Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
Job has been terminated due to a temporary spike in resource usage and may be restarted later.
Error code: JobManagerCrashedError
Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
conversations list | agent string | model string | model_provider string | date string | task string | episode string | run_id string | trial_name string | result string | instruction string | verifier_output string | prompt_token_ids list | completion_token_ids list | logprobs list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[{"content":"","role":"user"},{"content":"<think>Let me analyze this problem step by step.\n\nWe hav(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T18:00:06.105794Z | code_contests-7757 | episode-2 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-7757__EzaE6T9 | 0.0 | "Looking at this problem, I need to understand the structure of a complete binary tree with symmetri(...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[9764,728,22903,411,3377,2923,539,2923,13,271,1596,599,264,4434,7620,4757,440,307,16720,1332,307,10(...TRUNCATED) | [[-0.6896046996116638,-2.8610108984139515e-6,-0.30378273129463196,-0.0000361196871381253,-0.00051175(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>I need to solve this competitive programming proble(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T19:46:28.154275Z | code_contests-7410 | episode-2 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-7410__WZLmGEU | 1.0 | "Looking at this problem, I need to understand the pattern:\n- If `a = \"abac\"`, then `b = \"ab\" +(...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[40,1144,310,11290,411,14257,15019,3377,13,6558,728,3418,424,25,271,16,13,13853,8211,440,886,1510,6(...TRUNCATED) | [[-2.20676851272583,-0.0007986203418113291,-1.9073418116022367e-6,-0.4270991086959839,-0.00807662960(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>This is a simple AtCoder problem where I need to ca(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T19:56:44.196756Z | code_contests-7367 | episode-2 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-7367__jvp2zDu | 1.0 | "Looking at this problem, I need to calculate the total number of people in the theater. Each group (...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[1919,369,264,4145,2332,34120,3377,1332,353,1144,310,10724,279,2702,1324,314,1208,11362,303,264,258(...TRUNCATED) | [[-0.4674043655395508,-9.179052540275734e-6,-0.0021971119567751884,-0.11131913959980011,-0.556074500(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>This is a straightforward implementation problem. L(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T20:07:37.135563Z | code_contests-7337 | episode-2 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-7337__fAxuEJC | 1.0 | "Looking at this problem, I need to:\n1. Process oranges in order\n2. Only squeeze oranges with size(...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[1919,369,264,29350,7873,3377,13,6558,728,3418,279,11870,25,271,16,13,710,5552,64,11036,81141,303,1(...TRUNCATED) | [[-0.7942375540733337,-0.000020146124370512553,-0.0005694191786460578,-0.7279885411262512,-0.0319010(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>This is a competitive programming problem about cal(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T13:37:04.536396Z | code_contests-9452 | episode-2 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-9452__m2BssKA | 1.0 | "Looking at this problem, I need to:\n1. Read multiple datasets until n=0\n2. For each food item, ca(...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[1919,369,264,14257,15019,3377,883,49864,24217,13,6558,728,3418,279,8242,25,271,16,13,1690,1754,348(...TRUNCATED) | [[-0.6399960517883301,-0.00021622198983095586,-0.000021338186343200505,-0.07205991446971893,-8.10618(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>Let me analyze this problem step by step.\n\nWe hav(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T15:35:42.353117Z | code_contests-9055 | episode-2 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-9055__GVBXUhQ | 1.0 | "Looking at this problem, I need to understand the tree structure:\n- Infinite binary tree with root(...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[9764,728,22903,411,3377,2923,539,2923,13,271,1596,599,449,23064,2400,7620,4757,1332,25,198,12,1828(...TRUNCATED) | [[-0.5726649165153503,-0.000010251921594317537,-0.12877872586250305,-0.000060079561080783606,-0.0103(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>The user wants me to solve a competitive programmin(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T15:04:36.756383Z | code_contests-9152 | episode-1 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-9152__WUZtvMy | 1.0 | "I'll solve this inversion counting problem using a merge sort-based approach which runs in O(n log (...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[760,1156,6587,728,310,11290,264,14257,15019,3377,883,24217,1475,34109,303,449,1287,13,561,47993,22(...TRUNCATED) | [[-1.3900878429412842,-0.056865058839321136,-0.0022539671044796705,-0.0004328738432377577,-1.1920901(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>Let me analyze this problem step by step.\n\nWe hav(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T15:56:02.479709Z | code_contests-9000 | episode-3 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-9000__e6sakxN | 0.0 | "Looking at this problem, I need to compute the expected starting time for each node in a DFS traver(...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[9764,728,22903,411,3377,2923,539,2923,13,271,1596,599,264,4757,39527,506,3177,220,16,11,321,567,26(...TRUNCATED) | [[-0.3454674184322357,-1.7881341136671836e-6,-0.41013145446777344,-0.00005185458576306701,-0.0011575(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>Let me analyze this problem:\n\n1. We have a tree r(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T11:54:52.116030Z | code_contests-9797 | episode-3 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-9797__JNARