medication as prescribed", "module": "independent_living", "mastery_criterion": "mc_self_initiation", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "75542"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4370\nProfile: Adult Learner (18+ years)\nCurricula: Independent Living + Vocational\nDate range: Sessions 1\u201312 across 24 days (2026-04-11 to 2026-05-05)\n\nACCELERATION PROGRAMS\n1. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n2. managing a budget (Independent Living)\n Method: Task Analysis\n3. scheduling medical appointments (Independent Living)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Property destruction \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-11 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 10/13 correct (75%); latency 2.8s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d72\n managing a budget: 8/11 correct (75%); latency 2.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n scheduling medical appointments: 12/14 correct (86%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d711\n Property destruction: freq 1\n ABC (property destruction): A = adult attention diverted to another learner; B = vocalized loudly + approached staff; C = staff turned to address behavior\n\nSession 2 \u2014 2026-04-13 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 8/12 correct (66%); latency 3.2s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d73\n managing a budget: 6/9 correct (67%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d72\n scheduling medical appointments: 8/10 correct (77%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d76\n Property destruction: freq 2\n\nSession 3 \u2014 2026-04-15 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 8/13 correct (65%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d74\n managing a budget: 8/14 correct (59%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d712\n scheduling medical appointments: 12/15 correct (79%); latency 2.3s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d77\n Property destruction: freq 1\n\nSession 4 \u2014 2026-04-17 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 9/15 correct (59%); latency 3.4s; prompts FP\u00d73, PP\u00d75, G\u00d74, I\u00d73\n managing a budget: 8/14 correct (58%); latency 3.7s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d77\n scheduling medical appointments: 7/11 correct (67%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d710\n Property destruction: freq 2\n ABC (property destruction): A = adult attention diverted to another learner; B = vocalized loudly + approached staff; C = staff turned to address behavior\n\nSession 5 \u2014 2026-04-19 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 6/12 correct (54%); latency 3.4s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d77\n managing a budget: 3/8 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n scheduling medical appointments: 8/13 correct (61%); latency 3.0s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d75\n Property destruction: freq 3\n\nSession 6 \u2014 2026-04-21 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 5/10 correct (54%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d78\n managing a budget: 4/10 correct (42%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n scheduling medical appointments: 5/9 correct (59%); latency 3.5s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n Property destruction: freq 3\n\nSession 7 \u2014 2026-04-23 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 6/14 correct (45%); latency 4.2s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d79\n managing a budget: 4/13 correct (31%); latency 4.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d78\n scheduling medical appointments: 5/9 correct (60%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n Property destruction: freq 3\n ABC (property destruction): A = staff engaged in paperwork nearby; B = yelled name + tapped staff; C = staff attended and redirected\n\nSession 8 \u2014 2026-04-25 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 4/9 correct (45%); latency 4.2s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d71\n managing a budget: 4/14 correct (26%); latency 4.8s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d78\n scheduling medical appointments: 7/13 correct (52%); latency 3.5s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n Property destruction: freq 3\n\nSession 9 \u2014 2026-04-27 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 4/11 correct (37%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n managing a budget: 2/9 correct (22%); latency 4.8s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n scheduling medical appointments: 6/13 correct (48%); latency 4.0s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d77\n Property destruction: freq 3\n\nSession 10 \u2014 2026-04-29 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 3/12 correct (27%); latency 5.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d710\n managing a budget: 1/8 correct (17%); latency 5.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n scheduling medical appointments: 5/13 correct (38%); latency 4.2s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d78\n Property destruction: freq 3\n\nSession 11 \u2014 2026-05-01 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 2/8 correct (22%); latency 5.2s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n managing a budget: 1/11 correct (10%); latency 5.8s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n scheduling medical appointments: 4/10 correct (40%); latency 4.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d76\n Property destruction: freq 5\n\nSession 12 \u2014 2026-05-03 \u2014 56 min \u2014 1 observer\n completing assigned tasks in order: 2/10 correct (18%); latency 5.3s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d78\n managing a budget: 1/11 correct (10%); latency 5.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n scheduling medical appointments: 4/12 correct (37%); latency 4.2s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d78\n Property destruction: freq 4\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Self-stimulatory behavior increase during demand periods\n- Elopement from the work area\n- Crying during demand presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 75% to 18% across 12 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nProperty destruction: attention\n Evidence: ABC events in the log support the attention function; behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 47.3%.\n- Trend direction: downward (first session: 75%, last session: 18%).\n- Property destruction: mean 2.8/session (early-window mean 1.5 -> late-window mean 3.8).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "d4c4852748046c1f", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Property destruction": "attention"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "adult", "n_sessions": 12, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["property_destruction"], "behavior_functions": ["attention"], "has_abc_data": true, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "71491"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: identifies coins by name\nCurriculum: Math L2\nLearner Level: Early Learner\nBaseline: Approaching mastery\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies coins by name\n- Curriculum: Math L2\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What number is this?\"\nVariations: \"Which number?\"; \"Tell me the number\"\nPresentation: Present the numeral card.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: book, phone, cup\nDistractor stimuli: brush, sock, plate, car\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "0f6185c89d45e3f4", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L2", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies coins by name", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "crf", "error_correction": "simple_correction", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "20226"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: negotiates and compromises during group activities\nCurriculum Reference: Social Behavior & Social Play L3\nLearner Profile: School-Age Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: negotiates and compromises during group activities\n- Curriculum: Social Behavior & Social Play L3\n- Learner: School-Age Learner\n- Current mastery: Approaching mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: circle time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's circle time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the approaching mastery stage, use time delay (0 s -> 2 s -> 4 s) before delivering any model prompt; reinforce independent responses differentially.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "dcc3298d58b6c0c6", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L3", "learner_profile": "school_age", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "negotiates and compromises during group activities", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "time_delay", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "30191"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3264\nProfile: Adult Learner (18+ years)\nCurricula: Independent Living + Mand + Self-Care\nDate range: Sessions 1\u20139 across 18 days (2026-07-06 to 2026-07-24)\n\nACCELERATION PROGRAMS\n1. washing hands independently (Self-Care)\n Method: Task Analysis\n2. self-advocacy statements (Independent Living)\n Method: BST\n3. requesting a break during extended tasks (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Vocal stereotypy \u2014 function hypothesized: automatic\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-06 \u2014 40 min \u2014 1 observer\n washing hands independently: 6/14 correct (46%); latency 3.9s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d79\n self-advocacy statements: 5/10 correct (47%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d77\n requesting a break during extended tasks: 8/11 correct (73%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n Vocal stereotypy: freq 0; PIR 2%\n\nSession 2 \u2014 2026-07-08 \u2014 40 min \u2014 1 observer\n washing hands independently: 4/9 correct (49%); latency 4.0s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n self-advocacy statements: 6/8 correct (70%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n requesting a break during extended tasks: 6/9 correct (72%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d77\n Vocal stereotypy: freq 3; PIR 19%\n\nSession 3 \u2014 2026-07-10 \u2014 40 min \u2014 1 observer\n washing hands independently: 6/9 correct (72%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n self-advocacy statements: 10/14 correct (71%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d713\n requesting a break during extended tasks: 7/12 correct (59%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d75\n Vocal stereotypy: freq 4; PIR 21%\n\nSession 4 \u2014 2026-07-12 \u2014 40 min \u2014 1 observer\n washing hands independently: 5/14 correct (34%); latency 4.5s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n self-advocacy statements: 9/15 correct (62%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d710\n requesting a break during extended tasks: 9/15 correct (62%); latency 3.5s; prompts FP\u00d75, PP\u00d73, G\u00d72, I\u00d75\n Vocal stereotypy: freq 1; PIR 9%\n\nSession 5 \u2014 2026-07-14 \u2014 IOA SESSION \u2014 2 observers\n washing hands independently: 58% (primary); IOA 91% agreement\n self-advocacy statements: 40% (primary); IOA 91% agreement\n requesting a break during extended tasks: 51% (primary); IOA 91% agreement\n Vocal stereotypy: freq 4; PIR 20%; IOA 91% agreement\n\nSession 6 \u2014 2026-07-16 \u2014 40 min \u2014 1 observer\n washing hands independently: 4/8 correct (47%); latency 3.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n self-advocacy statements: 8/12 correct (68%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d79\n requesting a break during extended tasks: 7/10 correct (74%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n Vocal stereotypy: freq 2; PIR 17%\n\nSession 7 \u2014 2026-07-18 \u2014 40 min \u2014 1 observer\n washing hands independently: 9/13 correct (70%); latency 2.7s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n self-advocacy statements: 6/10 correct (55%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d73\n requesting a break during extended tasks: 9/11 correct (78%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d75\n Vocal stereotypy: freq 4; PIR 28%\n\nSession 8 \u2014 2026-07-20 \u2014 40 min \u2014 1 observer\n washing hands independently: 10/15 correct (68%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d712\n self-advocacy statements: 7/11 correct (61%); latency 3.0s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n requesting a break during extended tasks: 5/8 correct (63%); latency 2.9s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n Vocal stereotypy: freq 1; PIR 3%\n\nSession 9 \u2014 2026-07-22 \u2014 40 min \u2014 1 observer\n washing hands independently: 6/15 correct (43%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d76\n self-advocacy statements: 7/11 correct (65%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n requesting a break during extended tasks: 7/12 correct (54%); latency 3.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d76\n Vocal stereotypy: freq 2; PIR 9%\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Stereotypic behavior during inter-trial intervals\n- Leaving seat without permission\n- Playing with non-task materials\n- Echolalic responding (repeating SD rather than answering)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 45% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Behavior Function Hypothesis\nVocal stereotypy: automatic\n Evidence: behavior persists across contexts without clear social mediation.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 9 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 54.2%.\n- Trend direction: downward (first session: 46%, last session: 43%).\n- Vocal stereotypy: mean 2.3/session (early-window mean 2.3 -> late-window mean 2.3).\n- IOA data: 91% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "1d8c7a27726d1f40", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {"Vocal stereotypy": "automatic"}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "adult", "n_sessions": 9, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["vocal_stereotypy"], "behavior_functions": ["automatic"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "20321"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4052\nProfile: Adult Learner (18+ years)\nCurricula: Self-Care + Vocational\nDate range: Sessions 1\u20137 across 14 days (2026-02-06 to 2026-02-20)\n\nACCELERATION PROGRAMS\n1. clocking in at start of shift (Vocational)\n Method: Task Analysis\n2. washing hands independently (Self-Care)\n Method: Task Analysis\n3. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-06 \u2014 35 min \u2014 1 observer\n clocking in at start of shift: 3/8 correct (33%); latency 4.5s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n washing hands independently: 3/12 correct (27%); latency 4.5s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d75\n dressing (pants, shirt): 3/13 correct (25%); latency 5.1s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d77\n\nSession 2 \u2014 2026-02-08 \u2014 35 min \u2014 1 observer\n clocking in at start of shift: 4/9 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n washing hands independently: 4/11 correct (40%); latency 4.3s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n dressing (pants, shirt): 4/11 correct (33%); latency 4.6s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d75\n\nSession 3 \u2014 2026-02-10 \u2014 35 min \u2014 1 observer\n clocking in at start of shift: 4/9 correct (49%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n washing hands independently: 7/15 correct (45%); latency 4.2s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d76\n dressing (pants, shirt): 4/9 correct (40%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n\nSession 4 \u2014 2026-02-12 \u2014 35 min \u2014 1 observer\n clocking in at start of shift: 5/10 correct (53%); latency 3.4s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n washing hands independently: 9/15 correct (57%); latency 3.2s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d78\n dressing (pants, shirt): 7/14 correct (51%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d77\n\nSession 5 \u2014 2026-02-14 \u2014 35 min \u2014 1 observer\n clocking in at start of shift: 7/12 correct (62%); latency 3.1s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d74\n washing hands independently: 7/11 correct (66%); latency 2.9s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n dressing (pants, shirt): 6/10 correct (61%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d75\n\nSession 6 \u2014 2026-02-16 \u2014 35 min \u2014 1 observer\n clocking in at start of shift: 10/15 correct (70%); latency 2.9s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d711\n washing hands independently: 8/10 correct (78%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n dressing (pants, shirt): 10/15 correct (65%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d714\n\nSession 7 \u2014 2026-02-18 \u2014 35 min \u2014 1 observer\n clocking in at start of shift: 9/12 correct (78%); latency 2.3s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d74\n washing hands independently: 7/8 correct (88%); latency 1.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n dressing (pants, shirt): 10/14 correct (72%); latency 2.5s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d712\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Reaching for materials proactively\n- Eye contact maintained throughout trials\n- Quick response latency (within 2\u20133 seconds)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 33% to 78% across 7 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 55.3%.\n- Trend direction: upward (first session: 33%, last session: 78%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "b46965baacde72dd", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "adult", "n_sessions": 7, "n_programs": 3, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "96053"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4608\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Mand + Self-Care\nDate range: Sessions 1\u20137 across 14 days (2026-04-07 to 2026-04-21)\n\nACCELERATION PROGRAMS\n1. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n2. requesting help when a task is difficult (Mand)\n Method: NET\n3. brushing teeth independently (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Non-compliance \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-07 \u2014 45 min \u2014 1 observer\n dressing (pants, shirt): 4/8 correct (46%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n requesting help when a task is difficult: 6/12 correct (50%); latency 3.6s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d75\n brushing teeth independently: 6/15 correct (38%); latency 4.6s; prompts FP\u00d75, PP\u00d74, G\u00d73, I\u00d73\n Non-compliance: freq 2\n\nSession 2 \u2014 2026-04-09 \u2014 45 min \u2014 1 observer\n dressing (pants, shirt): 6/12 correct (54%); latency 3.6s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n requesting help when a task is difficult: 7/11 correct (60%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d78\n brushing teeth independently: 5/10 correct (48%); latency 4.0s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d76\n Non-compliance: freq 2\n\nSession 3 \u2014 2026-04-11 \u2014 45 min \u2014 1 observer\n dressing (pants, shirt): 7/11 correct (62%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n requesting help when a task is difficult: 7/10 correct (66%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d75\n brushing teeth independently: 6/11 correct (57%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d79\n Non-compliance: freq 2\n\nSession 4 \u2014 2026-04-13 \u2014 45 min \u2014 1 observer\n dressing (pants, shirt): 8/11 correct (72%); latency 2.8s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d77\n requesting help when a task is difficult: 10/13 correct (76%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d77\n brushing teeth independently: 10/14 correct (68%); latency 2.9s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d78\n Non-compliance: freq 2\n\nSession 5 \u2014 2026-04-15 \u2014 45 min \u2014 1 observer\n dressing (pants, shirt): 9/11 correct (78%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n requesting help when a task is difficult: 9/11 correct (83%); latency 2.4s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d75\n brushing teeth independently: 9/12 correct (76%); latency 2.7s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d75\n Non-compliance: freq 2\n\nSession 6 \u2014 2026-04-17 \u2014 45 min \u2014 1 observer\n dressing (pants, shirt): 7/9 correct (82%); latency 2.2s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d71\n requesting help when a task is difficult: 8/9 correct (84%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d77\n brushing teeth independently: 11/14 correct (76%); latency 2.5s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d78\n Non-compliance: freq 1\n\nSession 7 \u2014 2026-04-19 \u2014 45 min \u2014 1 observer\n dressing (pants, shirt): 11/13 correct (82%); latency 2.4s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d74\n requesting help when a task is difficult: 11/13 correct (84%); latency 2.4s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d75\n brushing teeth independently: 10/13 correct (76%); latency 2.3s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d76\n Non-compliance: freq 3\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 46% at return, recovering to 82%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Behavior Function Hypothesis\nNon-compliance: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 67.8%.\n- Trend direction: upward (first session: 46%, last session: 82%).\n- Non-compliance: mean 2.0/session (early-window mean 2.0 -> late-window mean 2.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "2ed1e4d10b470ad7", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {"Non-compliance": "escape"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "adolescent", "n_sessions": 7, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["non_compliance"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "99687"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: responds to own name\nCurriculum: Social Behavior & Social Play L1\nLearner Level: Early Learner\nBaseline: Approaching mastery\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: responds to own name\n- Curriculum: Social Behavior & Social Play L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: peer play.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's peer play routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the approaching mastery stage, use time delay (0 s -> 2 s -> 4 s) before delivering any model prompt; reinforce independent responses differentially.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "c8e9b465cb3fbf39", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "responds to own name", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "time_delay", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "75835"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: using public transportation\nCurriculum: AFLS Community Participation Skills\nLearner: Adult Learner\nMastery Status: Emerging\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: using public transportation\n- Curriculum: AFLS Community Participation Skills\n- Learner: Adult Learner\n- Current mastery: Emerging\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Confirm the correct stop or station. <- Learner-taught step (forward chaining starts here)\n2. Purchase or have the fare ready.\n3. Wait at the designated boarding area.\n4. Board the vehicle when it arrives.\n5. Pay the fare or present the pass.\n6. Sit or stand safely.\n7. Monitor the route for the correct stop.\n8. Exit at the correct stop.\n\n## Prompt Strategy Per Step\nStrategy: Graduated Guidance\nHand-over-hand physical guidance with fading pressure; move to shadow, then independent.\nCurrent prompt level: At the emerging stage, provide hand-over-hand guidance at each step; reduce physical pressure across sessions.\n\n## Error Correction Procedure\nModel -> prompt -> fade: Demonstrate the correct step; provide physical or gestural prompt as needed; fade prompt across subsequent trials\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 60s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "23b8b87f077c7021", "gold_labels": {"method": "task_analysis", "domain": "AFLS.community", "skill": "using public transportation", "program_type": "independence", "learner_profile": "adult", "mastery_state": "emerging", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "using public transportation", "module": "community", "mastery_criterion": "mc_fluent_chain", "chain_type": "forward", "prompt_strategy": "graduated_guidance", "reinforcement_schedule": "crf_per_step", "error_correction": "model_prompt_fade"}, "teacher_model": null, "seed_tag": "91439"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1299\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Listener Responding + Mand + Tolerating Denied Access\nDate range: Sessions 1\u201311 across 22 days (2026-10-17 to 2026-11-08)\n\nACCELERATION PROGRAMS\n1. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n2. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n3. mands for missing items needed to complete an activity (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Toileting accident (urine or bowel) \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-17 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 11/12 correct (88%); latency 2.3s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d77\n follows 1-step motor instructions: 9/12 correct (77%); latency 2.5s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d75\n mands for missing items needed to complete an activity: 7/9 correct (78%); latency 2.6s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d72\n Toileting accident (urine or bowel): urine: 4 in-toilet / 2 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 2 \u2014 2026-10-19 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 10/11 correct (90%); latency 2.0s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n follows 1-step motor instructions: 7/9 correct (82%); latency 2.4s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d76\n mands for missing items needed to complete an activity: 11/14 correct (76%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d78\n Toileting accident (urine or bowel): urine: 4 in-toilet / 2 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 3 \u2014 2026-10-21 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/9 correct (91%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n follows 1-step motor instructions: 10/13 correct (79%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d74\n mands for missing items needed to complete an activity: 11/15 correct (76%); latency 2.8s; prompts FP\u00d73, PP\u00d71, G\u00d75, I\u00d76\n Toileting accident (urine or bowel): urine: 4 in-toilet / 1 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 4 \u2014 2026-10-23 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/9 correct (92%); latency 1.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n follows 1-step motor instructions: 11/14 correct (80%); latency 2.4s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d72\n mands for missing items needed to complete an activity: 9/12 correct (72%); latency 2.7s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d76\n Toileting accident (urine or bowel): urine: 3 in-toilet / 1 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 5 \u2014 2026-10-25 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 11/12 correct (95%); latency 2.0s; prompts FP\u00d74, PP\u00d74, G\u00d73, I\u00d71\n follows 1-step motor instructions: 11/13 correct (82%); latency 2.2s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d76\n mands for missing items needed to complete an activity: 11/15 correct (74%); latency 2.5s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d714\n Toileting accident (urine or bowel): urine: 3 in-toilet / 2 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 6 \u2014 2026-10-27 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 11/12 correct (92%); latency 1.6s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d710\n follows 1-step motor instructions: 10/12 correct (80%); latency 2.6s; prompts FP\u00d74, PP\u00d70, G\u00d74, I\u00d74\n mands for missing items needed to complete an activity: 8/11 correct (73%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d77\n Toileting accident (urine or bowel): urine: 5 in-toilet / 0 accidents; BM: 1 in-toilet / 1 accidents\n\nSession 7 \u2014 2026-10-29 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/8 correct (97%); latency 1.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n follows 1-step motor instructions: 10/12 correct (86%); latency 2.1s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d79\n mands for missing items needed to complete an activity: 7/9 correct (74%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d74\n Toileting accident (urine or bowel): urine: 4 in-toilet / 2 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 8 \u2014 2026-10-31 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 9/9 correct (95%); latency 1.5s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n follows 1-step motor instructions: 10/12 correct (82%); latency 2.3s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d73\n mands for missing items needed to complete an activity: 5/8 correct (66%); latency 2.7s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n Toileting accident (urine or bowel): urine: 3 in-toilet / 1 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 9 \u2014 2026-11-02 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 12/13 correct (94%); latency 2.0s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d76\n follows 1-step motor instructions: 12/14 correct (86%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d710\n mands for missing items needed to complete an activity: 6/9 correct (66%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d77\n Toileting accident (urine or bowel): urine: 4 in-toilet / 1 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 10 \u2014 2026-11-04 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/8 correct (98%); latency 1.8s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n follows 1-step motor instructions: 13/15 correct (83%); latency 2.5s; prompts FP\u00d71, PP\u00d73, G\u00d75, I\u00d76\n mands for missing items needed to complete an activity: 6/9 correct (63%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n Toileting accident (urine or bowel): urine: 2 in-toilet / 2 accidents; BM: 0 in-toilet / 0 accidents\n\nSession 11 \u2014 2026-11-06 \u2014 44 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 15/15 correct (98%); latency 1.7s; prompts FP\u00d72, PP\u00d75, G\u00d72, I\u00d76\n follows 1-step motor instructions: 8/10 correct (83%); latency 2.1s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n mands for missing items needed to complete an activity: 5/8 correct (66%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n Toileting accident (urine or bowel): urine: 5 in-toilet / 1 accidents; BM: 0 in-toilet / 0 accidents\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Stereotypic behavior during inter-trial intervals"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (88%\u201398%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Behavior Function Hypothesis\nToileting accident (urine or bowel): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 93.7%.\n- Trend direction: upward (first session: 88%, last session: 98%).\n- Toileting accident (urine or bowel): mean 1.6/session (early-window mean 1.7 -> late-window mean 1.7).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "1ad58f4e88363430", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {"Toileting accident (urine or bowel)": "escape"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "early", "n_sessions": 11, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["toileting_accident"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "74744"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: mands for information using \"when\"\nCurriculum Reference: Mand L3\nLearner Profile: Adolescent Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands for information using \"when\"\n- Curriculum: Mand L3\n- Learner: Adolescent Learner\n- Current mastery: Approaching mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nBriefly withhold or restrict access to the target preferred item/activity for 30\u201360 seconds to establish motivation before the teaching opportunity.\nPrimary natural context: leisure time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's leisure time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the approaching mastery stage, use time delay (0 s -> 2 s -> 4 s) before delivering any model prompt; reinforce independent responses differentially.\n\n## Natural Reinforcer\nNatural reinforcer: immediate access to the requested item for 30\u201360 seconds.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "c9872efb9c14b070", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L3", "learner_profile": "adolescent", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands for information using \"when\"", "mo_category": "mand_item", "mo_arrangement": "deprivation_preferred_item", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "36908"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: selects items by class (find an animal)\nCurriculum Reference: Listener Responding L2\nLearner Profile: Early Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by class (find an animal)\n- Curriculum: Listener Responding L2\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: dog, chicken, duck\nDistractor stimuli: bear, lion, rabbit, monkey\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "9d204ccd2a2af8db", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L2", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by class (find an animal)", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "fr2", "error_correction": "four_step", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "87673"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: identifies basic shapes in math context\nCurriculum Reference: Math L1\nLearner Profile: Early Learner\nCurrent Mastery: Emerging\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies basic shapes in math context\n- Curriculum: Math L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What number is this?\"\nVariations: \"Which number?\"; \"Tell me the number\"\nPresentation: Present the numeral card.\n\n## Prompt Hierarchy\nStrategy: Time Delay (progressive)\nSequence: 0s delay -> 2s delay -> 4s delay -> 6s delay -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: star, heart, triangle\nDistractor stimuli: diamond, rectangle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "47203bda3945e9c0", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies basic shapes in math context", "prompt_hierarchy": "time_delay", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "69141"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: reproduces block designs from model\nCurriculum Reference: Visual Perceptual Skills & Matching-to-Sample L3\nLearner Profile: Adolescent Learner\nCurrent Mastery: Developing\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: reproduces block designs from model\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L3\n- Learner: Adolescent Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Stimulus Fading\nSequence: exaggerated stimulus -> moderate fade -> minimal fade -> natural stimulus\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: block, spoon, apple\nDistractor stimuli: towel, backpack, glue, jacket, car\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy across 2 consecutive sessions with at least 10 trials each.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "31ed54f1f680c114", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L3", "learner_profile": "adolescent", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "reproduces block designs from model", "prompt_hierarchy": "stimulus_fading", "reinforcement_schedule": "crf", "error_correction": "backstep", "mastery_criterion": "mc_80_2sessions"}, "teacher_model": null, "seed_tag": "26013"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5232\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math + Social Behavior\nDate range: Sessions 1\u201310 across 20 days (2026-06-25 to 2026-07-15)\n\nACCELERATION PROGRAMS\n1. counts objects 1\u201320 (Math)\n Method: DTT\n2. indicating 'all done' when an activity is complete (Mand)\n Method: NET\n3. takes turns during structured activities (Social Behavior)\n Method: PRT\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-25 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 5/14 correct (37%); latency 4.6s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d710\n indicating 'all done' when an activity is complete: 5/15 correct (36%); latency 4.6s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d711\n takes turns during structured activities: 6/13 correct (47%); latency 4.0s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d79\n\nSession 2 \u2014 2026-06-27 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 5/12 correct (44%); latency 4.2s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d72\n indicating 'all done' when an activity is complete: 3/8 correct (41%); latency 4.2s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n takes turns during structured activities: 4/8 correct (56%); latency 3.8s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n\nSession 3 \u2014 2026-06-29 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 6/12 correct (50%); latency 3.7s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d77\n indicating 'all done' when an activity is complete: 6/12 correct (47%); latency 4.1s; prompts FP\u00d73, PP\u00d70, G\u00d74, I\u00d75\n takes turns during structured activities: 5/8 correct (64%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n\nSession 4 \u2014 2026-07-01 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 5/9 correct (59%); latency 3.3s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n indicating 'all done' when an activity is complete: 6/11 correct (52%); latency 3.8s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d75\n takes turns during structured activities: 7/10 correct (70%); latency 3.1s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n\nSession 5 \u2014 2026-07-03 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 7/10 correct (68%); latency 2.7s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n indicating 'all done' when an activity is complete: 6/10 correct (62%); latency 3.5s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d72\n takes turns during structured activities: 6/8 correct (71%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n\nSession 6 \u2014 2026-07-05 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 10/13 correct (75%); latency 2.8s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d76\n indicating 'all done' when an activity is complete: 8/12 correct (69%); latency 3.2s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d75\n takes turns during structured activities: 6/8 correct (71%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n\nSession 7 \u2014 2026-07-07 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 9/11 correct (77%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n indicating 'all done' when an activity is complete: 11/14 correct (76%); latency 2.9s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d79\n takes turns during structured activities: 7/10 correct (71%); latency 2.8s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n\nSession 8 \u2014 2026-07-09 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 10/13 correct (77%); latency 2.3s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d76\n indicating 'all done' when an activity is complete: 8/11 correct (77%); latency 2.5s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n takes turns during structured activities: 8/11 correct (71%); latency 2.7s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n\nSession 9 \u2014 2026-07-11 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 9/12 correct (77%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d77\n indicating 'all done' when an activity is complete: 11/14 correct (77%); latency 2.6s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n takes turns during structured activities: 11/15 correct (71%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d77\n\nSession 10 \u2014 2026-07-13 \u2014 40 min \u2014 1 observer\n counts objects 1\u201320: 10/13 correct (77%); latency 2.6s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d75\n indicating 'all done' when an activity is complete: 8/11 correct (77%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n takes turns during structured activities: 10/14 correct (71%); latency 2.8s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Looking away during SD presentation\n- Playing with non-task materials"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 37% at return, recovering to 77%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 10 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 64.3%.\n- Trend direction: upward (first session: 37%, last session: 77%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "bd40b4ac9a754f4a", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "school_age", "n_sessions": 10, "n_programs": 3, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "46674"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: sequences 3\u20134 step picture sequences\nCurriculum: Visual Perceptual Skills & Matching-to-Sample L3\nLearner Level: Adolescent Learner\nBaseline: Mastered at current level\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: sequences 3\u20134 step picture sequences\n- Curriculum: Visual Perceptual Skills & Matching-to-Sample L3\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Match\"\nVariations: \"Find the same\"; \"Put with same\"\nPresentation: Present the sample stimulus and an array of comparison stimuli simultaneously.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: shoe, cup, ball\nDistractor stimuli: car, apple, glue, pencil, backpack\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "6284cf37ac9d828d", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.vp_mts", "level": "L3", "learner_profile": "adolescent", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "sequences 3\u20134 step picture sequences", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "fr2", "error_correction": "transfer_trial", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "61305"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: clocking in at start of shift\nCurriculum: AFLS Vocational Skills\nLearner: Adult Learner\nMastery Status: Generalization phase\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: clocking in at start of shift\n- Curriculum: AFLS Vocational Skills\n- Learner: Adult Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Arrive at the workplace by the scheduled time.\n2. Locate the time clock or digital system.\n3. Enter identification (ID card / badge / code).\n4. Confirm the clock-in timestamp.\n5. Notify the supervisor or check the day's task list.\n6. Proceed to the assigned workstation.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 120s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "29258e58319befc3", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "clocking in at start of shift", "program_type": "independence", "learner_profile": "adult", "mastery_state": "generalization", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "clocking in at start of shift", "module": "vocational", "mastery_criterion": "mc_fluent_chain", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "6035"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a chaining program for the following.\n\nSkill: putting on a shirt (pullover)\nCurriculum: AFLS Basic Living Skills\nLearner Level: Adolescent Learner\nBaseline: Generalization phase\n\nInclude the full Task Analysis structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: putting on a shirt (pullover)\n- Curriculum: AFLS Basic Living Skills\n- Learner: Adolescent Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Hold the shirt with the front facing away.\n2. Place both arms into the sleeves.\n3. Pull the opening over the head.\n4. Push arms through the sleeves fully.\n5. Pull the bottom of the shirt down to straighten it.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 120s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "c1f6dc90eda66233", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "putting on a shirt (pullover)", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "generalization", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "putting on a shirt (pullover)", "module": "basic_living", "mastery_criterion": "mc_fluent_chain", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "44637"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: identifies all upper-case letters\nCurriculum: Reading L2\nLearner: Early Learner\nMastery Status: Developing\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies all upper-case letters\n- Curriculum: Reading L2\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What letter is this?\"\nVariations: \"Read this letter\"; \"What does this say?\"\nPresentation: Present the letter flashcard.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: X, I, S\nDistractor stimuli: K, T, U, A\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy at independent prompt level across 3 sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "0343089ca4769f77", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L2", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies all upper-case letters", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_80_independent"}, "teacher_model": null, "seed_tag": "35263"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3715\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Reading + Tolerating Denied Access\nDate range: Sessions 1\u20138 across 16 days (2026-07-16 to 2026-08-01)\n\nACCELERATION PROGRAMS\n1. reads 10\u201320 sight words (Reading)\n Method: DTT\n2. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n3. requesting preferred items using AAC device (e.g., \"I want cookie please\") (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-16 \u2014 59 min \u2014 1 observer\n reads 10\u201320 sight words: 12/14 correct (87%); latency 2.1s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d78\n wait calmly when access to preferred item is denied: 7/10 correct (74%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 9/12 correct (74%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d74\n Tantrum: freq 2, duration 4m total\n\nSession 2 \u2014 2026-07-18 \u2014 59 min \u2014 1 observer\n reads 10\u201320 sight words: 12/15 correct (78%); latency 2.5s; prompts FP\u00d71, PP\u00d71, G\u00d75, I\u00d78\n wait calmly when access to preferred item is denied: 8/11 correct (72%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/10 correct (69%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n Tantrum: freq 4, duration 12m total\n\nSession 3 \u2014 2026-07-20 \u2014 59 min \u2014 1 observer\n reads 10\u201320 sight words: 7/9 correct (78%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d76\n wait calmly when access to preferred item is denied: 8/11 correct (69%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 7/12 correct (60%); latency 3.2s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d75\n Tantrum: freq 5, duration 25m total\n\nSession 4 \u2014 2026-07-22 \u2014 59 min \u2014 1 observer\n reads 10\u201320 sight words: 9/13 correct (69%); latency 3.2s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d73\n wait calmly when access to preferred item is denied: 8/13 correct (64%); latency 3.0s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 5/11 correct (47%); latency 3.7s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n Tantrum: freq 5, duration 15m total\n\nSession 5 \u2014 2026-07-24 \u2014 IOA SESSION \u2014 2 observers\n reads 10\u201320 sight words: 61% (primary); IOA 96% agreement\n wait calmly when access to preferred item is denied: 61% (primary); IOA 96% agreement\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 47% (primary); IOA 96% agreement\n Tantrum: freq 4, duration 8m total; IOA 96% agreement\n\nSession 6 \u2014 2026-07-26 \u2014 59 min \u2014 1 observer\n reads 10\u201320 sight words: 7/11 correct (63%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n wait calmly when access to preferred item is denied: 7/12 correct (57%); latency 3.3s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d76\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 3/9 correct (38%); latency 4.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n Tantrum: freq 6, duration 30m total\n\nSession 7 \u2014 2026-07-28 \u2014 59 min \u2014 1 observer\n reads 10\u201320 sight words: 7/11 correct (59%); latency 3.5s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d77\n wait calmly when access to preferred item is denied: 6/12 correct (52%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d77\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 3/12 correct (26%); latency 4.9s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d76\n Tantrum: freq 7, duration 14m total\n\nSession 8 \u2014 2026-07-30 \u2014 59 min \u2014 1 observer\n reads 10\u201320 sight words: 6/12 correct (49%); latency 4.0s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d78\n wait calmly when access to preferred item is denied: 4/9 correct (41%); latency 4.0s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d74\n requesting preferred items using AAC device (e.g., \"I want cookie please\"): 2/12 correct (17%); latency 4.9s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n Tantrum: freq 8, duration 24m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Elopement from the work area"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (87% -> 49%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nTantrum: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nhigh\n\nPattern is well-supported: 8 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 68.1%.\n- Trend direction: downward (first session: 87%, last session: 49%).\n- Tantrum: mean 5.1/session (early-window mean 3.0 -> late-window mean 7.5).\n- IOA data: 96% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "5d15065360c3bac4", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Tantrum": "escape"}, "escalation_level": 3, "confidence": "high", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "school_age", "n_sessions": 8, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["tantrum"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "87221"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: engages in social games (peek-a-boo, tickle)\nCurriculum: Social Behavior & Social Play L1\nLearner: Early Learner\nMastery Status: Near mastery\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: engages in social games (peek-a-boo, tickle)\n- Curriculum: Social Behavior & Social Play L1\n- Learner: Early Learner\n- Current mastery: Near mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: circle time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's circle time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the near mastery stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nAverage rate of \u2265 3 spontaneous responses per 30-minute session across 3 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "0f39cad4ee379441", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L1", "learner_profile": "early", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "engages in social games (peek-a-boo, tickle)", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "time_delay", "mastery_criterion": "mc_spontaneous_rate"}, "teacher_model": null, "seed_tag": "83467"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: copies basic shapes from model\nCurriculum: Writing L1\nLearner Level: Early Learner\nBaseline: Emerging\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: copies basic shapes from model\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Emerging\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the emerging stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: diamond, square, rectangle\nDistractor stimuli: heart, triangle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "8f62fe68a9d67641", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "copies basic shapes from model", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "27367"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: selects items by function (What do you drink from?)\nCurriculum Reference: LRFFC L1\nLearner Profile: Early Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects items by function (What do you drink from?)\n- Curriculum: LRFFC L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: toothbrush, crayon, napkin\nDistractor stimuli: hat, bottle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy across 2 consecutive sessions with at least 10 trials each.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "047d27b94f192273", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects items by function (What do you drink from?)", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "crf", "error_correction": "backstep", "mastery_criterion": "mc_80_2sessions"}, "teacher_model": null, "seed_tag": "92219"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7307\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Reading + Tolerating Denied Access\nDate range: Sessions 1\u20137 across 14 days (2026-07-25 to 2026-08-08)\n\nACCELERATION PROGRAMS\n1. sounds out CVC words (Reading)\n Method: DTT\n2. mands for missing items needed to complete an activity (Mand)\n Method: NET\n3. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n4. single-word requests for preferred items (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-25 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 6/14 correct (43%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d713\n mands for missing items needed to complete an activity: 7/15 correct (48%); latency 3.8s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d710\n wait calmly when access to preferred item is denied: 7/13 correct (53%); latency 3.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d78\n single-word requests for preferred items: 6/15 correct (42%); latency 4.0s; prompts FP\u00d72, PP\u00d75, G\u00d72, I\u00d76\n\nSession 2 \u2014 2026-07-27 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 8/15 correct (53%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d712\n mands for missing items needed to complete an activity: 5/8 correct (56%); latency 3.7s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n wait calmly when access to preferred item is denied: 7/11 correct (63%); latency 3.4s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n single-word requests for preferred items: 5/10 correct (52%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d73\n\nSession 3 \u2014 2026-07-29 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 5/8 correct (58%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n mands for missing items needed to complete an activity: 8/13 correct (65%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d73\n wait calmly when access to preferred item is denied: 6/9 correct (70%); latency 3.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d76\n single-word requests for preferred items: 6/10 correct (60%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d76\n\nSession 4 \u2014 2026-07-31 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 8/12 correct (64%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d73\n mands for missing items needed to complete an activity: 11/15 correct (71%); latency 3.0s; prompts FP\u00d74, PP\u00d73, G\u00d75, I\u00d73\n wait calmly when access to preferred item is denied: 9/12 correct (77%); latency 2.3s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d76\n single-word requests for preferred items: 5/8 correct (65%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n\nSession 5 \u2014 2026-08-02 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 6/8 correct (73%); latency 2.6s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n mands for missing items needed to complete an activity: 12/15 correct (78%); latency 2.8s; prompts FP\u00d73, PP\u00d75, G\u00d73, I\u00d74\n wait calmly when access to preferred item is denied: 7/9 correct (83%); latency 2.5s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d75\n single-word requests for preferred items: 6/8 correct (71%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n\nSession 6 \u2014 2026-08-04 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 8/10 correct (78%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n mands for missing items needed to complete an activity: 10/12 correct (83%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d77\n wait calmly when access to preferred item is denied: 12/15 correct (83%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d710\n single-word requests for preferred items: 10/13 correct (78%); latency 2.6s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d79\n\nSession 7 \u2014 2026-08-06 \u2014 60 min \u2014 1 observer\n sounds out CVC words: 6/8 correct (78%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n mands for missing items needed to complete an activity: 12/14 correct (83%); latency 2.5s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n wait calmly when access to preferred item is denied: 10/12 correct (83%); latency 2.2s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d75\n single-word requests for preferred items: 8/10 correct (79%); latency 2.2s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Stereotypic behavior during inter-trial intervals\n- Looking away during SD presentation\n- Delayed responding (>5 seconds consistently)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Skill loss following break**: performance dropped to 43% at return, recovering to 78%.\n- Maintenance schedule should be reviewed and strengthened.\n\n## Pattern Classification\nskill_loss_after_break\n\nSharp drop at the start of the log followed by gradual recovery indicates skill loss following an absence.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Implement booster sessions at the most-recently-effective prompt level.\n- Increase session frequency temporarily until pre-break levels are recovered.\n\n### Consequence strategies\n- Review and strengthen the maintenance schedule to prevent future skill loss.\n- Consider sending practice materials home during extended breaks.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 63.7%.\n- Trend direction: upward (first session: 43%, last session: 78%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "605eb128dcfdee94", "gold_labels": {"pattern_class": "skill_loss_after_break", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "skill_loss_after_break", "learner_profile": "school_age", "n_sessions": 7, "n_programs": 4, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "7865"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8784\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Reading + Tact\nDate range: Sessions 1\u201310 across 20 days (2026-07-11 to 2026-07-31)\n\nACCELERATION PROGRAMS\n1. tacts colors of objects (Tact)\n Method: DTT\n2. sounds out CVC words (Reading)\n Method: DTT\n3. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-11 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 5/10 correct (50%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n sounds out CVC words: 7/15 correct (49%); latency 3.7s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d710\n answers WH-questions about familiar topics: 8/13 correct (63%); latency 3.3s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d712\n\nSession 2 \u2014 2026-07-13 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 5/10 correct (52%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n sounds out CVC words: 6/10 correct (64%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n answers WH-questions about familiar topics: 6/12 correct (52%); latency 3.8s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d78\n\nSession 3 \u2014 2026-07-15 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 7/12 correct (54%); latency 3.6s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d72\n sounds out CVC words: 8/13 correct (60%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d78\n answers WH-questions about familiar topics: 5/9 correct (55%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n\nSession 4 \u2014 2026-07-17 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 9/14 correct (61%); latency 3.5s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d75\n sounds out CVC words: 6/10 correct (63%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n answers WH-questions about familiar topics: 5/8 correct (59%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n\nSession 5 \u2014 2026-07-19 \u2014 IOA SESSION \u2014 2 observers\n tacts colors of objects: 58% (primary); IOA 90% agreement\n sounds out CVC words: 60% (primary); IOA 90% agreement\n answers WH-questions about familiar topics: 55% (primary); IOA 90% agreement\n\nSession 6 \u2014 2026-07-21 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 8/13 correct (63%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d74\n sounds out CVC words: 8/11 correct (69%); latency 3.0s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n answers WH-questions about familiar topics: 6/10 correct (57%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n\nSession 7 \u2014 2026-07-23 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 8/13 correct (61%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d75\n sounds out CVC words: 6/9 correct (62%); latency 3.5s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n answers WH-questions about familiar topics: 6/10 correct (56%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n\nSession 8 \u2014 2026-07-25 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 7/12 correct (62%); latency 3.1s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d76\n sounds out CVC words: 8/13 correct (60%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d77\n answers WH-questions about familiar topics: 7/13 correct (56%); latency 3.4s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d73\n\nSession 9 \u2014 2026-07-27 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 6/10 correct (62%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n sounds out CVC words: 8/11 correct (74%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n answers WH-questions about familiar topics: 5/11 correct (50%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d79\n\nSession 10 \u2014 2026-07-29 \u2014 33 min \u2014 1 observer\n tacts colors of objects: 8/11 correct (71%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n sounds out CVC words: 8/12 correct (69%); latency 2.7s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d72\n answers WH-questions about familiar topics: 7/15 correct (49%); latency 3.7s; prompts FP\u00d72, PP\u00d75, G\u00d70, I\u00d78\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Delayed responding (>5 seconds consistently)\n- Looking away during SD presentation\n- Playing with non-task materials\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Plateau**: accuracy has remained near 60% for 10 sessions without meaningful improvement.\n- Performance is below mastery criteria; current teaching procedure may not be effective for this learner.\n\n## Pattern Classification\nplateau\n\nResponding has stabilized below mastery criterion without meaningful movement, indicating the current procedure is limiting further acquisition.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Modify teaching procedure \u2014 switch prompt type (e.g., from most-to-least to time delay).\n- Conduct preference assessment and update reinforcer menu.\n- Break the current skill into smaller component steps if possible.\n- Increase practice opportunities by embedding targets in natural-environment training.\n\n### Consequence strategies\n- Check for inadvertent reinforcement of near-misses; tighten differential reinforcement.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nhigh\n\nPattern is well-supported: 10 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 10 sessions: 59.5%.\n- Trend direction: upward (first session: 50%, last session: 71%).\n- IOA data: 90% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "2350389104a74c98", "gold_labels": {"pattern_class": "plateau", "behavior_functions": {}, "escalation_level": 2, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "plateau", "learner_profile": "early", "n_sessions": 10, "n_programs": 3, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "4427"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-7486\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Mand + Reading\nDate range: Sessions 1\u201312 across 24 days (2026-08-03 to 2026-08-27)\n\nACCELERATION PROGRAMS\n1. 2-word mand phrases (e.g., \"more cracker\", \"open please\") (Mand)\n Method: NET\n2. sounds out CVC words (Reading)\n Method: DTT\n3. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-08-03 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 11/15 correct (71%); latency 2.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d710\n sounds out CVC words: 11/13 correct (87%); latency 2.0s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 12/14 correct (82%); latency 2.1s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d79\n Tantrum: freq 1, duration 5m total\n\nSession 2 \u2014 2026-08-05 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 7/10 correct (66%); latency 3.1s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n sounds out CVC words: 11/14 correct (76%); latency 2.4s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 11/14 correct (79%); latency 2.3s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d75\n Tantrum: freq 1, duration 4m total\n\nSession 3 \u2014 2026-08-07 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 9/14 correct (63%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d710\n sounds out CVC words: 8/11 correct (74%); latency 2.9s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/10 correct (70%); latency 2.9s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n Tantrum: freq 2, duration 10m total\n\nSession 4 \u2014 2026-08-09 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/10 correct (52%); latency 3.3s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n sounds out CVC words: 6/9 correct (66%); latency 2.9s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/8 correct (71%); latency 2.7s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n Tantrum: freq 2, duration 4m total\n\nSession 5 \u2014 2026-08-11 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/10 correct (51%); latency 3.7s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n sounds out CVC words: 8/14 correct (59%); latency 3.1s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/10 correct (60%); latency 3.2s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d78\n Tantrum: freq 1, duration 3m total\n\nSession 6 \u2014 2026-08-13 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 5/12 correct (44%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d76\n sounds out CVC words: 6/10 correct (58%); latency 3.2s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/9 correct (52%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n Tantrum: freq 3, duration 6m total\n\nSession 7 \u2014 2026-08-15 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 6/15 correct (39%); latency 4.4s; prompts FP\u00d75, PP\u00d72, G\u00d71, I\u00d77\n sounds out CVC words: 6/12 correct (51%); latency 3.7s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d71\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/12 correct (47%); latency 4.1s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d78\n Tantrum: freq 2, duration 10m total\n\nSession 8 \u2014 2026-08-17 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 4/12 correct (31%); latency 4.8s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d78\n sounds out CVC words: 6/14 correct (41%); latency 4.0s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d710\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/8 correct (51%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n Tantrum: freq 2, duration 8m total\n\nSession 9 \u2014 2026-08-19 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 2/9 correct (21%); latency 5.2s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d72\n sounds out CVC words: 6/15 correct (37%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d710\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/10 correct (42%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d75\n Tantrum: freq 3, duration 9m total\n\nSession 10 \u2014 2026-08-21 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 2/15 correct (13%); latency 5.5s; prompts FP\u00d75, PP\u00d71, G\u00d73, I\u00d76\n sounds out CVC words: 2/9 correct (27%); latency 4.6s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/11 correct (35%); latency 4.4s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d77\n Tantrum: freq 4, duration 12m total\n\nSession 11 \u2014 2026-08-23 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 1/9 correct (14%); latency 5.6s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n sounds out CVC words: 2/8 correct (23%); latency 4.9s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/10 correct (30%); latency 4.7s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d77\n Tantrum: freq 4, duration 8m total\n\nSession 12 \u2014 2026-08-25 \u2014 51 min \u2014 1 observer\n 2-word mand phrases (e.g., \"more cracker\", \"open please\"): 1/13 correct (10%); latency 5.5s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d75\n sounds out CVC words: 3/13 correct (24%); latency 5.0s; prompts FP\u00d74, PP\u00d71, G\u00d74, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/10 correct (29%); latency 4.9s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d78\n Tantrum: freq 5, duration 10m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Pushing materials away from the work area\n- Elopement from the work area\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 71% to 10% across 12 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nTantrum: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 39.7%.\n- Trend direction: downward (first session: 71%, last session: 10%).\n- Tantrum: mean 2.5/session (early-window mean 1.5 -> late-window mean 4.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "275422cd61681fb0", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Tantrum": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "early", "n_sessions": 12, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["tantrum"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "80849"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-6069\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Intraverbal + Listener Responding + Mand\nDate range: Sessions 1\u20139 across 18 days (2026-03-22 to 2026-04-09)\n\nACCELERATION PROGRAMS\n1. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n2. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n3. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n\nDECELERATION TARGETS\n1. Aggression \u2014 function hypothesized: tangible\n\nSESSION DATA\n\nSession 1 \u2014 2026-03-22 \u2014 57 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 10/12 correct (82%); latency 2.3s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d77\n answers WH-questions about familiar topics: 7/11 correct (61%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d78\n follows 1-step motor instructions: 8/10 correct (84%); latency 2.4s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n Aggression: freq 3\n ABC (aggression): A = peer took preferred toy; B = grabbed toy back + cried; C = staff mediated and returned item\n\nSession 2 \u2014 2026-03-24 \u2014 57 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 8/14 correct (56%); latency 3.6s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d74\n answers WH-questions about familiar topics: 6/11 correct (51%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n follows 1-step motor instructions: 7/14 correct (49%); latency 4.0s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d74\n Aggression: freq 0\n\nSession 3 \u2014 2026-03-26 \u2014 57 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 5/9 correct (58%); latency 3.3s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n answers WH-questions about familiar topics: 6/14 correct (40%); latency 4.3s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d710\n follows 1-step motor instructions: 7/9 correct (73%); latency 2.5s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n Aggression: freq 4\n ABC (aggression): A = peer took preferred toy; B = grabbed toy back + cried; C = staff mediated and returned item\n\nSession 4 \u2014 2026-03-28 \u2014 57 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 8/11 correct (74%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n answers WH-questions about familiar topics: 10/14 correct (70%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d78\n follows 1-step motor instructions: 11/15 correct (71%); latency 2.6s; prompts FP\u00d72, PP\u00d73, G\u00d75, I\u00d75\n Aggression: freq 1\n\nSession 5 \u2014 2026-03-30 \u2014 57 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 7/11 correct (62%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d75\n answers WH-questions about familiar topics: 5/9 correct (56%); latency 3.6s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n follows 1-step motor instructions: 12/15 correct (83%); latency 2.4s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d712\n Aggression: freq 3\n\nSession 6 \u2014 2026-04-01 \u2014 57 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 6/11 correct (52%); latency 3.8s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d711\n answers WH-questions about familiar topics: 3/10 correct (34%); latency 4.3s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d77\n follows 1-step motor instructions: 8/11 correct (73%); latency 2.7s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n Aggression: freq 1\n ABC (aggression): A = preferred iPad removed at end of break; B = screamed + reached for device; C = staff redirected to alternative\n\nSession 7 \u2014 2026-04-03 \u2014 IOA SESSION \u2014 2 observers\n requesting a break ('break please' or AAC 'I need a break'): 64% (primary); IOA 85% agreement\n answers WH-questions about familiar topics: 58% (primary); IOA 85% agreement\n follows 1-step motor instructions: 81% (primary); IOA 85% agreement\n Aggression: freq 0; IOA 85% agreement\n\nSession 8 \u2014 2026-04-05 \u2014 57 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 9/11 correct (83%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d79\n answers WH-questions about familiar topics: 7/14 correct (47%); latency 3.7s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d77\n follows 1-step motor instructions: 11/15 correct (72%); latency 2.8s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d76\n Aggression: freq 3\n\nSession 9 \u2014 2026-04-07 \u2014 57 min \u2014 1 observer\n requesting a break ('break please' or AAC 'I need a break'): 10/14 correct (68%); latency 3.0s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d710\n answers WH-questions about familiar topics: 10/15 correct (64%); latency 2.9s; prompts FP\u00d70, PP\u00d71, G\u00d75, I\u00d79\n follows 1-step motor instructions: 10/13 correct (79%); latency 2.3s; prompts FP\u00d72, PP\u00d74, G\u00d73, I\u00d74\n Aggression: freq 3\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Delayed responding (>5 seconds consistently)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 75% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Behavior Function Hypothesis\nAggression: tangible\n Evidence: ABC events in the log support the tangible function; behavior occurs when preferred items are restricted and is followed by access to the item.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nhigh\n\nPattern is well-supported: 9 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 66.5%.\n- Trend direction: downward (first session: 82%, last session: 68%).\n- Aggression: mean 2.0/session (early-window mean 2.3 -> late-window mean 2.0).\n- IOA data: 85% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "1247171dd3ca44d5", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {"Aggression": "tangible"}, "escalation_level": 3, "confidence": "high", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "early", "n_sessions": 9, "n_programs": 3, "n_behaviors": 1, "behavior_ids": ["aggression"], "behavior_functions": ["tangible"], "has_abc_data": true, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "11965"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-1527\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Echoic + Mand + Motor Imitation + Reading + Tact\nDate range: Sessions 1\u201311 across 22 days (2026-04-09 to 2026-05-01)\n\nACCELERATION PROGRAMS\n1. reads 10\u201320 sight words (Reading)\n Method: DTT\n2. tacts colors of objects (Tact)\n Method: DTT\n3. imitates 3-step motor sequences (Motor Imitation)\n Method: DTT variant\n4. indicating completion ('all done', 'finished') (Mand)\n Method: NET\n5. sounds out CVC words (Reading)\n Method: DTT\n6. echoes 2-word phrases (Echoic)\n Method: DTT variant\n\nSESSION DATA\n\nSession 1 \u2014 2026-04-09 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 4/8 correct (47%); latency 4.0s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n tacts colors of objects: 8/15 correct (53%); latency 3.4s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d714\n imitates 3-step motor sequences: 4/9 correct (41%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n indicating completion ('all done', 'finished'): 8/15 correct (51%); latency 3.7s; prompts FP\u00d74, PP\u00d75, G\u00d74, I\u00d72\n sounds out CVC words: 4/8 correct (51%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n echoes 2-word phrases: 8/14 correct (56%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d712\n\nSession 2 \u2014 2026-04-11 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 8/13 correct (59%); latency 3.3s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d710\n tacts colors of objects: 4/9 correct (45%); latency 4.3s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d74\n imitates 3-step motor sequences: 4/10 correct (43%); latency 4.2s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n indicating completion ('all done', 'finished'): 5/10 correct (52%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n sounds out CVC words: 5/9 correct (55%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n echoes 2-word phrases: 6/11 correct (55%); latency 3.3s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n\nSession 3 \u2014 2026-04-13 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 6/10 correct (60%); latency 3.3s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n tacts colors of objects: 6/15 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d78\n imitates 3-step motor sequences: 6/11 correct (56%); latency 3.3s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d77\n indicating completion ('all done', 'finished'): 4/10 correct (43%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n sounds out CVC words: 7/13 correct (51%); latency 3.8s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d76\n echoes 2-word phrases: 5/10 correct (52%); latency 3.5s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n\nSession 4 \u2014 2026-04-15 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 4/8 correct (55%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n tacts colors of objects: 6/14 correct (41%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d78\n imitates 3-step motor sequences: 7/14 correct (52%); latency 3.4s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d78\n indicating completion ('all done', 'finished'): 7/13 correct (54%); latency 3.3s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n sounds out CVC words: 4/8 correct (52%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n echoes 2-word phrases: 9/14 correct (65%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d78\n\nSession 5 \u2014 2026-04-17 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 8/14 correct (56%); latency 3.7s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d78\n tacts colors of objects: 6/12 correct (46%); latency 4.0s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d74\n imitates 3-step motor sequences: 8/15 correct (52%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d75, I\u00d78\n indicating completion ('all done', 'finished'): 5/10 correct (53%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d73\n sounds out CVC words: 7/12 correct (54%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d74\n echoes 2-word phrases: 6/13 correct (50%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d79\n\nSession 6 \u2014 2026-04-19 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 5/11 correct (44%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n tacts colors of objects: 5/11 correct (49%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n imitates 3-step motor sequences: 6/12 correct (46%); latency 4.1s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d77\n indicating completion ('all done', 'finished'): 5/11 correct (43%); latency 4.3s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n sounds out CVC words: 6/13 correct (42%); latency 3.9s; prompts FP\u00d70, PP\u00d71, G\u00d74, I\u00d78\n echoes 2-word phrases: 6/11 correct (58%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n\nSession 7 \u2014 2026-04-21 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 8/14 correct (54%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d710\n tacts colors of objects: 8/15 correct (56%); latency 3.4s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d711\n imitates 3-step motor sequences: 7/14 correct (48%); latency 3.6s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d77\n indicating completion ('all done', 'finished'): 8/14 correct (55%); latency 3.5s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n sounds out CVC words: 5/11 correct (44%); latency 3.9s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n echoes 2-word phrases: 9/14 correct (64%); latency 3.1s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d710\n\nSession 8 \u2014 2026-04-23 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 8/14 correct (57%); latency 3.3s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d77\n tacts colors of objects: 4/10 correct (41%); latency 4.3s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n imitates 3-step motor sequences: 7/15 correct (50%); latency 3.9s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d711\n indicating completion ('all done', 'finished'): 4/9 correct (50%); latency 4.0s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n sounds out CVC words: 6/12 correct (50%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d74, I\u00d74\n echoes 2-word phrases: 7/13 correct (56%); latency 3.4s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d79\n\nSession 9 \u2014 2026-04-25 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 4/8 correct (44%); latency 4.2s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n tacts colors of objects: 5/12 correct (43%); latency 4.3s; prompts FP\u00d73, PP\u00d73, G\u00d74, I\u00d72\n imitates 3-step motor sequences: 6/15 correct (42%); latency 4.0s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d711\n indicating completion ('all done', 'finished'): 4/9 correct (50%); latency 3.9s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n sounds out CVC words: 4/8 correct (53%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n echoes 2-word phrases: 5/8 correct (62%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n\nSession 10 \u2014 2026-04-27 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 7/14 correct (48%); latency 3.8s; prompts FP\u00d74, PP\u00d70, G\u00d73, I\u00d77\n tacts colors of objects: 4/8 correct (47%); latency 3.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n imitates 3-step motor sequences: 8/15 correct (50%); latency 3.6s; prompts FP\u00d74, PP\u00d74, G\u00d75, I\u00d72\n indicating completion ('all done', 'finished'): 8/15 correct (52%); latency 3.7s; prompts FP\u00d75, PP\u00d71, G\u00d70, I\u00d79\n sounds out CVC words: 3/8 correct (39%); latency 4.3s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n echoes 2-word phrases: 9/15 correct (63%); latency 3.2s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d77\n\nSession 11 \u2014 2026-04-29 \u2014 32 min \u2014 1 observer\n reads 10\u201320 sight words: 5/9 correct (52%); latency 3.5s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n tacts colors of objects: 3/8 correct (42%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n imitates 3-step motor sequences: 5/10 correct (51%); latency 3.9s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d73\n indicating completion ('all done', 'finished'): 7/15 correct (48%); latency 3.7s; prompts FP\u00d75, PP\u00d70, G\u00d70, I\u00d710\n sounds out CVC words: 7/15 correct (45%); latency 3.7s; prompts FP\u00d75, PP\u00d74, G\u00d75, I\u00d71\n echoes 2-word phrases: 7/11 correct (63%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Stereotypic behavior during inter-trial intervals\n- Leaving seat without permission\n- Delayed responding (>5 seconds consistently)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Plateau**: accuracy has remained near 50% for 11 sessions without meaningful improvement.\n- Performance is below mastery criteria; current teaching procedure may not be effective for this learner.\n\n## Pattern Classification\nplateau\n\nResponding has stabilized below mastery criterion without meaningful movement, indicating the current procedure is limiting further acquisition.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Modify teaching procedure \u2014 switch prompt type (e.g., from most-to-least to time delay).\n- Conduct preference assessment and update reinforcer menu.\n- Break the current skill into smaller component steps if possible.\n- Increase practice opportunities by embedding targets in natural-environment training.\n\n### Consequence strategies\n- Check for inadvertent reinforcement of near-misses; tighten differential reinforcement.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 52.4%.\n- Trend direction: upward (first session: 47%, last session: 52%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "26fd25f89043f5c9", "gold_labels": {"pattern_class": "plateau", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "plateau", "learner_profile": "early", "n_sessions": 11, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "55785"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: initiates social interactions with peers\nCurriculum Reference: Social Behavior & Social Play L2\nLearner Profile: Early Learner\nCurrent Mastery: Developing\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: initiates social interactions with peers\n- Curriculum: Social Behavior & Social Play L2\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: peer play.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's peer play routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the developing stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 4 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use of target response across 3 natural opportunities per day for 3 consecutive days.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "100758a5bfb54a73", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L2", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "initiates social interactions with peers", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_indep_natural_env"}, "teacher_model": null, "seed_tag": "70185"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3610\nProfile: Adult Learner (18+ years)\nCurricula: Independent Living + Mand + Self-Care\nDate range: Sessions 1\u20139 across 18 days (2026-07-21 to 2026-08-08)\n\nACCELERATION PROGRAMS\n1. requesting assistance using AAC device (Mand)\n Method: NET\n2. self-advocacy statements (Independent Living)\n Method: BST\n3. brushing teeth independently (Self-Care)\n Method: Task Analysis\n4. scheduling medical appointments (Independent Living)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Toileting accident (urine or bowel) \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-07-21 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 11/14 correct (81%); latency 2.1s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d75\n self-advocacy statements: 9/12 correct (75%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d75\n brushing teeth independently: 6/8 correct (74%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n scheduling medical appointments: 10/11 correct (88%); latency 2.2s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d75\n Toileting accident (urine or bowel): urine: 2 in-toilet / 2 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 2 \u2014 2026-07-23 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 12/15 correct (78%); latency 2.4s; prompts FP\u00d72, PP\u00d74, G\u00d74, I\u00d75\n self-advocacy statements: 9/14 correct (68%); latency 2.8s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d77\n brushing teeth independently: 6/9 correct (67%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n scheduling medical appointments: 7/10 correct (72%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n Toileting accident (urine or bowel): urine: 3 in-toilet / 4 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 3 \u2014 2026-07-25 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 10/15 correct (67%); latency 3.3s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d713\n self-advocacy statements: 6/10 correct (58%); latency 3.2s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n brushing teeth independently: 6/11 correct (58%); latency 3.4s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n scheduling medical appointments: 5/8 correct (66%); latency 2.7s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d77\n Toileting accident (urine or bowel): urine: 3 in-toilet / 2 accidents; BM: 0 in-toilet / 1 accidents\n\nSession 4 \u2014 2026-07-27 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 8/12 correct (65%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d73\n self-advocacy statements: 6/10 correct (60%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d73\n brushing teeth independently: 9/15 correct (58%); latency 3.3s; prompts FP\u00d72, PP\u00d75, G\u00d71, I\u00d77\n scheduling medical appointments: 7/10 correct (65%); latency 3.3s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d76\n Toileting accident (urine or bowel): urine: 0 in-toilet / 5 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 5 \u2014 2026-07-29 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 7/11 correct (63%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n self-advocacy statements: 5/9 correct (54%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n brushing teeth independently: 7/14 correct (51%); latency 3.7s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d711\n scheduling medical appointments: 5/8 correct (58%); latency 3.6s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d75\n Toileting accident (urine or bowel): urine: 0 in-toilet / 4 accidents; BM: 0 in-toilet / 2 accidents\n\nSession 6 \u2014 2026-07-31 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 6/10 correct (59%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d73\n self-advocacy statements: 6/13 correct (42%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d78\n brushing teeth independently: 4/8 correct (45%); latency 3.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n scheduling medical appointments: 4/9 correct (44%); latency 3.7s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d72\n Toileting accident (urine or bowel): urine: 1 in-toilet / 6 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 7 \u2014 2026-08-02 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 5/10 correct (47%); latency 3.8s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d72\n self-advocacy statements: 5/12 correct (42%); latency 4.1s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d78\n brushing teeth independently: 4/13 correct (34%); latency 4.2s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d74\n scheduling medical appointments: 3/8 correct (41%); latency 3.9s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n Toileting accident (urine or bowel): urine: 2 in-toilet / 6 accidents; BM: 1 in-toilet / 0 accidents\n\nSession 8 \u2014 2026-08-04 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 6/11 correct (52%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d75\n self-advocacy statements: 3/9 correct (39%); latency 4.1s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d74\n brushing teeth independently: 4/14 correct (28%); latency 4.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d710\n scheduling medical appointments: 5/15 correct (35%); latency 4.2s; prompts FP\u00d73, PP\u00d73, G\u00d75, I\u00d74\n Toileting accident (urine or bowel): urine: 1 in-toilet / 4 accidents; BM: 0 in-toilet / 2 accidents\n\nSession 9 \u2014 2026-08-06 \u2014 44 min \u2014 1 observer\n requesting assistance using AAC device: 4/8 correct (44%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n self-advocacy statements: 2/8 correct (27%); latency 4.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n brushing teeth independently: 2/10 correct (23%); latency 4.9s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n scheduling medical appointments: 3/14 correct (21%); latency 5.1s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d75\n Toileting accident (urine or bowel): urine: 0 in-toilet / 7 accidents; BM: 0 in-toilet / 0 accidents\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Pushing materials away from the work area\n- Crying during demand presentation\n- Turning away from task or staff"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (81% -> 44%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nToileting accident (urine or bowel): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 62.0%.\n- Trend direction: downward (first session: 81%, last session: 44%).\n- Toileting accident (urine or bowel): mean 5.1/session (early-window mean 3.3 -> late-window mean 6.3).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "7ab4a36f97d4b956", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Toileting accident (urine or bowel)": "escape"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "adult", "n_sessions": 9, "n_programs": 4, "n_behaviors": 1, "behavior_ids": ["toileting_accident"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "6686"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a chaining program for the following.\n\nSkill: clocking in at start of shift\nCurriculum: AFLS Vocational Skills\nLearner Level: Adolescent Learner\nBaseline: Developing\n\nInclude the full Task Analysis structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: clocking in at start of shift\n- Curriculum: AFLS Vocational Skills\n- Learner: Adolescent Learner\n- Current mastery: Developing\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Arrive at the workplace by the scheduled time.\n2. Locate the time clock or digital system.\n3. Enter identification (ID card / badge / code).\n4. Confirm the clock-in timestamp.\n5. Notify the supervisor or check the day's task list.\n6. Proceed to the assigned workstation.\n\n## Prompt Strategy Per Step\nStrategy: Graduated Guidance\nHand-over-hand physical guidance with fading pressure; move to shadow, then independent.\nCurrent prompt level: At the developing stage, provide hand-over-hand guidance at each step; reduce physical pressure across sessions.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nCRF per step (acquisition) \u2014 Continuous reinforcement for each correctly-completed step during acquisition.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed independently with 2 different adults in 2 different settings across 2 consecutive days.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "d28df9505938b55d", "gold_labels": {"method": "task_analysis", "domain": "AFLS.vocational", "skill": "clocking in at start of shift", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "developing", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "clocking in at start of shift", "module": "vocational", "mastery_criterion": "mc_generalization", "chain_type": "total_task", "prompt_strategy": "graduated_guidance", "reinforcement_schedule": "crf_per_step", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "44637"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3091\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Math\nDate range: Sessions 1\u20135 across 10 days (2026-02-12 to 2026-02-22)\n\nACCELERATION PROGRAMS\n1. identifies numerals 1\u201320 (Math)\n Method: DTT\n2. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n3. counts objects 1\u201320 (Math)\n Method: DTT\n4. requesting preferred items using a full sentence (Mand)\n Method: NET\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-12 \u2014 58 min \u2014 1 observer\n identifies numerals 1\u201320: 4/12 correct (31%); latency 4.7s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 2/11 correct (22%); latency 4.9s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n counts objects 1\u201320: 3/11 correct (29%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n requesting preferred items using a full sentence: 4/12 correct (35%); latency 4.5s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d75\n\nSession 2 \u2014 2026-02-14 \u2014 58 min \u2014 1 observer\n identifies numerals 1\u201320: 4/9 correct (40%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/8 correct (37%); latency 4.6s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n counts objects 1\u201320: 5/14 correct (34%); latency 4.2s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d78\n requesting preferred items using a full sentence: 6/15 correct (41%); latency 4.0s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d77\n\nSession 3 \u2014 2026-02-16 \u2014 58 min \u2014 1 observer\n identifies numerals 1\u201320: 7/12 correct (55%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/12 correct (41%); latency 4.3s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d77\n counts objects 1\u201320: 6/15 correct (42%); latency 3.8s; prompts FP\u00d73, PP\u00d75, G\u00d75, I\u00d72\n requesting preferred items using a full sentence: 8/15 correct (54%); latency 3.5s; prompts FP\u00d71, PP\u00d73, G\u00d75, I\u00d76\n\nSession 4 \u2014 2026-02-18 \u2014 58 min \u2014 1 observer\n identifies numerals 1\u201320: 7/12 correct (60%); latency 3.5s; prompts FP\u00d70, PP\u00d74, G\u00d72, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/15 correct (50%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d710\n counts objects 1\u201320: 6/13 correct (49%); latency 4.0s; prompts FP\u00d73, PP\u00d74, G\u00d74, I\u00d72\n requesting preferred items using a full sentence: 7/10 correct (66%); latency 3.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d77\n\nSession 5 \u2014 2026-02-20 \u2014 58 min \u2014 1 observer\n identifies numerals 1\u201320: 7/10 correct (74%); latency 3.0s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/12 correct (61%); latency 3.0s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d75\n counts objects 1\u201320: 5/8 correct (59%); latency 3.1s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n requesting preferred items using a full sentence: 7/9 correct (73%); latency 2.7s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Reaching for materials proactively\n- Smiling during reinforcement delivery"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 31% to 74% across 5 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 5 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 5 sessions: 52.0%.\n- Trend direction: upward (first session: 31%, last session: 74%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "38523ee2605e059d", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "school_age", "n_sessions": 5, "n_programs": 4, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "42504"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: selects correct item from an array of 2\nCurriculum: Listener Responding L1\nLearner: Early Learner\nMastery Status: Developing\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects correct item from an array of 2\n- Curriculum: Listener Responding L1\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: backpack, block, scissors\nDistractor stimuli: bottle, ball\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "6f400751336bfa39", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L1", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects correct item from an array of 2", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "crf", "error_correction": "simple_correction", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "70400"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3089\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Independent Living + Vocational\nDate range: Sessions 1\u201311 across 22 days (2026-10-13 to 2026-11-04)\n\nACCELERATION PROGRAMS\n1. managing a budget (Independent Living)\n Method: Task Analysis\n2. self-advocacy statements (Independent Living)\n Method: BST\n3. clocking in at start of shift (Vocational)\n Method: Task Analysis\n4. scheduling medical appointments (Independent Living)\n Method: Task Analysis\n5. doing laundry (Home Skills)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-13 \u2014 32 min \u2014 1 observer\n managing a budget: 7/8 correct (91%); latency 1.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n self-advocacy statements: 10/11 correct (88%); latency 1.8s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d77\n clocking in at start of shift: 11/14 correct (79%); latency 2.7s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d712\n scheduling medical appointments: 11/13 correct (83%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d78\n doing laundry: 12/13 correct (95%); latency 1.5s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d78\n\nSession 2 \u2014 2026-10-15 \u2014 32 min \u2014 1 observer\n managing a budget: 8/8 correct (94%); latency 1.7s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n self-advocacy statements: 12/13 correct (92%); latency 1.6s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d710\n clocking in at start of shift: 10/13 correct (79%); latency 2.2s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d76\n scheduling medical appointments: 13/15 correct (85%); latency 2.1s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d710\n doing laundry: 10/11 correct (94%); latency 1.9s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n\nSession 3 \u2014 2026-10-17 \u2014 32 min \u2014 1 observer\n managing a budget: 9/9 correct (95%); latency 1.4s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d75\n self-advocacy statements: 12/14 correct (89%); latency 2.0s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d78\n clocking in at start of shift: 6/8 correct (79%); latency 2.3s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n scheduling medical appointments: 10/12 correct (82%); latency 2.4s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d76\n doing laundry: 14/15 correct (92%); latency 1.9s; prompts FP\u00d75, PP\u00d74, G\u00d71, I\u00d75\n\nSession 4 \u2014 2026-10-19 \u2014 32 min \u2014 1 observer\n managing a budget: 14/15 correct (93%); latency 2.0s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d712\n self-advocacy statements: 11/12 correct (90%); latency 2.2s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d75\n clocking in at start of shift: 7/9 correct (80%); latency 2.1s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n scheduling medical appointments: 9/11 correct (85%); latency 2.0s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n doing laundry: 10/11 correct (95%); latency 1.5s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d710\n\nSession 5 \u2014 2026-10-21 \u2014 32 min \u2014 1 observer\n managing a budget: 10/11 correct (87%); latency 2.3s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d76\n self-advocacy statements: 13/14 correct (90%); latency 2.2s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d711\n clocking in at start of shift: 8/10 correct (76%); latency 2.4s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d71\n scheduling medical appointments: 12/15 correct (78%); latency 2.4s; prompts FP\u00d75, PP\u00d73, G\u00d75, I\u00d72\n doing laundry: 9/10 correct (93%); latency 1.8s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d76\n\nSession 6 \u2014 2026-10-23 \u2014 32 min \u2014 1 observer\n managing a budget: 9/10 correct (91%); latency 2.0s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n self-advocacy statements: 7/8 correct (89%); latency 1.9s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n clocking in at start of shift: 9/13 correct (73%); latency 2.7s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n scheduling medical appointments: 7/8 correct (82%); latency 2.2s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n doing laundry: 10/11 correct (94%); latency 1.8s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n\nSession 7 \u2014 2026-10-25 \u2014 32 min \u2014 1 observer\n managing a budget: 8/9 correct (88%); latency 1.8s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n self-advocacy statements: 8/9 correct (92%); latency 2.1s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n clocking in at start of shift: 8/11 correct (72%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d75\n scheduling medical appointments: 10/12 correct (82%); latency 2.1s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d78\n doing laundry: 12/13 correct (91%); latency 2.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d710\n\nSession 8 \u2014 2026-10-27 \u2014 32 min \u2014 1 observer\n managing a budget: 13/15 correct (87%); latency 2.2s; prompts FP\u00d75, PP\u00d72, G\u00d74, I\u00d74\n self-advocacy statements: 10/11 correct (92%); latency 2.1s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n clocking in at start of shift: 11/15 correct (73%); latency 2.5s; prompts FP\u00d75, PP\u00d71, G\u00d74, I\u00d75\n scheduling medical appointments: 6/8 correct (76%); latency 2.5s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d77\n doing laundry: 11/12 correct (94%); latency 2.0s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d710\n\nSession 9 \u2014 2026-10-29 \u2014 32 min \u2014 1 observer\n managing a budget: 11/12 correct (92%); latency 1.8s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d78\n self-advocacy statements: 7/8 correct (91%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n clocking in at start of shift: 10/13 correct (75%); latency 2.3s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d76\n scheduling medical appointments: 10/13 correct (78%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d713\n doing laundry: 8/9 correct (87%); latency 1.9s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d72\n\nSession 10 \u2014 2026-10-31 \u2014 32 min \u2014 1 observer\n managing a budget: 12/14 correct (87%); latency 2.3s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d711\n self-advocacy statements: 14/15 correct (97%); latency 1.7s; prompts FP\u00d74, PP\u00d71, G\u00d75, I\u00d75\n clocking in at start of shift: 10/13 correct (75%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d77\n scheduling medical appointments: 8/10 correct (75%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d77\n doing laundry: 9/10 correct (92%); latency 2.2s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n\nSession 11 \u2014 2026-11-02 \u2014 32 min \u2014 1 observer\n managing a budget: 12/13 correct (89%); latency 2.2s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d76\n self-advocacy statements: 9/9 correct (98%); latency 1.6s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d79\n clocking in at start of shift: 8/11 correct (71%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d76\n scheduling medical appointments: 12/15 correct (82%); latency 2.2s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d78\n doing laundry: 8/9 correct (92%); latency 2.0s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d77\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Leaving seat without permission\n- Playing with non-task materials\n- Delayed responding (>5 seconds consistently)\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (91%\u201389%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 11 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 11 sessions: 90.3%.\n- Trend direction: downward (first session: 91%, last session: 89%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "acb13453f24cdb34", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "adult", "n_sessions": 11, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "39407"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-2332\nProfile: School-Age Learner (6\u201312 years)\nCurricula: Mand + Reading + Tolerating Denied Access\nDate range: Sessions 1\u201312 across 24 days (2026-01-07 to 2026-01-31)\n\nACCELERATION PROGRAMS\n1. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n2. sounds out CVC words (Reading)\n Method: DTT\n3. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n4. single-word requests for preferred items (Mand)\n Method: NET\n5. mands for missing items needed to complete an activity (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Toileting accident (urine or bowel) \u2014 function hypothesized: escape\n2. Property destruction \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-07 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/10 correct (78%); latency 2.7s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n sounds out CVC words: 9/13 correct (68%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d710\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/8 correct (75%); latency 2.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n single-word requests for preferred items: 7/9 correct (76%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n mands for missing items needed to complete an activity: 12/14 correct (86%); latency 2.3s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d79\n Toileting accident (urine or bowel): urine: 3 in-toilet / 2 accidents; BM: 0 in-toilet / 1 accidents\n Property destruction: freq 2\n\nSession 2 \u2014 2026-01-09 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/10 correct (76%); latency 2.7s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d73\n sounds out CVC words: 6/9 correct (72%); latency 2.5s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/9 correct (73%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d72\n single-word requests for preferred items: 10/15 correct (66%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d75, I\u00d76\n mands for missing items needed to complete an activity: 9/12 correct (78%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d79\n Toileting accident (urine or bowel): urine: 1 in-toilet / 3 accidents; BM: 0 in-toilet / 0 accidents\n Property destruction: freq 3\n\nSession 3 \u2014 2026-01-11 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/11 correct (73%); latency 2.5s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d74\n sounds out CVC words: 6/10 correct (59%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/11 correct (68%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n single-word requests for preferred items: 9/13 correct (70%); latency 2.9s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d75\n mands for missing items needed to complete an activity: 10/14 correct (72%); latency 3.0s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n Toileting accident (urine or bowel): urine: 5 in-toilet / 2 accidents; BM: 0 in-toilet / 0 accidents\n Property destruction: freq 2\n\nSession 4 \u2014 2026-01-13 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/12 correct (66%); latency 2.8s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d73\n sounds out CVC words: 7/11 correct (60%); latency 3.0s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/13 correct (68%); latency 3.1s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d77\n single-word requests for preferred items: 8/13 correct (65%); latency 3.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d711\n mands for missing items needed to complete an activity: 8/11 correct (74%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d77\n Toileting accident (urine or bowel): urine: 3 in-toilet / 3 accidents; BM: 0 in-toilet / 0 accidents\n Property destruction: freq 3\n\nSession 5 \u2014 2026-01-15 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 9/15 correct (58%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d78\n sounds out CVC words: 4/8 correct (56%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/11 correct (57%); latency 3.6s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n single-word requests for preferred items: 9/15 correct (59%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d75, I\u00d79\n mands for missing items needed to complete an activity: 6/9 correct (65%); latency 2.8s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n Toileting accident (urine or bowel): urine: 3 in-toilet / 2 accidents; BM: 0 in-toilet / 1 accidents\n Property destruction: freq 3\n\nSession 6 \u2014 2026-01-17 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 5/11 correct (48%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d76\n sounds out CVC words: 4/8 correct (47%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/15 correct (54%); latency 3.5s; prompts FP\u00d75, PP\u00d73, G\u00d74, I\u00d73\n single-word requests for preferred items: 6/12 correct (53%); latency 3.4s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d78\n mands for missing items needed to complete an activity: 9/14 correct (61%); latency 3.0s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d75\n Toileting accident (urine or bowel): urine: 3 in-toilet / 4 accidents; BM: 0 in-toilet / 0 accidents\n Property destruction: freq 3\n\nSession 7 \u2014 2026-01-19 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 5/11 correct (43%); latency 4.2s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d76\n sounds out CVC words: 5/11 correct (46%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d73, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/15 correct (54%); latency 3.8s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d77\n single-word requests for preferred items: 6/11 correct (50%); latency 3.7s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n mands for missing items needed to complete an activity: 7/12 correct (60%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d78\n Toileting accident (urine or bowel): urine: 1 in-toilet / 4 accidents; BM: 0 in-toilet / 1 accidents\n Property destruction: freq 3\n\nSession 8 \u2014 2026-01-21 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 4/11 correct (38%); latency 4.5s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n sounds out CVC words: 5/13 correct (37%); latency 4.1s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/12 correct (49%); latency 3.7s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d75\n single-word requests for preferred items: 5/12 correct (45%); latency 3.8s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d74\n mands for missing items needed to complete an activity: 8/15 correct (52%); latency 3.9s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d78\n Toileting accident (urine or bowel): urine: 3 in-toilet / 4 accidents; BM: 1 in-toilet / 0 accidents\n Property destruction: freq 4\n\nSession 9 \u2014 2026-01-23 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 5/15 correct (32%); latency 4.7s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d77\n sounds out CVC words: 6/15 correct (38%); latency 4.3s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d77\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 4/8 correct (48%); latency 4.1s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n single-word requests for preferred items: 5/11 correct (42%); latency 4.2s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n mands for missing items needed to complete an activity: 5/10 correct (54%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d77\n Toileting accident (urine or bowel): urine: 0 in-toilet / 4 accidents; BM: 0 in-toilet / 1 accidents\n Property destruction: freq 5\n\nSession 10 \u2014 2026-01-25 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 3/12 correct (27%); latency 4.9s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d73\n sounds out CVC words: 3/10 correct (30%); latency 4.9s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 6/14 correct (46%); latency 3.7s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d75\n single-word requests for preferred items: 5/13 correct (38%); latency 4.2s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d75\n mands for missing items needed to complete an activity: 6/14 correct (45%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d75\n Toileting accident (urine or bowel): urine: 2 in-toilet / 4 accidents; BM: 0 in-toilet / 1 accidents\n Property destruction: freq 5\n\nSession 11 \u2014 2026-01-27 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 2/11 correct (18%); latency 4.9s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d74\n sounds out CVC words: 3/9 correct (31%); latency 4.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 3/10 correct (34%); latency 4.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d76\n single-word requests for preferred items: 3/9 correct (31%); latency 4.6s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d75\n mands for missing items needed to complete an activity: 4/10 correct (39%); latency 4.5s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d76\n Toileting accident (urine or bowel): urine: 2 in-toilet / 4 accidents; BM: 0 in-toilet / 0 accidents\n Property destruction: freq 5\n\nSession 12 \u2014 2026-01-29 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 2/13 correct (12%); latency 5.7s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n sounds out CVC words: 3/14 correct (24%); latency 5.0s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d79\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 5/13 correct (37%); latency 4.3s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d78\n single-word requests for preferred items: 2/11 correct (22%); latency 4.9s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d78\n mands for missing items needed to complete an activity: 3/8 correct (40%); latency 4.3s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n Toileting accident (urine or bowel): urine: 0 in-toilet / 5 accidents; BM: 1 in-toilet / 1 accidents\n Property destruction: freq 5\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Turning away from task or staff\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Increased response latency (3\u20135\u00d7 baseline)\n- Vocal refusal ('no', 'I don't want to')"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 78% to 12% across 12 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nToileting accident (urine or bowel): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\nProperty destruction: attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 47.4%.\n- Trend direction: downward (first session: 78%, last session: 12%).\n- Toileting accident (urine or bowel): mean 3.9/session (early-window mean 2.8 -> late-window mean 5.0).\n- Property destruction: mean 3.6/session (early-window mean 2.5 -> late-window mean 5.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "f380ff3d198961e7", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Toileting accident (urine or bowel)": "escape", "Property destruction": "attention"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "school_age", "n_sessions": 12, "n_programs": 5, "n_behaviors": 2, "behavior_ids": ["toileting_accident", "property_destruction"], "behavior_functions": ["escape", "attention"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "6062"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: identifies place value (ones, tens)\nCurriculum Reference: Math L3\nLearner Profile: School-Age Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies place value (ones, tens)\n- Curriculum: Math L3\n- Learner: School-Age Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What number is this?\"\nVariations: \"Which number?\"; \"Tell me the number\"\nPresentation: Present the numeral card.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: towel, scissors, hat\nDistractor stimuli: pencil, jacket, backpack, apple, cup\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nPrevent errors by using high prompts from the start; fade gradually. Paired with most-to-least prompt hierarchy.\n\n## Reinforcement Schedule\nToken economy \u2014 Tokens delivered per correct response; exchanged at session end for a back-up reinforcer appropriate to the learner (for children: candy, cookies, brief leisure-time access, preferred activity, screen time, or a favorite sensory item). Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "55532e0b6b52e83a", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L3", "learner_profile": "school_age", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies place value (ones, tens)", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "token_economy", "error_correction": "errorless", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "28081"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: tacts abstract concepts (same/different, first/last)\nCurriculum: Tact L3\nLearner Level: Adolescent Learner\nBaseline: Mastered at current level\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: tacts abstract concepts (same/different, first/last)\n- Curriculum: Tact L3\n- Learner: Adolescent Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What is this?\"\nVariations: \"Tell me what you see\"; \"What's that?\"; \"Name this\"\nPresentation: Present the target stimulus within visual field and ask while pointing to it.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: plate, bottle, hat\nDistractor stimuli: blanket, sock, backpack, scissors, napkin\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nFR-2 (fixed ratio 2) \u2014 Every 2nd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy at independent prompt level across 3 sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "d056a9483678d00f", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.tact", "level": "L3", "learner_profile": "adolescent", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "tacts abstract concepts (same/different, first/last)", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "fr2", "error_correction": "four_step", "mastery_criterion": "mc_80_independent"}, "teacher_model": null, "seed_tag": "70400"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a NET program for this skill.\n\nTarget: provides definitions of words\nCurriculum: Intraverbal L3\nLearner: School-Age Learner\nMastery Status: Emerging\n\nPlease include the MO arrangement, natural opportunity, prompt strategy, natural reinforcer, generalization tactics, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: provides definitions of words\n- Curriculum: Intraverbal L3\n- Learner: School-Age Learner\n- Current mastery: Emerging\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nEngage the learner in a naturalistic conversation on a topic of demonstrated interest. Pause at natural turn boundaries to invite the target response.\nPrimary natural context: post-activity debrief.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's post-activity debrief routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the emerging stage, begin with a model prompt delivered during the motivated moment; fade to expectant look across sessions.\n\n## Natural Reinforcer\nNatural reinforcer: conversation continues with adult's naturally matched reply.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "550f8896125a0c2a", "gold_labels": {"method": "net", "domain": "VB-MAPP.intraverbal", "level": "L3", "learner_profile": "school_age", "mastery_state": "emerging"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "provides definitions of words", "mo_category": "intraverbal_multi_turn", "mo_arrangement": "reciprocal_conversation", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "54871"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5254\nProfile: Adult Learner (18+ years)\nCurricula: Community + Mand + Self-Care + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u20138 across 16 days (2026-01-10 to 2026-01-26)\n\nACCELERATION PROGRAMS\n1. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n2. using public transportation (Community)\n Method: Task Analysis\n3. requesting assistance using AAC device (Mand)\n Method: NET\n4. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n5. washing hands independently (Self-Care)\n Method: Task Analysis\n\nDECELERATION TARGETS\n1. Fecal smearing (scatolia) \u2014 function hypothesized: attention\n2. Self-injurious behavior (SIB) \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-10 \u2014 43 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 9/13 correct (69%); latency 2.7s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d710\n using public transportation: 8/10 correct (84%); latency 2.1s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d77\n requesting assistance using AAC device: 7/10 correct (67%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d75\n completing assigned tasks in order: 7/10 correct (72%); latency 3.0s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n washing hands independently: 7/9 correct (75%); latency 2.5s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n Fecal smearing (scatolia): attempts 3 (2 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n Self-injurious behavior (SIB): freq 2\n\nSession 2 \u2014 2026-01-12 \u2014 43 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 10/14 correct (69%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n using public transportation: 6/8 correct (78%); latency 2.7s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n requesting assistance using AAC device: 5/8 correct (63%); latency 3.3s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d76\n completing assigned tasks in order: 8/12 correct (68%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d77\n washing hands independently: 6/9 correct (71%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d74\n Fecal smearing (scatolia): attempts 3 (2 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n Self-injurious behavior (SIB): freq 2\n\nSession 3 \u2014 2026-01-14 \u2014 43 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 8/12 correct (63%); latency 3.2s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d75\n using public transportation: 11/15 correct (74%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d77\n requesting assistance using AAC device: 7/12 correct (60%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d74, I\u00d75\n completing assigned tasks in order: 9/14 correct (63%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d711\n washing hands independently: 8/13 correct (65%); latency 2.9s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d711\n Fecal smearing (scatolia): attempts 5 (4 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n Self-injurious behavior (SIB): freq 2\n\nSession 4 \u2014 2026-01-16 \u2014 43 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 4/8 correct (53%); latency 3.5s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n using public transportation: 8/12 correct (70%); latency 2.8s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d78\n requesting assistance using AAC device: 6/13 correct (49%); latency 4.1s; prompts FP\u00d74, PP\u00d70, G\u00d72, I\u00d77\n completing assigned tasks in order: 5/10 correct (55%); latency 3.4s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d78\n washing hands independently: 8/14 correct (58%); latency 3.2s; prompts FP\u00d70, PP\u00d74, G\u00d70, I\u00d710\n Fecal smearing (scatolia): attempts 4 (4 intercepted \u2014 staff redirected before smearing; 0 completed \u2014 feces transferred to skin, clothing, or surface)\n Self-injurious behavior (SIB): freq 5\n\nSession 5 \u2014 2026-01-18 \u2014 43 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 7/15 correct (48%); latency 3.5s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d77\n using public transportation: 6/10 correct (62%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d78\n requesting assistance using AAC device: 7/14 correct (48%); latency 4.1s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d77\n completing assigned tasks in order: 6/13 correct (47%); latency 3.8s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d710\n washing hands independently: 4/9 correct (44%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n Fecal smearing (scatolia): attempts 6 (4 intercepted \u2014 staff redirected before smearing; 2 completed \u2014 feces transferred to skin, clothing, or surface)\n Self-injurious behavior (SIB): freq 4\n\nSession 6 \u2014 2026-01-20 \u2014 43 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 5/10 correct (46%); latency 4.0s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n using public transportation: 8/14 correct (58%); latency 3.3s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d76\n requesting assistance using AAC device: 5/13 correct (41%); latency 4.3s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d76\n completing assigned tasks in order: 6/13 correct (45%); latency 4.1s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d74\n washing hands independently: 6/13 correct (44%); latency 4.2s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d77\n Fecal smearing (scatolia): attempts 6 (5 intercepted \u2014 staff redirected before smearing; 1 completed \u2014 feces transferred to skin, clothing, or surface)\n Self-injurious behavior (SIB): freq 5\n\nSession 7 \u2014 2026-01-22 \u2014 43 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 5/12 correct (39%); latency 4.0s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d72\n using public transportation: 8/14 correct (54%); latency 3.4s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d76\n requesting assistance using AAC device: 3/8 correct (38%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d74\n completing assigned tasks in order: 3/10 correct (32%); latency 4.9s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d74\n washing hands independently: 4/15 correct (29%); latency 4.7s; prompts FP\u00d73, PP\u00d75, G\u00d74, I\u00d73\n Fecal smearing (scatolia): attempts 7 (5 intercepted \u2014 staff redirected before smearing; 2 completed \u2014 feces transferred to skin, clothing, or surface)\n Self-injurious behavior (SIB): freq 5\n\nSession 8 \u2014 2026-01-24 \u2014 43 min \u2014 1 observer\n wait calmly when a preferred activity is denied: 3/8 correct (39%); latency 4.5s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n using public transportation: 5/9 correct (53%); latency 3.6s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n requesting assistance using AAC device: 3/10 correct (29%); latency 4.8s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d75\n completing assigned tasks in order: 4/13 correct (29%); latency 4.9s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d710\n washing hands independently: 3/14 correct (25%); latency 4.9s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d712\n Fecal smearing (scatolia): attempts 8 (5 intercepted \u2014 staff redirected before smearing; 3 completed \u2014 feces transferred to skin, clothing, or surface)\n Self-injurious behavior (SIB): freq 6\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Pushing materials away from the work area\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)\n- Increased response latency (3\u20135\u00d7 baseline)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Frustration pattern**: declining accuracy (69% -> 39%) with escape-indicator behaviors.\n- Risk of learned helplessness and escape-maintained behavior if not addressed.\n\n## Pattern Classification\nfrustration_pattern\n\nDeclining accuracy co-occurs with escape-indicator behaviors, consistent with frustration and escape-maintained responding to demand.\n\n## Behavior Function Hypothesis\nFecal smearing (scatolia): attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\nSelf-injurious behavior (SIB): escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- **Immediately** reduce task difficulty \u2014 drop back 1\u20132 prompt levels or present previously-mastered targets.\n- Intersperse easy (mastered) tasks with acquisition targets at a 3:1 or 4:1 ratio.\n- Shorten session length and increase break frequency.\n\n### Replacement behavior (FCT)\n- Teach a replacement response ('break please', 'wait please', 'all done') and reinforce it at the function of the problem behavior.\n- Pair the replacement response with short, predictable escape windows.\n\n### Consequence strategies\n- Do NOT remove demand contingent on tantrum / escape behavior \u2014 this reinforces the escape function.\n- Provide brief break contingent on independent replacement response instead.\n\n### Crisis plan\n- If aggression toward staff, peer aggression, SIB, or property destruction exceeds the learner's safety threshold: first use verbal de-escalation and environmental safety measures (clear the area, move peers to safe distance, remove hazards).\n- If behavior continues to pose imminent risk, follow the facility's tiered crisis-intervention protocol \u2014 only staff currently certified in the facility's training (e.g., Safety-Care, CPI, PMT, or equivalent) may implement physical intervention, and the least-restrictive option appropriate to the risk level is used. Physical intervention is applied only when specifically authorized in this learner's BIP; for learners with contraindications (medical, developmental, trauma history, or explicit BIP restrictions), the plan stops at de-escalation + environmental safety + supervisor contact.\n- Notify the supervising BCBA immediately; pause the skill-acquisition program until the BIP is reviewed. Document the incident (antecedent, topography, duration, staff response, post-incident state) per facility and BACB Ethics Code (2020, Section 3.05) requirements.\n\n## Escalation Level\n4 \u2014 Safety immediate\n\nSafety-critical signals require immediate cessation of current program and direct BCBA contact; consider crisis-plan activation.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 53.1%.\n- Trend direction: downward (first session: 69%, last session: 39%).\n- Fecal smearing (scatolia): mean 5.2/session (early-window mean 3.0 -> late-window mean 7.5).\n- Self-injurious behavior (SIB): mean 3.9/session (early-window mean 2.0 -> late-window mean 5.5).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "ce183713e1ab3651", "gold_labels": {"pattern_class": "frustration_pattern", "behavior_functions": {"Fecal smearing (scatolia)": "attention", "Self-injurious behavior (SIB)": "escape"}, "escalation_level": 4, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "frustration_pattern", "learner_profile": "adult", "n_sessions": 8, "n_programs": 5, "n_behaviors": 2, "behavior_ids": ["fecal_smearing", "sib"], "behavior_functions": ["attention", "escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "55369"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: ordering in a restaurant\nCurriculum Reference: AFLS Community Participation Skills\nLearner Profile: Adolescent Learner\nCurrent Mastery: Near mastery\nTeaching Method: Task Analysis / Chaining\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: ordering in a restaurant\n- Curriculum: AFLS Community Participation Skills\n- Learner: Adolescent Learner\n- Current mastery: Near mastery\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Backward chaining\nComplete all steps for the learner except the last; teach the last step first, then work backward. The final reinforcer (task completion) is always present for the learner.\n\nSteps:\n1. Approach the counter or wait to be seated.\n2. Review the menu.\n3. Decide on a choice.\n4. Place the order verbally (or with an AAC device).\n5. Respond to clarifying questions.\n6. Pay using money or a card.\n7. Wait for the order and collect it. <- Learner-taught step (backward chaining starts here)\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the near mastery stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nToken economy \u2014 One token per correctly-completed step; token exchange at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 60s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "bbcedfdf0100038b", "gold_labels": {"method": "task_analysis", "domain": "AFLS.community", "skill": "ordering in a restaurant", "program_type": "independence", "learner_profile": "adolescent", "mastery_state": "near", "chain_type": "backward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "ordering in a restaurant", "module": "community", "mastery_criterion": "mc_fluent_chain", "chain_type": "backward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "97806"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-3841\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Mand + Reading + Self-Care\nDate range: Sessions 1\u20138 across 16 days (2026-10-04 to 2026-10-20)\n\nACCELERATION PROGRAMS\n1. requesting preferred items using AAC device (Mand)\n Method: NET\n2. identifying community safety signs (Community)\n Method: DTT\n3. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n4. brushing teeth independently (Self-Care)\n Method: Task Analysis\n5. sounds out CVC words (Reading)\n Method: DTT\n\nDECELERATION TARGETS\n1. Property destruction \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-10-04 \u2014 34 min \u2014 1 observer\n requesting preferred items using AAC device: 8/11 correct (71%); latency 2.9s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n identifying community safety signs: 11/15 correct (76%); latency 2.5s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d77\n meal cleanup after eating: 10/13 correct (78%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d76\n brushing teeth independently: 7/9 correct (80%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d77\n sounds out CVC words: 12/15 correct (81%); latency 2.6s; prompts FP\u00d71, PP\u00d73, G\u00d75, I\u00d76\n Property destruction: freq 2\n\nSession 2 \u2014 2026-10-06 \u2014 34 min \u2014 1 observer\n requesting preferred items using AAC device: 6/8 correct (70%); latency 3.1s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n identifying community safety signs: 7/9 correct (78%); latency 2.6s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d75\n meal cleanup after eating: 8/12 correct (65%); latency 3.2s; prompts FP\u00d74, PP\u00d72, G\u00d73, I\u00d73\n brushing teeth independently: 11/15 correct (72%); latency 2.5s; prompts FP\u00d75, PP\u00d73, G\u00d71, I\u00d76\n sounds out CVC words: 8/12 correct (66%); latency 2.9s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d710\n Property destruction: freq 3\n\nSession 3 \u2014 2026-10-08 \u2014 34 min \u2014 1 observer\n requesting preferred items using AAC device: 8/14 correct (59%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d713\n identifying community safety signs: 9/14 correct (62%); latency 3.0s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d79\n meal cleanup after eating: 7/12 correct (58%); latency 3.5s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d76\n brushing teeth independently: 6/9 correct (66%); latency 3.2s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d73\n sounds out CVC words: 5/8 correct (59%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n Property destruction: freq 4\n\nSession 4 \u2014 2026-10-10 \u2014 IOA SESSION \u2014 2 observers\n requesting preferred items using AAC device: 54% (primary); IOA 82% agreement\n identifying community safety signs: 62% (primary); IOA 82% agreement\n meal cleanup after eating: 52% (primary); IOA 82% agreement\n brushing teeth independently: 54% (primary); IOA 82% agreement\n sounds out CVC words: 55% (primary); IOA 82% agreement\n Property destruction: freq 4; IOA 82% agreement\n\nSession 5 \u2014 2026-10-12 \u2014 34 min \u2014 1 observer\n requesting preferred items using AAC device: 7/13 correct (53%); latency 3.8s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d76\n identifying community safety signs: 7/13 correct (54%); latency 3.6s; prompts FP\u00d74, PP\u00d73, G\u00d70, I\u00d76\n meal cleanup after eating: 4/8 correct (46%); latency 4.1s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n brushing teeth independently: 7/13 correct (55%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d78\n sounds out CVC words: 4/9 correct (43%); latency 4.0s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d77\n Property destruction: freq 5\n\nSession 6 \u2014 2026-10-14 \u2014 34 min \u2014 1 observer\n requesting preferred items using AAC device: 7/14 correct (49%); latency 3.6s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d77\n identifying community safety signs: 6/15 correct (43%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d79\n meal cleanup after eating: 5/11 correct (45%); latency 4.3s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n brushing teeth independently: 6/12 correct (47%); latency 3.9s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d73\n sounds out CVC words: 4/10 correct (40%); latency 4.5s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d77\n Property destruction: freq 4\n\nSession 7 \u2014 2026-10-16 \u2014 34 min \u2014 1 observer\n requesting preferred items using AAC device: 3/8 correct (37%); latency 4.4s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d75\n identifying community safety signs: 4/12 correct (35%); latency 4.1s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d710\n meal cleanup after eating: 4/11 correct (38%); latency 4.4s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d75\n brushing teeth independently: 5/15 correct (33%); latency 4.5s; prompts FP\u00d75, PP\u00d70, G\u00d74, I\u00d76\n sounds out CVC words: 3/9 correct (29%); latency 4.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n Property destruction: freq 6\n\nSession 8 \u2014 2026-10-18 \u2014 34 min \u2014 1 observer\n requesting preferred items using AAC device: 4/14 correct (30%); latency 4.6s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d79\n identifying community safety signs: 3/9 correct (29%); latency 4.7s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d74\n meal cleanup after eating: 4/12 correct (35%); latency 4.7s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d77\n brushing teeth independently: 2/8 correct (27%); latency 4.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n sounds out CVC words: 2/9 correct (22%); latency 5.3s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d78\n Property destruction: freq 6\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Self-stimulatory behavior increase during demand periods\n- Turning away from task or staff\n- Elopement from the work area\n- Aggression attempt directed at staff (hit, kick, or scratch toward adult)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Regression identified**: accuracy has declined from 71% to 30% across 8 sessions.\n- Accompanying behavior data suggests the decline may be function-related.\n\n## Pattern Classification\nregression\n\nPreviously-established responding has declined across recent sessions, warranting review of environmental and reinforcement variables.\n\n## Behavior Function Hypothesis\nProperty destruction: attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Conduct reinforcer assessment to identify current high-preference items.\n- Review recent environmental or schedule changes that may be affecting performance.\n- Return temporarily to a previously-mastered prompt level and re-fade systematically.\n\n### Replacement behavior (FCT)\n- If problem behavior accompanies regression, strengthen replacement-behavior training for the hypothesized function.\n\n### Consequence strategies\n- Increase reinforcement magnitude and schedule temporarily (return to CRF if needed).\n- Implement more frequent maintenance probes (at least weekly) after re-mastery.\n\n### Crisis plan\n- If regression co-occurs with severe behavior (SIB, aggression, property destruction) reaching the learner's safety threshold: pause all skill-acquisition programming, implement environmental safety measures (clear the area of hazards, move peers to safe distance), and contact the supervising BCBA.\n- Staff should first attempt verbal de-escalation and least-restrictive strategies; physical intervention is used only as a last resort and only by staff currently certified in the facility's crisis-prevention framework (e.g., Safety-Care, CPI, or equivalent).\n- Physical intervention is applied only when specifically authorized in this learner's BIP. Many learners have contraindications (medical conditions, developmental or age-related factors, trauma history, or explicit BIP restrictions) that rule out restrictive procedures \u2014 in those cases the crisis plan defaults to verbal de-escalation, environmental safety measures, and immediate supervisor / emergency contact without physical intervention.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nhigh\n\nPattern is well-supported: 8 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 52.9%.\n- Trend direction: downward (first session: 71%, last session: 30%).\n- Property destruction: mean 4.2/session (early-window mean 2.5 -> late-window mean 6.0).\n- IOA data: 82% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "8ac09633bbe9844a", "gold_labels": {"pattern_class": "regression", "behavior_functions": {"Property destruction": "attention"}, "escalation_level": 3, "confidence": "high", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "regression", "learner_profile": "adolescent", "n_sessions": 8, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["property_destruction"], "behavior_functions": ["attention"], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "54692"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: maintains friendships over time\nCurriculum Reference: Social Behavior & Social Play L3\nLearner Profile: Adolescent Learner\nCurrent Mastery: Near mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: maintains friendships over time\n- Curriculum: Social Behavior & Social Play L3\n- Learner: Adolescent Learner\n- Current mastery: Near mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nArrange a shared activity with one or more peers where the target response is naturally occasioned (turn-taking game, shared snack, collaborative task).\nPrimary natural context: peer play.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's peer play routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Model + immediate fade\nDeliver a vocal/gestural model if no response within the motivated moment; fade to expectant look over sessions.\nCurrent prompt level: At the near mastery stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: peer engages back; activity continues with both.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use across 3 different adults and 2 different settings within 2 weeks.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "7a5ab2737dbc8bb6", "gold_labels": {"method": "net", "domain": "VB-MAPP.social", "level": "L3", "learner_profile": "adolescent", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "maintains friendships over time", "mo_category": "social_initiation", "mo_arrangement": "peer_presence", "prompt_strategy": "model_then_fade", "mastery_criterion": "mc_generalize_multi_therapist"}, "teacher_model": null, "seed_tag": "76914"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9381\nProfile: Adult Learner (18+ years)\nCurricula: Community + Independent Living + Mand + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u20138 across 16 days (2026-06-05 to 2026-06-21)\n\nACCELERATION PROGRAMS\n1. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n2. self-advocacy statements (Independent Living)\n Method: BST\n3. requesting a break during extended tasks (Mand)\n Method: NET\n4. using public transportation (Community)\n Method: Task Analysis\n5. indicating 'all done' at task completion (Mand)\n Method: NET\n6. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n\nSESSION DATA\n\nSession 1 \u2014 2026-06-05 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 2/9 correct (23%); latency 5.3s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d76\n self-advocacy statements: 3/10 correct (32%); latency 4.6s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d74\n requesting a break during extended tasks: 3/9 correct (30%); latency 4.9s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d75\n using public transportation: 3/14 correct (22%); latency 5.3s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d79\n indicating 'all done' at task completion: 3/11 correct (28%); latency 4.5s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d75\n wait calmly when a preferred activity is denied: 3/8 correct (36%); latency 4.6s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n\nSession 2 \u2014 2026-06-07 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 5/14 correct (34%); latency 4.3s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d78\n self-advocacy statements: 5/13 correct (38%); latency 4.4s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d75\n requesting a break during extended tasks: 5/15 correct (33%); latency 4.4s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d710\n using public transportation: 4/12 correct (31%); latency 4.8s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d76\n indicating 'all done' at task completion: 5/13 correct (40%); latency 3.9s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d79\n wait calmly when a preferred activity is denied: 4/8 correct (50%); latency 3.5s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n\nSession 3 \u2014 2026-06-09 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 4/11 correct (41%); latency 4.0s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d75\n self-advocacy statements: 5/10 correct (51%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n requesting a break during extended tasks: 4/10 correct (42%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d72\n using public transportation: 6/15 correct (40%); latency 4.3s; prompts FP\u00d73, PP\u00d75, G\u00d73, I\u00d74\n indicating 'all done' at task completion: 6/12 correct (51%); latency 3.8s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d70\n wait calmly when a preferred activity is denied: 5/9 correct (59%); latency 3.2s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n\nSession 4 \u2014 2026-06-11 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 7/14 correct (51%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d710\n self-advocacy statements: 6/9 correct (65%); latency 2.9s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n requesting a break during extended tasks: 6/12 correct (53%); latency 3.9s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d74\n using public transportation: 7/14 correct (53%); latency 3.8s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d73\n indicating 'all done' at task completion: 6/10 correct (63%); latency 3.2s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d75\n wait calmly when a preferred activity is denied: 11/15 correct (73%); latency 2.4s; prompts FP\u00d72, PP\u00d75, G\u00d74, I\u00d74\n\nSession 5 \u2014 2026-06-13 \u2014 IOA SESSION \u2014 2 observers\n completing assigned tasks in order: 62% (primary); IOA 84% agreement\n self-advocacy statements: 73% (primary); IOA 84% agreement\n requesting a break during extended tasks: 59% (primary); IOA 84% agreement\n using public transportation: 67% (primary); IOA 84% agreement\n indicating 'all done' at task completion: 74% (primary); IOA 84% agreement\n wait calmly when a preferred activity is denied: 81% (primary); IOA 84% agreement\n\nSession 6 \u2014 2026-06-15 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 6/8 correct (73%); latency 2.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n self-advocacy statements: 9/11 correct (83%); latency 2.2s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n requesting a break during extended tasks: 6/9 correct (69%); latency 2.8s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n using public transportation: 8/10 correct (77%); latency 2.8s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d75\n indicating 'all done' at task completion: 13/15 correct (84%); latency 2.4s; prompts FP\u00d72, PP\u00d72, G\u00d74, I\u00d77\n wait calmly when a preferred activity is denied: 10/11 correct (92%); latency 1.6s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d73\n\nSession 7 \u2014 2026-06-17 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 8/9 correct (86%); latency 2.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d75\n self-advocacy statements: 11/12 correct (93%); latency 1.8s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d78\n requesting a break during extended tasks: 11/14 correct (79%); latency 2.4s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d76\n using public transportation: 9/10 correct (90%); latency 2.1s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d74\n indicating 'all done' at task completion: 7/8 correct (94%); latency 1.7s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n wait calmly when a preferred activity is denied: 10/10 correct (97%); latency 1.6s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n\nSession 8 \u2014 2026-06-19 \u2014 54 min \u2014 1 observer\n completing assigned tasks in order: 9/9 correct (95%); latency 1.6s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n self-advocacy statements: 9/9 correct (97%); latency 1.5s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n requesting a break during extended tasks: 11/12 correct (91%); latency 1.8s; prompts FP\u00d74, PP\u00d73, G\u00d74, I\u00d71\n using public transportation: 13/13 correct (97%); latency 1.7s; prompts FP\u00d70, PP\u00d74, G\u00d71, I\u00d78\n indicating 'all done' at task completion: 10/10 correct (97%); latency 1.5s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 8/8 correct (97%); latency 1.5s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d73\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Eye contact maintained throughout trials\n- Appropriate sitting posture maintained\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 23% to 95% across 8 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nhigh\n\nPattern is well-supported: 8 sessions of data, low variance, and IOA evidence confirm reliability.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 58.2%.\n- Trend direction: upward (first session: 23%, last session: 95%).\n- IOA data: 84% agreement on IOA session \u2014 adequate."}], "meta": {"task_type": "session_interpretation", "example_id": "828fa6936749f212", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "high", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "adult", "n_sessions": 8, "n_programs": 6, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": true}, "teacher_model": null, "seed_tag": "42406"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a Task Analysis program for this multi-step skill.\n\nTarget: brushing teeth\nCurriculum: AFLS Basic Living Skills\nLearner: School-Age Learner\nMastery Status: Generalization phase\n\nPlease include the task analysis (numbered steps), chain type, prompt strategy per step, error correction, reinforcement, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: brushing teeth\n- Curriculum: AFLS Basic Living Skills\n- Learner: School-Age Learner\n- Current mastery: Generalization phase\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Total-task presentation\nPrompt the learner through the entire chain every trial; fade prompts across all steps simultaneously.\n\nSteps:\n1. Collect toothbrush and toothpaste.\n2. Wet the toothbrush under water.\n3. Apply a pea-sized amount of toothpaste.\n4. Brush upper-front teeth in small circles for 30 seconds.\n5. Brush lower-front teeth in small circles for 30 seconds.\n6. Brush upper-back teeth (left and right).\n7. Brush lower-back teeth (left and right).\n8. Spit into the sink and rinse mouth.\n9. Rinse the toothbrush and return it to the holder.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the generalization stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nTask reset: Pause the chain; reset environmental stimuli; restart the chain from the beginning with full prompts at the previously-missed step\n\n## Reinforcement\nTerminal reinforcement (mastered) \u2014 Reinforcement delivered only at chain completion; no per-step reinforcement.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nFull chain completed within 180s across 3 consecutive sessions with independent responding on all steps.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 3 different settings and with 2 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "213d35bdc90930a3", "gold_labels": {"method": "task_analysis", "domain": "AFLS.basic_living", "skill": "brushing teeth", "program_type": "independence", "learner_profile": "school_age", "mastery_state": "generalization", "chain_type": "total_task"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "brushing teeth", "module": "basic_living", "mastery_criterion": "mc_fluent_chain", "chain_type": "total_task", "prompt_strategy": "least_to_most", "reinforcement_schedule": "terminal_reinforcement", "error_correction": "task_reset"}, "teacher_model": null, "seed_tag": "75542"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8111\nProfile: Adult Learner (18+ years)\nCurricula: Home Skills + Independent Living + Tolerating Denied Access + Vocational\nDate range: Sessions 1\u201312 across 24 days (2026-05-19 to 2026-06-12)\n\nACCELERATION PROGRAMS\n1. completing assigned tasks in order (Vocational)\n Method: Task Analysis\n2. wait calmly when a preferred activity is denied (Tolerating Denied Access)\n Method: FCT\n3. self-advocacy statements (Independent Living)\n Method: BST\n4. simple meal preparation (Home Skills)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-05-19 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 7/12 correct (55%); latency 3.6s; prompts FP\u00d71, PP\u00d74, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 11/15 correct (72%); latency 2.9s; prompts FP\u00d74, PP\u00d70, G\u00d75, I\u00d76\n self-advocacy statements: 6/15 correct (40%); latency 4.1s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d711\n simple meal preparation: 8/13 correct (59%); latency 3.5s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d74\n\nSession 2 \u2014 2026-05-21 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 3/8 correct (35%); latency 4.4s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n wait calmly when a preferred activity is denied: 5/9 correct (50%); latency 3.8s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n self-advocacy statements: 5/11 correct (49%); latency 3.7s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d72\n simple meal preparation: 10/14 correct (70%); latency 2.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d713\n\nSession 3 \u2014 2026-05-23 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 7/10 correct (66%); latency 3.3s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d76\n wait calmly when a preferred activity is denied: 8/15 correct (54%); latency 3.3s; prompts FP\u00d75, PP\u00d75, G\u00d71, I\u00d74\n self-advocacy statements: 7/15 correct (50%); latency 3.7s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d79\n simple meal preparation: 8/11 correct (72%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n\nSession 4 \u2014 2026-05-25 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 3/8 correct (31%); latency 4.4s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n wait calmly when a preferred activity is denied: 6/12 correct (50%); latency 3.9s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d77\n self-advocacy statements: 4/8 correct (56%); latency 3.6s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d72\n simple meal preparation: 7/15 correct (46%); latency 3.7s; prompts FP\u00d75, PP\u00d74, G\u00d75, I\u00d71\n\nSession 5 \u2014 2026-05-27 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 10/15 correct (65%); latency 3.0s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d77\n wait calmly when a preferred activity is denied: 5/10 correct (48%); latency 3.8s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n self-advocacy statements: 7/11 correct (61%); latency 3.6s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d75\n simple meal preparation: 4/11 correct (40%); latency 4.3s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d76\n\nSession 6 \u2014 2026-05-29 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 4/15 correct (29%); latency 4.9s; prompts FP\u00d71, PP\u00d75, G\u00d72, I\u00d77\n wait calmly when a preferred activity is denied: 8/10 correct (81%); latency 2.6s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d76\n self-advocacy statements: 5/13 correct (40%); latency 4.3s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d73\n simple meal preparation: 11/15 correct (73%); latency 2.7s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d711\n\nSession 7 \u2014 2026-05-31 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 4/8 correct (54%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n wait calmly when a preferred activity is denied: 6/13 correct (46%); latency 4.2s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d74\n self-advocacy statements: 4/10 correct (41%); latency 3.9s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d76\n simple meal preparation: 4/10 correct (41%); latency 4.4s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d72\n\nSession 8 \u2014 2026-06-02 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 10/15 correct (66%); latency 3.1s; prompts FP\u00d75, PP\u00d75, G\u00d70, I\u00d75\n wait calmly when a preferred activity is denied: 7/14 correct (48%); latency 3.6s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d76\n self-advocacy statements: 7/15 correct (49%); latency 3.8s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d79\n simple meal preparation: 6/15 correct (42%); latency 4.2s; prompts FP\u00d70, PP\u00d73, G\u00d74, I\u00d78\n\nSession 9 \u2014 2026-06-04 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 7/10 correct (66%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d77\n wait calmly when a preferred activity is denied: 6/12 correct (48%); latency 4.1s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d76\n self-advocacy statements: 9/13 correct (66%); latency 2.9s; prompts FP\u00d70, PP\u00d74, G\u00d74, I\u00d75\n simple meal preparation: 4/11 correct (34%); latency 4.4s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d76\n\nSession 10 \u2014 2026-06-06 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 7/14 correct (47%); latency 3.6s; prompts FP\u00d74, PP\u00d71, G\u00d72, I\u00d77\n wait calmly when a preferred activity is denied: 7/15 correct (47%); latency 3.6s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d79\n self-advocacy statements: 10/14 correct (71%); latency 2.6s; prompts FP\u00d74, PP\u00d71, G\u00d73, I\u00d76\n simple meal preparation: 8/12 correct (70%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d79\n\nSession 11 \u2014 2026-06-08 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 3/9 correct (37%); latency 4.5s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n wait calmly when a preferred activity is denied: 6/10 correct (65%); latency 3.0s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d74\n self-advocacy statements: 4/10 correct (39%); latency 4.3s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d74\n simple meal preparation: 8/14 correct (56%); latency 3.4s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d78\n\nSession 12 \u2014 2026-06-10 \u2014 36 min \u2014 1 observer\n completing assigned tasks in order: 3/9 correct (32%); latency 4.4s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d77\n wait calmly when a preferred activity is denied: 11/15 correct (72%); latency 2.9s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d714\n self-advocacy statements: 5/10 correct (48%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d74\n simple meal preparation: 6/12 correct (52%); latency 3.9s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d74\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Playing with non-task materials\n- Looking away during SD presentation"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Variable performance**: accuracy fluctuating around 44% with no clear trend.\n- Inconsistency may indicate stimulus-control issues or motivational variability across sessions.\n\n## Pattern Classification\nvariable_performance\n\nHigh session-to-session variability with no clear trend suggests environmental or motivational inconsistency rather than a single programmatic issue.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Check for environmental variables that differ across sessions (time of day, therapist, setting).\n- Standardize session structure and reinforcement delivery across therapists.\n\n### Consequence strategies\n- Implement inter-observer agreement probes to rule out measurement inconsistency.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 48.7%.\n- Trend direction: downward (first session: 55%, last session: 32%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "e19fa23e4d579ded", "gold_labels": {"pattern_class": "variable_performance", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "variable_performance", "learner_profile": "adult", "n_sessions": 12, "n_programs": 4, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "76678"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: scheduling a medical appointment\nCurriculum Reference: AFLS Independent Living Skills\nLearner Profile: Adult Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: Task Analysis / Chaining\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: scheduling a medical appointment\n- Curriculum: AFLS Independent Living Skills\n- Learner: Adult Learner\n- Current mastery: Mastered at current level\n\nThis Task Analysis program teaches the target skill as a chain of discrete steps, each taught and reinforced until the learner can complete the full sequence independently.\n\n## Task Analysis\nChain type: Forward chaining\nTeach step 1 to mastery, then 1->2, then 1->2->3, progressively adding later steps.\n\nSteps:\n1. Identify the reason for the appointment. <- Learner-taught step (forward chaining starts here)\n2. Locate the provider's contact information.\n3. Call or use the online system.\n4. Provide name, date of birth, and insurance information.\n5. Request an available appointment time.\n6. Confirm the appointment and save it to the calendar.\n\n## Prompt Strategy Per Step\nStrategy: Least-to-Most\nAllow independent attempt; add progressively more intrusive prompts only if learner does not initiate.\nCurrent prompt level: At the mastered stage, deliver the least intrusive prompt that prevents an error; expect independence on previously-mastered steps.\n\n## Error Correction Procedure\nBack-step + re-approach: Return to the previously-mastered step; re-execute that step correctly; then re-attempt the missed step with one prompt level above the last independent level\n\n## Reinforcement\nToken economy \u2014 One token per correctly-completed step; token exchange at chain completion.\nPair the terminal reinforcer with the natural consequence of the completed task (e.g., clean hands, clean dishes, completed routine).\n\n## Mastery Criteria\nChain self-initiated from the appropriate antecedent (no verbal prompt to begin) across 3 consecutive opportunities.\n\n## Data Collection\nPer-step data: each step is scored for independence / prompt level on every trial. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe the full chain across 2 different settings and with 3 different adults. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "55bb0787e41697b0", "gold_labels": {"method": "task_analysis", "domain": "AFLS.independent_living", "skill": "scheduling a medical appointment", "program_type": "independence", "learner_profile": "adult", "mastery_state": "mastered", "chain_type": "forward"}, "provenance": {"layer": 1, "area": "task_analysis", "template_id": "task1_task_analysis_v1", "taxonomy_cells": {"skill_target": "scheduling a medical appointment", "module": "independent_living", "mastery_criterion": "mc_self_initiation", "chain_type": "forward", "prompt_strategy": "least_to_most", "reinforcement_schedule": "token_economy", "error_correction": "back_to_previous_step"}, "teacher_model": null, "seed_tag": "98892"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-4502\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Echoic + Mand + Reading + Tact + Tolerating Denied Access\nDate range: Sessions 1\u20139 across 18 days (2026-09-21 to 2026-10-09)\n\nACCELERATION PROGRAMS\n1. reads 10\u201320 sight words (Reading)\n Method: DTT\n2. single-word mands for preferred items (e.g., \"cookie\", \"iPad\") (Mand)\n Method: NET\n3. requesting a break ('break please' or AAC 'I need a break') (Mand)\n Method: NET\n4. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n5. tacts common objects (Tact)\n Method: DTT\n6. echoes 2-word phrases (Echoic)\n Method: DTT variant\n\nDECELERATION TARGETS\n1. Pica \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-21 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 5/8 correct (64%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/13 correct (62%); latency 3.5s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d79\n requesting a break ('break please' or AAC 'I need a break'): 4/8 correct (56%); latency 3.6s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d74\n wait calmly when access to preferred item is denied: 6/11 correct (56%); latency 3.6s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d710\n tacts common objects: 7/13 correct (53%); latency 3.3s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d79\n echoes 2-word phrases: 7/11 correct (64%); latency 3.0s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d73\n Pica: attempts 2 (1 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 2 \u2014 2026-09-23 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 8/13 correct (63%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 7/10 correct (66%); latency 3.3s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d75\n requesting a break ('break please' or AAC 'I need a break'): 8/15 correct (54%); latency 3.3s; prompts FP\u00d75, PP\u00d73, G\u00d74, I\u00d73\n wait calmly when access to preferred item is denied: 6/13 correct (50%); latency 3.9s; prompts FP\u00d74, PP\u00d70, G\u00d71, I\u00d78\n tacts common objects: 8/15 correct (56%); latency 3.5s; prompts FP\u00d70, PP\u00d72, G\u00d75, I\u00d78\n echoes 2-word phrases: 9/14 correct (66%); latency 2.8s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d77\n Pica: attempts 2 (0 unsuccessful \u2014 staff retrieved item before ingestion; 2 successful \u2014 item ingested)\n\nSession 3 \u2014 2026-09-25 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 6/10 correct (62%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d76\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/15 correct (70%); latency 2.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d711\n requesting a break ('break please' or AAC 'I need a break'): 7/13 correct (57%); latency 3.3s; prompts FP\u00d71, PP\u00d74, G\u00d72, I\u00d76\n wait calmly when access to preferred item is denied: 4/8 correct (52%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n tacts common objects: 4/8 correct (55%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d76\n echoes 2-word phrases: 8/12 correct (68%); latency 3.1s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d73\n Pica: attempts 5 (4 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 4 \u2014 2026-09-27 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 8/11 correct (70%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/15 correct (65%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d710\n requesting a break ('break please' or AAC 'I need a break'): 8/12 correct (65%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d76\n wait calmly when access to preferred item is denied: 7/12 correct (58%); latency 3.2s; prompts FP\u00d73, PP\u00d72, G\u00d74, I\u00d73\n tacts common objects: 5/8 correct (57%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n echoes 2-word phrases: 10/14 correct (73%); latency 3.0s; prompts FP\u00d71, PP\u00d70, G\u00d72, I\u00d711\n Pica: attempts 5 (4 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 5 \u2014 2026-09-29 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 8/11 correct (73%); latency 2.8s; prompts FP\u00d71, PP\u00d73, G\u00d73, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 11/15 correct (76%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d79\n requesting a break ('break please' or AAC 'I need a break'): 5/8 correct (65%); latency 3.4s; prompts FP\u00d70, PP\u00d72, G\u00d71, I\u00d75\n wait calmly when access to preferred item is denied: 4/8 correct (52%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d70, I\u00d76\n tacts common objects: 5/9 correct (53%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d76\n echoes 2-word phrases: 10/15 correct (67%); latency 3.1s; prompts FP\u00d72, PP\u00d75, G\u00d73, I\u00d75\n Pica: attempts 1 (1 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 6 \u2014 2026-10-01 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 9/12 correct (72%); latency 2.5s; prompts FP\u00d72, PP\u00d74, G\u00d71, I\u00d75\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 9/11 correct (78%); latency 2.7s; prompts FP\u00d70, PP\u00d70, G\u00d73, I\u00d78\n requesting a break ('break please' or AAC 'I need a break'): 10/14 correct (69%); latency 2.8s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d76\n wait calmly when access to preferred item is denied: 8/14 correct (54%); latency 3.4s; prompts FP\u00d74, PP\u00d72, G\u00d72, I\u00d76\n tacts common objects: 8/14 correct (57%); latency 3.5s; prompts FP\u00d72, PP\u00d72, G\u00d73, I\u00d77\n echoes 2-word phrases: 11/15 correct (74%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d75, I\u00d77\n Pica: attempts 2 (2 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 7 \u2014 2026-10-03 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 10/14 correct (75%); latency 2.8s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d712\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 8/10 correct (78%); latency 2.5s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d79\n requesting a break ('break please' or AAC 'I need a break'): 9/13 correct (71%); latency 2.8s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d78\n wait calmly when access to preferred item is denied: 7/14 correct (53%); latency 3.9s; prompts FP\u00d71, PP\u00d72, G\u00d71, I\u00d710\n tacts common objects: 7/13 correct (50%); latency 3.9s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d79\n echoes 2-word phrases: 12/15 correct (77%); latency 2.4s; prompts FP\u00d75, PP\u00d73, G\u00d75, I\u00d72\n Pica: attempts 2 (2 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nSession 8 \u2014 2026-10-05 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 7/9 correct (78%); latency 2.4s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 12/14 correct (84%); latency 1.9s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d79\n requesting a break ('break please' or AAC 'I need a break'): 7/10 correct (70%); latency 2.8s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d710\n wait calmly when access to preferred item is denied: 6/12 correct (53%); latency 3.8s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d78\n tacts common objects: 4/8 correct (53%); latency 3.9s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d77\n echoes 2-word phrases: 10/14 correct (74%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d711\n Pica: attempts 2 (1 unsuccessful \u2014 staff retrieved item before ingestion; 1 successful \u2014 item ingested)\n\nSession 9 \u2014 2026-10-07 \u2014 51 min \u2014 1 observer\n reads 10\u201320 sight words: 8/10 correct (82%); latency 2.6s; prompts FP\u00d71, PP\u00d72, G\u00d73, I\u00d74\n single-word mands for preferred items (e.g., \"cookie\", \"iPad\"): 10/12 correct (81%); latency 2.5s; prompts FP\u00d74, PP\u00d73, G\u00d71, I\u00d74\n requesting a break ('break please' or AAC 'I need a break'): 12/15 correct (78%); latency 2.4s; prompts FP\u00d74, PP\u00d75, G\u00d74, I\u00d72\n wait calmly when access to preferred item is denied: 7/12 correct (57%); latency 3.5s; prompts FP\u00d74, PP\u00d70, G\u00d70, I\u00d78\n tacts common objects: 5/9 correct (58%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n echoes 2-word phrases: 7/9 correct (74%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d75\n Pica: attempts 1 (1 unsuccessful \u2014 staff retrieved item before ingestion; 0 successful \u2014 item ingested)\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Attempts at property destruction (throwing materials, swiping items off the surface)\n- Pushing materials away from the work area\n- Self-injurious behavior onset during task difficulty (self-biting, hair-pulling, head-hitting)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nPica: attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n### Crisis plan\n- If problem-behavior intensity or topography exceeds the learner's baseline safety threshold (SIB causing tissue damage, aggression causing injury, imminent elopement into hazard): pause the extinction procedure and implement the facility's tiered crisis-prevention protocol (e.g., Safety-Care, CPI, or equivalent).\n- De-escalation and environmental safety first; physical intervention is last resort and only by staff currently certified in the facility's framework. Least-restrictive option appropriate to the risk level applies at every step. Physical intervention is used only when specifically authorized for this learner in the BIP \u2014 contraindications (medical, developmental, trauma history) may restrict the procedures available, in which case the plan is de-escalation + environmental safety + supervisor contact only.\n- Contact the supervising BCBA immediately; do not resume the extinction procedure without BCBA review. Document duration, intensity, antecedent, staff response, and post-incident state.\n\n## Escalation Level\n3 \u2014 Supervisor review\n\nCombination of performance decline and/or behavior data warrants supervising BCBA review within 24\u201348 hours.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 9 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 9 sessions: 70.9%.\n- Trend direction: upward (first session: 64%, last session: 82%).\n- Pica: mean 2.4/session (early-window mean 3.0 -> late-window mean 1.7).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "b248cd78c0ea1c32", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Pica": "attention"}, "escalation_level": 3, "confidence": "moderate", "crisis_plan_required": true}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "early", "n_sessions": 9, "n_programs": 6, "n_behaviors": 1, "behavior_ids": ["pica"], "behavior_functions": ["attention"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "10409"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Review this session log and produce a structured clinical interpretation.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5619\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Home Skills + Self-Care + Tolerating Denied Access + Writing\nDate range: Sessions 1\u201312 across 24 days (2026-03-08 to 2026-04-01)\n\nACCELERATION PROGRAMS\n1. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n2. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n3. brushing teeth independently (Self-Care)\n Method: Task Analysis\n4. making the bed (Home Skills)\n Method: Task Analysis\n5. copies simple words from model (Writing)\n Method: DTT\n\nDECELERATION TARGETS\n1. Property destruction \u2014 function hypothesized: attention\n\nSESSION DATA\n\nSession 1 \u2014 2026-03-08 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 13/15 correct (84%); latency 2.1s; prompts FP\u00d75, PP\u00d70, G\u00d71, I\u00d79\n meal cleanup after eating: 7/8 correct (90%); latency 2.1s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n brushing teeth independently: 9/12 correct (77%); latency 2.3s; prompts FP\u00d74, PP\u00d74, G\u00d72, I\u00d72\n making the bed: 10/11 correct (91%); latency 1.6s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d77\n copies simple words from model: 12/15 correct (78%); latency 2.2s; prompts FP\u00d71, PP\u00d72, G\u00d74, I\u00d78\n Property destruction: freq 2\n\nSession 2 \u2014 2026-03-10 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 13/14 correct (90%); latency 2.0s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d79\n meal cleanup after eating: 7/8 correct (85%); latency 2.0s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d75\n brushing teeth independently: 12/15 correct (80%); latency 2.4s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d78\n making the bed: 9/10 correct (93%); latency 1.6s; prompts FP\u00d70, PP\u00d73, G\u00d72, I\u00d75\n copies simple words from model: 12/15 correct (82%); latency 2.0s; prompts FP\u00d75, PP\u00d70, G\u00d74, I\u00d76\n Property destruction: freq 2\n\nSession 3 \u2014 2026-03-12 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 11/13 correct (83%); latency 2.4s; prompts FP\u00d72, PP\u00d70, G\u00d74, I\u00d77\n meal cleanup after eating: 10/12 correct (83%); latency 2.2s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d711\n brushing teeth independently: 7/9 correct (81%); latency 2.1s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d73\n making the bed: 8/9 correct (90%); latency 1.8s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d72\n copies simple words from model: 10/13 correct (76%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d710\n Property destruction: freq 2\n\nSession 4 \u2014 2026-03-14 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 9/10 correct (89%); latency 2.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n meal cleanup after eating: 11/12 correct (90%); latency 1.7s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d77\n brushing teeth independently: 11/15 correct (75%); latency 2.9s; prompts FP\u00d73, PP\u00d72, G\u00d72, I\u00d78\n making the bed: 12/13 correct (90%); latency 2.1s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d77\n copies simple words from model: 9/12 correct (79%); latency 2.4s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d75\n Property destruction: freq 2\n\nSession 5 \u2014 2026-03-16 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 12/14 correct (88%); latency 2.3s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d79\n meal cleanup after eating: 8/9 correct (87%); latency 2.0s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d74\n brushing teeth independently: 6/8 correct (73%); latency 2.5s; prompts FP\u00d70, PP\u00d70, G\u00d70, I\u00d78\n making the bed: 8/9 correct (90%); latency 1.7s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d73\n copies simple words from model: 9/12 correct (75%); latency 2.5s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d76\n Property destruction: freq 3\n\nSession 6 \u2014 2026-03-18 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 10/11 correct (89%); latency 1.9s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n meal cleanup after eating: 10/11 correct (89%); latency 1.8s; prompts FP\u00d73, PP\u00d71, G\u00d70, I\u00d77\n brushing teeth independently: 6/8 correct (70%); latency 3.0s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n making the bed: 8/9 correct (90%); latency 1.8s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d73\n copies simple words from model: 8/12 correct (70%); latency 3.1s; prompts FP\u00d72, PP\u00d73, G\u00d74, I\u00d73\n Property destruction: freq 3\n\nSession 7 \u2014 2026-03-20 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 12/14 correct (88%); latency 2.2s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d78\n meal cleanup after eating: 12/14 correct (87%); latency 1.9s; prompts FP\u00d74, PP\u00d74, G\u00d70, I\u00d76\n brushing teeth independently: 8/11 correct (72%); latency 3.0s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d76\n making the bed: 10/11 correct (89%); latency 1.8s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d710\n copies simple words from model: 7/10 correct (70%); latency 3.1s; prompts FP\u00d71, PP\u00d70, G\u00d70, I\u00d79\n Property destruction: freq 2\n\nSession 8 \u2014 2026-03-22 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 12/14 correct (85%); latency 2.4s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d77\n meal cleanup after eating: 10/11 correct (89%); latency 2.0s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n brushing teeth independently: 8/12 correct (66%); latency 3.1s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d79\n making the bed: 9/11 correct (86%); latency 2.2s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d76\n copies simple words from model: 6/9 correct (66%); latency 3.1s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n Property destruction: freq 2\n\nSession 9 \u2014 2026-03-24 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 10/11 correct (87%); latency 1.9s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d76\n meal cleanup after eating: 8/9 correct (88%); latency 1.8s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n brushing teeth independently: 9/14 correct (67%); latency 2.7s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d72\n making the bed: 13/15 correct (85%); latency 2.5s; prompts FP\u00d70, PP\u00d72, G\u00d74, I\u00d79\n copies simple words from model: 10/14 correct (71%); latency 2.9s; prompts FP\u00d70, PP\u00d70, G\u00d74, I\u00d710\n Property destruction: freq 3\n\nSession 10 \u2014 2026-03-26 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 9/10 correct (88%); latency 2.3s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d75\n meal cleanup after eating: 10/11 correct (92%); latency 1.7s; prompts FP\u00d73, PP\u00d71, G\u00d73, I\u00d74\n brushing teeth independently: 9/14 correct (65%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d71, I\u00d76\n making the bed: 8/10 correct (82%); latency 2.3s; prompts FP\u00d73, PP\u00d73, G\u00d72, I\u00d72\n copies simple words from model: 8/12 correct (63%); latency 3.1s; prompts FP\u00d73, PP\u00d74, G\u00d73, I\u00d72\n Property destruction: freq 3\n\nSession 11 \u2014 2026-03-28 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 10/11 correct (90%); latency 2.2s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d78\n meal cleanup after eating: 10/11 correct (91%); latency 1.7s; prompts FP\u00d73, PP\u00d73, G\u00d70, I\u00d75\n brushing teeth independently: 9/14 correct (67%); latency 2.7s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n making the bed: 9/11 correct (77%); latency 2.2s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n copies simple words from model: 6/9 correct (65%); latency 3.1s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d78\n Property destruction: freq 3\n\nSession 12 \u2014 2026-03-30 \u2014 60 min \u2014 1 observer\n wait calmly when access to preferred item is denied: 8/9 correct (87%); latency 1.9s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d74\n meal cleanup after eating: 8/9 correct (87%); latency 1.9s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d73\n brushing teeth independently: 6/10 correct (60%); latency 3.6s; prompts FP\u00d73, PP\u00d70, G\u00d71, I\u00d76\n making the bed: 8/11 correct (76%); latency 2.4s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d78\n copies simple words from model: 6/10 correct (60%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d78\n Property destruction: freq 3\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Playing with non-task materials\n- Looking away during SD presentation\n- Delayed responding (>5 seconds consistently)\n- Leaving seat without permission\n\nPlease include: (1) clinical concerns, (2) pattern classification, (3) function hypothesis for any target behaviors, (4) recommendations structured as antecedent / replacement / consequence / crisis, (5) escalation level and confidence, (6) data-supported rationale."}, {"role": "assistant", "content": "## Clinical Concerns\n- **Prompt dependency**: high accuracy maintained (84%\u201387%) but primarily at prompted levels.\n- Independent responding remains low despite extended training.\n\n## Pattern Classification\nprompt_dependency\n\nAccuracy stays high only at prompted levels; independent responding remains low despite extended training.\n\n## Behavior Function Hypothesis\nProperty destruction: attention\n Evidence: behavior occurs during low-attention periods and results in social attention contingently.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Switch to a time-delay procedure (0s -> 2s -> 4s -> 6s) to encourage independent responding.\n- Avoid inadvertent prompt delivery (therapist gaze, body positioning) that may function as a prompt.\n\n### Consequence strategies\n- Ensure differential reinforcement \u2014 independent responses receive higher-quality reinforcement than prompted responses.\n- Consider stimulus fading instead of response prompting for this skill.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 12 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 12 sessions: 87.2%.\n- Trend direction: upward (first session: 84%, last session: 87%).\n- Property destruction: mean 2.5/session (early-window mean 2.0 -> late-window mean 3.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "44f157d318bb92cb", "gold_labels": {"pattern_class": "prompt_dependency", "behavior_functions": {"Property destruction": "attention"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "prompt_dependency", "learner_profile": "adolescent", "n_sessions": 12, "n_programs": 5, "n_behaviors": 1, "behavior_ids": ["property_destruction"], "behavior_functions": ["attention"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "49562"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: selects by single function from array of 3\nCurriculum Reference: LRFFC L1\nLearner Profile: Early Learner\nCurrent Mastery: Developing\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: selects by single function from array of 3\n- Curriculum: LRFFC L1\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: cup, block, shoe\nDistractor stimuli: key, napkin\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nModel correct response -> lead (do together) -> test (independent) -> distractor -> retest.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n90% accuracy across 3 consecutive sessions.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "3bd890922b748d88", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.lrffc", "level": "L1", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "selects by single function from array of 3", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "crf", "error_correction": "four_step", "mastery_criterion": "mc_90_3sessions"}, "teacher_model": null, "seed_tag": "26013"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Here is a multi-session behavioral log for a learner. Analyze it and provide your clinical interpretation using the structured format.\n\nLEARNER PROFILE\nSynthetic ID: SYN-9424\nProfile: Adult Learner (18+ years)\nCurricula: Community + Home Skills + Independent Living + Mand + Self-Care\nDate range: Sessions 1\u20138 across 16 days (2026-02-04 to 2026-02-20)\n\nACCELERATION PROGRAMS\n1. using public transportation (Community)\n Method: Task Analysis\n2. scheduling medical appointments (Independent Living)\n Method: Task Analysis\n3. doing laundry (Home Skills)\n Method: Task Analysis\n4. requesting a break during extended tasks (Mand)\n Method: NET\n5. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n\nSESSION DATA\n\nSession 1 \u2014 2026-02-04 \u2014 46 min \u2014 1 observer\n using public transportation: 5/8 correct (68%); latency 3.2s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n scheduling medical appointments: 7/12 correct (61%); latency 3.1s; prompts FP\u00d74, PP\u00d72, G\u00d74, I\u00d72\n doing laundry: 8/12 correct (64%); latency 2.9s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d78\n requesting a break during extended tasks: 12/15 correct (80%); latency 2.6s; prompts FP\u00d75, PP\u00d73, G\u00d70, I\u00d77\n dressing (pants, shirt): 8/11 correct (69%); latency 3.1s; prompts FP\u00d72, PP\u00d70, G\u00d71, I\u00d78\n\nSession 2 \u2014 2026-02-06 \u2014 46 min \u2014 1 observer\n using public transportation: 9/13 correct (66%); latency 3.2s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d74\n scheduling medical appointments: 8/11 correct (70%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d70, I\u00d78\n doing laundry: 9/14 correct (64%); latency 3.2s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d713\n requesting a break during extended tasks: 8/11 correct (71%); latency 2.9s; prompts FP\u00d72, PP\u00d73, G\u00d72, I\u00d74\n dressing (pants, shirt): 8/11 correct (71%); latency 2.8s; prompts FP\u00d71, PP\u00d73, G\u00d70, I\u00d77\n\nSession 3 \u2014 2026-02-08 \u2014 46 min \u2014 1 observer\n using public transportation: 8/12 correct (68%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d710\n scheduling medical appointments: 9/14 correct (66%); latency 2.9s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d75\n doing laundry: 8/12 correct (70%); latency 3.1s; prompts FP\u00d74, PP\u00d71, G\u00d70, I\u00d77\n requesting a break during extended tasks: 8/10 correct (79%); latency 2.5s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d77\n dressing (pants, shirt): 6/9 correct (71%); latency 2.5s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d71\n\nSession 4 \u2014 2026-02-10 \u2014 46 min \u2014 1 observer\n using public transportation: 5/9 correct (53%); latency 3.9s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d75\n scheduling medical appointments: 4/12 correct (32%); latency 4.7s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d78\n doing laundry: 4/9 correct (48%); latency 4.0s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d77\n requesting a break during extended tasks: 6/13 correct (50%); latency 3.5s; prompts FP\u00d74, PP\u00d74, G\u00d71, I\u00d74\n dressing (pants, shirt): 6/15 correct (43%); latency 4.3s; prompts FP\u00d72, PP\u00d71, G\u00d72, I\u00d710\n\nSession 5 \u2014 2026-02-12 \u2014 46 min \u2014 1 observer\n using public transportation: 7/11 correct (62%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d75\n scheduling medical appointments: 4/10 correct (41%); latency 4.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d77\n doing laundry: 7/13 correct (54%); latency 3.6s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d77\n requesting a break during extended tasks: 7/11 correct (59%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d72, I\u00d77\n dressing (pants, shirt): 7/15 correct (47%); latency 4.1s; prompts FP\u00d71, PP\u00d73, G\u00d74, I\u00d77\n\nSession 6 \u2014 2026-02-14 \u2014 46 min \u2014 1 observer\n using public transportation: 9/13 correct (69%); latency 2.6s; prompts FP\u00d70, PP\u00d74, G\u00d72, I\u00d77\n scheduling medical appointments: 3/8 correct (44%); latency 4.0s; prompts FP\u00d70, PP\u00d72, G\u00d70, I\u00d76\n doing laundry: 5/9 correct (57%); latency 3.3s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d76\n requesting a break during extended tasks: 9/13 correct (68%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d72, I\u00d711\n dressing (pants, shirt): 6/11 correct (51%); latency 4.0s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d77\n\nSession 7 \u2014 2026-02-16 \u2014 46 min \u2014 1 observer\n using public transportation: 10/15 correct (69%); latency 3.1s; prompts FP\u00d72, PP\u00d74, G\u00d70, I\u00d79\n scheduling medical appointments: 8/15 correct (51%); latency 3.9s; prompts FP\u00d71, PP\u00d74, G\u00d73, I\u00d77\n doing laundry: 5/9 correct (60%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d75\n requesting a break during extended tasks: 8/11 correct (75%); latency 2.6s; prompts FP\u00d73, PP\u00d72, G\u00d73, I\u00d73\n dressing (pants, shirt): 6/10 correct (63%); latency 3.0s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d75\n\nSession 8 \u2014 2026-02-18 \u2014 46 min \u2014 1 observer\n using public transportation: 8/12 correct (69%); latency 2.9s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d73\n scheduling medical appointments: 5/10 correct (55%); latency 3.4s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d74\n doing laundry: 6/9 correct (64%); latency 3.0s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d76\n requesting a break during extended tasks: 11/15 correct (75%); latency 2.5s; prompts FP\u00d72, PP\u00d73, G\u00d75, I\u00d75\n dressing (pants, shirt): 6/9 correct (67%); latency 3.2s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d75\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Echolalic responding (repeating SD rather than answering)\n- Delayed responding (>5 seconds consistently)"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Setting event pattern**: observable change in performance correlated with an external event (illness, sleep, schedule).\n- Correlation between setting event and performance should be tracked explicitly.\n\n## Pattern Classification\nsetting_event_trigger\n\nA discontinuous performance change at a specific session correlates with an external setting event.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Identify and document the setting event (sleep, illness, schedule change, medication).\n- Modify programming demand on days when setting event is present.\n- Coordinate with caregivers / medical team on setting-event factors outside the program.\n\n### Consequence strategies\n- Track setting events alongside performance data to quantify their effect.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 8 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 8 sessions: 65.3%.\n- Trend direction: upward (first session: 68%, last session: 69%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "d0b834159ead6a38", "gold_labels": {"pattern_class": "setting_event_trigger", "behavior_functions": {}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "setting_event_trigger", "learner_profile": "adult", "n_sessions": 8, "n_programs": 5, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "65927"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: writes own name from model\nCurriculum: Writing L1\nLearner Level: Early Learner\nBaseline: Generalization phase\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: writes own name from model\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Graduated Guidance\nSequence: hand over hand full -> hand over hand light -> shadow -> independent\nCurrent prompt level: At the generalization stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: blanket, key, glue\nDistractor stimuli: sock, ball\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\n\"No, watch me\" -> model -> re-present SD -> differential reinforcement for correct response.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "33649723e10238f2", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "writes own name from model", "prompt_hierarchy": "graduated_guidance", "reinforcement_schedule": "vr3", "error_correction": "simple_correction", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "61305"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-8199\nProfile: Early Learner (dev age 0\u201348 months)\nCurricula: Echoic + Intraverbal + Listener Responding + Tolerating Denied Access\nDate range: Sessions 1\u20137 across 14 days (2026-09-17 to 2026-10-01)\n\nACCELERATION PROGRAMS\n1. follows 1-step motor instructions (Listener Responding)\n Method: DTT\n2. answers WH-questions about familiar topics (Intraverbal)\n Method: NET\n3. wait calmly when access to preferred item is denied (Tolerating Denied Access)\n Method: FCT\n4. echoes 2-word phrases (Echoic)\n Method: DTT variant\n\nSESSION DATA\n\nSession 1 \u2014 2026-09-17 \u2014 43 min \u2014 1 observer\n follows 1-step motor instructions: 3/9 correct (36%); latency 4.2s; prompts FP\u00d72, PP\u00d70, G\u00d73, I\u00d74\n answers WH-questions about familiar topics: 2/8 correct (30%); latency 4.6s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d75\n wait calmly when access to preferred item is denied: 2/8 correct (23%); latency 4.7s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d74\n echoes 2-word phrases: 3/13 correct (22%); latency 5.3s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d78\n\nSession 2 \u2014 2026-09-19 \u2014 43 min \u2014 1 observer\n follows 1-step motor instructions: 5/11 correct (48%); latency 3.8s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d77\n answers WH-questions about familiar topics: 6/14 correct (42%); latency 4.3s; prompts FP\u00d71, PP\u00d70, G\u00d74, I\u00d79\n wait calmly when access to preferred item is denied: 5/14 correct (38%); latency 4.2s; prompts FP\u00d71, PP\u00d71, G\u00d73, I\u00d79\n echoes 2-word phrases: 3/11 correct (31%); latency 4.5s; prompts FP\u00d73, PP\u00d72, G\u00d70, I\u00d76\n\nSession 3 \u2014 2026-09-21 \u2014 43 min \u2014 1 observer\n follows 1-step motor instructions: 9/15 correct (59%); latency 3.2s; prompts FP\u00d73, PP\u00d73, G\u00d71, I\u00d78\n answers WH-questions about familiar topics: 6/12 correct (49%); latency 3.7s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d711\n wait calmly when access to preferred item is denied: 6/15 correct (42%); latency 4.3s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d710\n echoes 2-word phrases: 3/9 correct (39%); latency 4.2s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d73\n\nSession 4 \u2014 2026-09-23 \u2014 43 min \u2014 1 observer\n follows 1-step motor instructions: 7/9 correct (73%); latency 2.6s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d74\n answers WH-questions about familiar topics: 5/9 correct (60%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d72, I\u00d75\n wait calmly when access to preferred item is denied: 7/12 correct (56%); latency 3.2s; prompts FP\u00d70, PP\u00d72, G\u00d73, I\u00d77\n echoes 2-word phrases: 7/14 correct (46%); latency 3.8s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d711\n\nSession 5 \u2014 2026-09-25 \u2014 43 min \u2014 1 observer\n follows 1-step motor instructions: 11/13 correct (82%); latency 2.3s; prompts FP\u00d73, PP\u00d72, G\u00d71, I\u00d77\n answers WH-questions about familiar topics: 6/9 correct (72%); latency 3.0s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d76\n wait calmly when access to preferred item is denied: 9/14 correct (66%); latency 2.8s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d78\n echoes 2-word phrases: 4/8 correct (55%); latency 3.7s; prompts FP\u00d72, PP\u00d72, G\u00d71, I\u00d73\n\nSession 6 \u2014 2026-09-27 \u2014 43 min \u2014 1 observer\n follows 1-step motor instructions: 11/12 correct (93%); latency 1.7s; prompts FP\u00d71, PP\u00d74, G\u00d74, I\u00d73\n answers WH-questions about familiar topics: 12/14 correct (83%); latency 2.6s; prompts FP\u00d71, PP\u00d71, G\u00d70, I\u00d712\n wait calmly when access to preferred item is denied: 6/8 correct (79%); latency 2.3s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n echoes 2-word phrases: 9/15 correct (63%); latency 3.0s; prompts FP\u00d70, PP\u00d73, G\u00d71, I\u00d711\n\nSession 7 \u2014 2026-09-29 \u2014 43 min \u2014 1 observer\n follows 1-step motor instructions: 9/9 correct (97%); latency 1.4s; prompts FP\u00d72, PP\u00d72, G\u00d72, I\u00d73\n answers WH-questions about familiar topics: 7/8 correct (93%); latency 1.5s; prompts FP\u00d72, PP\u00d72, G\u00d70, I\u00d74\n wait calmly when access to preferred item is denied: 7/8 correct (84%); latency 2.0s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n echoes 2-word phrases: 7/10 correct (72%); latency 3.0s; prompts FP\u00d70, PP\u00d70, G\u00d71, I\u00d79\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Reaching for materials proactively\n- Quick response latency (within 2\u20133 seconds)\n- Requesting more trials verbally\n- Smiling during reinforcement delivery"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Rapid acquisition**: accelerated mastery from 36% to 97% across 7 sessions.\n- Acquisition has exceeded expected timeline.\n\n## Pattern Classification\nrapid_acquisition\n\nAccuracy ascended steeply beyond expected timeline for this learner's profile.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Advance to next skill in the sequence immediately.\n- Begin generalization probes across people, settings, and materials.\n\n### Consequence strategies\n- Move to maintenance schedule (probe monthly) and redirect session time to acquisition targets.\n\n## Escalation Level\n1 \u2014 Continue monitoring\n\nCurrent programming is effective; no change needed.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 69.9%.\n- Trend direction: upward (first session: 36%, last session: 97%).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "db498b635738696c", "gold_labels": {"pattern_class": "rapid_acquisition", "behavior_functions": {}, "escalation_level": 1, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "rapid_acquisition", "learner_profile": "early", "n_sessions": 7, "n_programs": 4, "n_behaviors": 0, "behavior_ids": [], "behavior_functions": [], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "23006"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: copies basic shapes from model\nCurriculum Reference: Writing L1\nLearner Profile: Early Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: copies basic shapes from model\n- Curriculum: Writing L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Write the target.\"\nVariations: \"Trace this\"; \"Copy this\"; \"Write {word}\"\nPresentation: Provide pencil and paper; deliver a clear verbal instruction naming the target letter or word.\n\n## Prompt Hierarchy\nStrategy: Least-to-Most\nSequence: independent -> gestural -> positional -> partial physical -> full physical\nCurrent prompt level: At the approaching mastery stage, deliver gestural or positional prompts; fade toward independence.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: triangle, heart, square\nDistractor stimuli: star, rectangle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nRe-present SD -> provide effective-level prompt -> reinforce prompted response -> distractor trial -> re-present SD independently.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "fc4b2855638cbd8f", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.writing", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "copies basic shapes from model", "prompt_hierarchy": "least_to_most", "reinforcement_schedule": "crf", "error_correction": "transfer_trial", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "93978"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: identifies basic shapes in math context\nCurriculum Reference: Math L1\nLearner Profile: Early Learner\nCurrent Mastery: Mastered at current level\nTeaching Method: DTT\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: identifies basic shapes in math context\n- Curriculum: Math L1\n- Learner: Early Learner\n- Current mastery: Mastered at current level\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What number is this?\"\nVariations: \"Which number?\"; \"Tell me the number\"\nPresentation: Present the numeral card.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the mastered stage, use minimal prompts (positional or verbal hint) only when needed; expect independent responding.\n\n## Stimulus Array\nArray size: field of 3 (target + 2 distractors)\nTarget stimuli: heart, diamond, square\nDistractor stimuli: circle, rectangle\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nVR-3 (variable ratio 3) \u2014 Average of every 3rd correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\n80% accuracy with 2 different therapists and 2 different settings.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 3 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "2f1b8725440a7f2a", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.math", "level": "L1", "learner_profile": "early", "mastery_state": "mastered"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "identifies basic shapes in math context", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "vr3", "error_correction": "backstep", "mastery_criterion": "mc_80_generalization"}, "teacher_model": null, "seed_tag": "60118"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Discrete Trial Training program for the following.\n\nSkill: reads simple 2\u20133 word phrases\nCurriculum: Reading L2\nLearner Level: Early Learner\nBaseline: Developing\n\nInclude the full DTT trial structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: reads simple 2\u20133 word phrases\n- Curriculum: Reading L2\n- Learner: Early Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"What word?\"\nVariations: \"Read this word\"; \"What does it say?\"\nPresentation: Present the sight-word card and deliver the SD.\n\n## Prompt Hierarchy\nStrategy: Most-to-Least (errorless)\nSequence: full physical -> partial physical -> gestural -> positional -> independent\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 5 (target + 4 distractors)\nTarget stimuli: bottle, book, apple\nDistractor stimuli: brush, phone, toothbrush, key\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nFluency criterion: correct responses within 3-second latency at 90% accuracy.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 4 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 3 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "0cb2c347cb31bddf", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.reading", "level": "L2", "learner_profile": "early", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "reads simple 2\u20133 word phrases", "prompt_hierarchy": "most_to_least", "reinforcement_schedule": "crf", "error_correction": "backstep", "mastery_criterion": "mc_fluency"}, "teacher_model": null, "seed_tag": "97982"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "I need a DTT program for this skill.\n\nTarget: follows instructions involving temporal concepts (before, after)\nCurriculum: Listener Responding L3\nLearner: Adolescent Learner\nMastery Status: Developing\n\nPlease include the SD, prompt hierarchy, stimulus array, error correction procedure, reinforcement schedule, and mastery criteria."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: follows instructions involving temporal concepts (before, after)\n- Curriculum: Listener Responding L3\n- Learner: Adolescent Learner\n- Current mastery: Developing\n\nThis DTT program establishes stimulus control over the target skill through structured discrete trials with a defined prompt hierarchy, stimulus array, and systematic error-correction procedure.\n\n## Discriminative Stimulus (SD)\nPrimary SD: \"Touch [target item]\"\nVariations: \"Point to [target item]\"; \"Give me [target item]\"; \"Show me [target item]\"\nPresentation: Present an array of items on the table and deliver a clear verbal SD.\n\n## Prompt Hierarchy\nStrategy: Stimulus Shaping\nSequence: modified stimulus -> intermediate shape -> target stimulus\nCurrent prompt level: At the developing stage, begin at higher prompt levels (full-physical or partial-physical) with systematic fading.\n\n## Stimulus Array\nArray size: field of 6 (target + 5 distractors, mixed categories)\nTarget stimuli: phone, backpack, toothbrush\nDistractor stimuli: bottle, book, towel, key, napkin\nRotation: Randomize position of target across trials to prevent position bias.\n\n## Error Correction Procedure\nReturn to previous prompt level that produced success -> successful response -> re-attempt at target prompt level.\n\n## Reinforcement Schedule\nCRF (continuous reinforcement) \u2014 Every correct response reinforced. Provide differential reinforcement: higher-quality reinforcement for independent correct responses than for prompted correct responses.\n\n## Mastery Criteria\nDemonstrated use in natural environment across 3 independent instances.\n\n## Data Collection\nTrial-by-trial data recording prompt level and response accuracy. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe with novel stimuli, across 2 additional therapists, and in at least 2 natural contexts. Maintenance probes weekly for 4 weeks, then monthly."}], "meta": {"task_type": "teaching_program", "example_id": "4fabd8df5b3a4f19", "gold_labels": {"method": "dtt", "domain": "VB-MAPP.listener_responding", "level": "L3", "learner_profile": "adolescent", "mastery_state": "developing"}, "provenance": {"layer": 1, "area": "dtt", "template_id": "task1_dtt_v1", "taxonomy_cells": {"skill_target": "follows instructions involving temporal concepts (before, after)", "prompt_hierarchy": "stimulus_shaping", "reinforcement_schedule": "crf", "error_correction": "backstep", "mastery_criterion": "mc_natural_env"}, "teacher_model": null, "seed_tag": "85854"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You\nanalyze multi-session behavioral session logs for individuals with autism and\nproduce structured clinical interpretations that identify patterns, hypothesize\nbehavior functions when applicable, and recommend programming adjustments\nstructured along BIP lines (antecedent strategies, replacement behaviors,\nconsequence strategies, crisis plan). Your interpretation also includes an\nescalation level and a confidence expression. Every recommendation is grounded\nin the data provided. Follow BACB ethical guidelines and reference no real\nclient data."}, {"role": "user", "content": "Interpret the following behavioral session log. Provide clinical concerns, pattern classification, behavior function hypothesis (if applicable), programming recommendations (antecedent / replacement / consequence / crisis), escalation level, confidence, and data-supported rationale.\n\nLEARNER PROFILE\nSynthetic ID: SYN-5719\nProfile: Adolescent Learner (13\u201317 years)\nCurricula: Community + Home Skills + Mand + Self-Care + Writing\nDate range: Sessions 1\u20137 across 14 days (2026-01-20 to 2026-02-03)\n\nACCELERATION PROGRAMS\n1. washing hands independently (Self-Care)\n Method: Task Analysis\n2. meal cleanup after eating (Home Skills)\n Method: Task Analysis\n3. copies simple words from model (Writing)\n Method: DTT\n4. dressing (pants, shirt) (Self-Care)\n Method: Task Analysis\n5. identifying community safety signs (Community)\n Method: DTT\n6. requesting a break during non-preferred activities (Mand)\n Method: NET\n\nDECELERATION TARGETS\n1. Tantrum \u2014 function hypothesized: escape\n\nSESSION DATA\n\nSession 1 \u2014 2026-01-20 \u2014 37 min \u2014 1 observer\n washing hands independently: 6/9 correct (68%); latency 2.8s; prompts FP\u00d70, PP\u00d71, G\u00d71, I\u00d77\n meal cleanup after eating: 9/15 correct (57%); latency 3.7s; prompts FP\u00d75, PP\u00d71, G\u00d73, I\u00d76\n copies simple words from model: 6/11 correct (51%); latency 3.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d79\n dressing (pants, shirt): 6/10 correct (59%); latency 3.4s; prompts FP\u00d70, PP\u00d73, G\u00d70, I\u00d77\n identifying community safety signs: 7/10 correct (66%); latency 2.8s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n requesting a break during non-preferred activities: 9/15 correct (59%); latency 3.1s; prompts FP\u00d72, PP\u00d73, G\u00d73, I\u00d77\n Tantrum: freq 1, duration 3m total\n\nSession 2 \u2014 2026-01-22 \u2014 37 min \u2014 1 observer\n washing hands independently: 5/8 correct (65%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d70, I\u00d75\n meal cleanup after eating: 7/13 correct (54%); latency 3.3s; prompts FP\u00d71, PP\u00d74, G\u00d71, I\u00d77\n copies simple words from model: 4/8 correct (55%); latency 3.4s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n dressing (pants, shirt): 5/8 correct (56%); latency 3.5s; prompts FP\u00d72, PP\u00d71, G\u00d71, I\u00d74\n identifying community safety signs: 8/11 correct (69%); latency 2.9s; prompts FP\u00d72, PP\u00d73, G\u00d71, I\u00d75\n requesting a break during non-preferred activities: 8/15 correct (51%); latency 3.6s; prompts FP\u00d72, PP\u00d71, G\u00d75, I\u00d77\n Tantrum: freq 2, duration 10m total\n\nSession 3 \u2014 2026-01-24 \u2014 37 min \u2014 1 observer\n washing hands independently: 8/11 correct (75%); latency 2.4s; prompts FP\u00d73, PP\u00d70, G\u00d72, I\u00d76\n meal cleanup after eating: 8/14 correct (57%); latency 3.7s; prompts FP\u00d70, PP\u00d71, G\u00d72, I\u00d711\n copies simple words from model: 7/13 correct (54%); latency 3.7s; prompts FP\u00d73, PP\u00d71, G\u00d71, I\u00d78\n dressing (pants, shirt): 7/11 correct (60%); latency 3.2s; prompts FP\u00d71, PP\u00d71, G\u00d71, I\u00d78\n identifying community safety signs: 8/11 correct (68%); latency 2.9s; prompts FP\u00d73, PP\u00d70, G\u00d73, I\u00d75\n requesting a break during non-preferred activities: 7/12 correct (60%); latency 3.0s; prompts FP\u00d73, PP\u00d74, G\u00d70, I\u00d75\n Tantrum: freq 5, duration 25m total\n\nSession 4 \u2014 2026-01-26 \u2014 37 min \u2014 1 observer\n washing hands independently: 7/9 correct (73%); latency 3.0s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d78\n meal cleanup after eating: 5/9 correct (54%); latency 3.6s; prompts FP\u00d73, PP\u00d73, G\u00d73, I\u00d70\n copies simple words from model: 8/14 correct (55%); latency 3.3s; prompts FP\u00d72, PP\u00d71, G\u00d73, I\u00d78\n dressing (pants, shirt): 7/12 correct (58%); latency 3.5s; prompts FP\u00d74, PP\u00d74, G\u00d74, I\u00d70\n identifying community safety signs: 8/11 correct (73%); latency 2.8s; prompts FP\u00d72, PP\u00d73, G\u00d70, I\u00d76\n requesting a break during non-preferred activities: 6/11 correct (57%); latency 3.5s; prompts FP\u00d70, PP\u00d71, G\u00d70, I\u00d710\n Tantrum: freq 7, duration 28m total\n\nSession 5 \u2014 2026-01-28 \u2014 37 min \u2014 1 observer\n washing hands independently: 7/10 correct (74%); latency 2.6s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d75\n meal cleanup after eating: 7/12 correct (58%); latency 3.5s; prompts FP\u00d74, PP\u00d73, G\u00d73, I\u00d72\n copies simple words from model: 5/8 correct (62%); latency 3.2s; prompts FP\u00d71, PP\u00d72, G\u00d72, I\u00d73\n dressing (pants, shirt): 5/8 correct (63%); latency 3.4s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n identifying community safety signs: 6/8 correct (81%); latency 2.1s; prompts FP\u00d72, PP\u00d70, G\u00d72, I\u00d74\n requesting a break during non-preferred activities: 7/12 correct (62%); latency 3.4s; prompts FP\u00d74, PP\u00d72, G\u00d71, I\u00d75\n Tantrum: freq 3, duration 15m total\n\nSession 6 \u2014 2026-01-30 \u2014 37 min \u2014 1 observer\n washing hands independently: 6/8 correct (75%); latency 2.6s; prompts FP\u00d71, PP\u00d70, G\u00d71, I\u00d76\n meal cleanup after eating: 7/13 correct (56%); latency 3.2s; prompts FP\u00d73, PP\u00d71, G\u00d72, I\u00d77\n copies simple words from model: 5/8 correct (57%); latency 3.2s; prompts FP\u00d72, PP\u00d71, G\u00d70, I\u00d75\n dressing (pants, shirt): 6/9 correct (65%); latency 3.1s; prompts FP\u00d70, PP\u00d73, G\u00d73, I\u00d73\n identifying community safety signs: 13/15 correct (85%); latency 2.4s; prompts FP\u00d74, PP\u00d72, G\u00d75, I\u00d74\n requesting a break during non-preferred activities: 7/11 correct (62%); latency 3.5s; prompts FP\u00d71, PP\u00d70, G\u00d73, I\u00d77\n Tantrum: freq 1, duration 2m total\n\nSession 7 \u2014 2026-02-01 \u2014 37 min \u2014 1 observer\n washing hands independently: 7/9 correct (83%); latency 2.4s; prompts FP\u00d71, PP\u00d73, G\u00d71, I\u00d74\n meal cleanup after eating: 7/12 correct (57%); latency 3.6s; prompts FP\u00d74, PP\u00d73, G\u00d72, I\u00d73\n copies simple words from model: 9/13 correct (66%); latency 2.9s; prompts FP\u00d71, PP\u00d71, G\u00d74, I\u00d77\n dressing (pants, shirt): 8/12 correct (63%); latency 3.4s; prompts FP\u00d74, PP\u00d71, G\u00d71, I\u00d76\n identifying community safety signs: 11/14 correct (80%); latency 2.6s; prompts FP\u00d72, PP\u00d74, G\u00d72, I\u00d76\n requesting a break during non-preferred activities: 6/10 correct (61%); latency 3.3s; prompts FP\u00d71, PP\u00d73, G\u00d72, I\u00d74\n Tantrum: freq 3, duration 12m total\n\nBEHAVIORAL OBSERVATIONS (across sessions)\n- Increased response latency (3\u20135\u00d7 baseline)\n- Vocal refusal ('no', 'I don't want to')\n- Self-stimulatory behavior increase during demand periods"}, {"role": "assistant", "content": "## Clinical Concerns\n- **Extinction burst** observed: temporary increase in problem behavior consistent with an extinction procedure.\n- This is an expected phase of behavior change and typically indicates the intervention is working.\n\n## Pattern Classification\nextinction_burst\n\nMid-log spike in problem-behavior frequency followed by recovery is consistent with a planned extinction procedure.\n\n## Behavior Function Hypothesis\nTantrum: escape\n Evidence: behavior occurs in the context of demand presentation and terminates contingent on task removal.\n\n## Programming Recommendations\n\n### Antecedent strategies\n- Maintain current antecedent arrangements \u2014 do not add extra demand.\n\n### Replacement behavior (FCT)\n- Ensure replacement response is available and reinforced at high magnitude during the burst.\n\n### Consequence strategies\n- **Maintain current protocol** \u2014 consistency during extinction bursts is critical.\n- Ensure all team members are trained on the procedure.\n\n## Escalation Level\n2 \u2014 Adjust next session\n\nProgramming adjustments indicated at next session; no immediate safety concern.\n\n## Confidence\nmoderate\n\nPattern is supported but alternatives cannot be fully excluded: 7 sessions of data; no IOA session included.\n\n## Data-Supported Rationale\n- Mean accuracy across 7 sessions: 73.2%.\n- Trend direction: upward (first session: 68%, last session: 83%).\n- Tantrum: mean 3.1/session (early-window mean 1.5 -> late-window mean 2.0).\n- No IOA session in this log; reliability of measurements cannot be independently verified."}], "meta": {"task_type": "session_interpretation", "example_id": "a9ab83f3f24f7c8e", "gold_labels": {"pattern_class": "extinction_burst", "behavior_functions": {"Tantrum": "escape"}, "escalation_level": 2, "confidence": "moderate", "crisis_plan_required": false}, "provenance": {"layer": 1, "area": "session_interpretation", "template_id": "task2_session_interp_v1", "taxonomy_cells": {"hidden_pattern_id": "extinction_burst", "learner_profile": "adolescent", "n_sessions": 7, "n_programs": 6, "n_behaviors": 1, "behavior_ids": ["tantrum"], "behavior_functions": ["escape"], "has_abc_data": false, "has_ioa_session": false}, "teacher_model": null, "seed_tag": "76065"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: mands for a break (e.g., \"break please\", AAC \"I need a break\")\nCurriculum Reference: Mand L1\nLearner Profile: Early Learner\nCurrent Mastery: Approaching mastery\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands for a break (e.g., \"break please\", AAC \"I need a break\")\n- Curriculum: Mand L1\n- Learner: Early Learner\n- Current mastery: Approaching mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nPresent a brief non-preferred task or demand at a level the learner can tolerate but may wish to pause. Wait for a request-for-break topography; honor the request immediately on first acquisition (CRF), thin later.\nPrimary natural context: academic period.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's academic period routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the approaching mastery stage, use time delay (0 s -> 2 s -> 4 s) before delivering any model prompt; reinforce independent responses differentially.\n\n## Natural Reinforcer\nNatural reinforcer: immediate brief escape from the demand (30\u201360 seconds) to a neutral or preferred activity.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 2 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "ac03b61c7496c605", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L1", "learner_profile": "early", "mastery_state": "approaching"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands for a break (e.g., \"break please\", AAC \"I need a break\")", "mo_category": "mand_break", "mo_arrangement": "break_opportunity", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "75835"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Design a Natural Environment Teaching program for the following.\n\nSkill: spontaneously uses humor appropriately\nCurriculum: Spontaneous Vocal Behavior L3\nLearner Level: School-Age Learner\nBaseline: Near mastery\n\nInclude the full naturalistic teaching structure."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: spontaneously uses humor appropriately\n- Curriculum: Spontaneous Vocal Behavior L3\n- Learner: School-Age Learner\n- Current mastery: Near mastery\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nCreate a small environmental change (new item, familiar item in new location, surprise event) that invites a verbal comment or question.\nPrimary natural context: morning greeting.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's morning greeting routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Expectant look (pause)\nDeliver no prompt \u2014 maintain eye contact and hold the preferred item until the learner responds.\nCurrent prompt level: At the near mastery stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: adult attends to the comment with matching affect.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 5 different stimuli or peers.\n- Rotate between 3 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nIndependent use with a peer in unstructured free play across 2 consecutive sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 3 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "0ac76b29391f279e", "gold_labels": {"method": "net", "domain": "VB-MAPP.spontaneous_vocal", "level": "L3", "learner_profile": "school_age", "mastery_state": "near"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "spontaneously uses humor appropriately", "mo_category": "spontaneous_comment", "mo_arrangement": "unexpected_change", "prompt_strategy": "expectant_look", "mastery_criterion": "mc_peer_initiation"}, "teacher_model": null, "seed_tag": "36908"}, "curation": {"target_split": "test"}}} +{"messages": [{"role": "system", "content": "You are an expert ABA (Applied Behavior Analysis) clinical assistant. You help\nBoard Certified Behavior Analysts and staff design teaching programs for\nindividuals with autism. Your responses are clinically accurate, individualized\nto the learner profile, follow BACB ethical guidelines, and reference no real\nclient data. Select the appropriate teaching method (DTT, NET, Task Analysis,\nFCT, BST, PRT) based on the skill target and learner profile."}, {"role": "user", "content": "Generate a teaching program for the following target.\n\nSkill Target: mands using adjectives (big, little, more)\nCurriculum Reference: Mand L2\nLearner Profile: Early Learner\nCurrent Mastery: Generalization phase\nTeaching Method: NET (Natural Environment Teaching)\n\nProvide the full program structure appropriate to the selected method."}, {"role": "assistant", "content": "## Program Overview\n- Target skill: mands using adjectives (big, little, more)\n- Curriculum: Mand L2\n- Learner: Early Learner\n- Current mastery: Generalization phase\n\nThis NET program teaches the target skill through naturalistic embedding \u2014 capturing motivated moments within the learner's routine rather than using contrived massed trials.\n\n## Motivating Operation (MO) Arrangement\nBriefly withhold or restrict access to the target preferred item/activity for 30\u201360 seconds to establish motivation before the teaching opportunity.\nPrimary natural context: snack time.\n\n## Natural Opportunity\nEmbed the teaching opportunity within the learner's snack time routine. Deliver the opportunity when the MO is evident (learner oriented to the relevant stimulus, approaching the materials, or demonstrating interest).\n\n## Prompt Strategy\nStrategy: Time Delay\nWait a brief interval (0->2->4 s) for independent response before delivering a model or verbal prompt.\nCurrent prompt level: At the generalization stage, use expectant look only; avoid direct prompts. The MO itself should be sufficient to occasion the response.\n\n## Natural Reinforcer\nNatural reinforcer: immediate access to the requested item for 30\u201360 seconds.\nAvoid contrived consequences \u2014 the functional outcome IS the reinforcer.\n\n## Generalization Tactics\n- Program multiple exemplars across 3 different stimuli or peers.\n- Rotate between 2 different natural settings.\n- Rotate across 3 different adults during the teaching phase.\n\n## Mastery Criteria\nFluent exchange (response within 3 s of MO / opportunity) with appropriate topography, 80% of opportunities across 3 sessions.\n\n## Data Collection\nOpportunity-based data recording: each naturally-occasioned trial is scored for independence and topography. IOA scheduled every 5 sessions minimum; target agreement \u2265 80%.\n\n## Generalization & Maintenance Plan\nPost-mastery: probe across novel peers, settings, and materials. Maintenance probes weekly for 4 weeks, then monthly. Fade adult-delivered prompts before declaring mastery."}], "meta": {"task_type": "teaching_program", "example_id": "4cd2613946218aec", "gold_labels": {"method": "net", "domain": "VB-MAPP.mand", "level": "L2", "learner_profile": "early", "mastery_state": "generalization"}, "provenance": {"layer": 1, "area": "net", "template_id": "task1_net_v1", "taxonomy_cells": {"skill_target": "mands using adjectives (big, little, more)", "mo_category": "mand_item", "mo_arrangement": "deprivation_preferred_item", "prompt_strategy": "time_delay", "mastery_criterion": "mc_fluent_exchange"}, "teacher_model": null, "seed_tag": "3768"}, "curation": {"target_split": "test"}}}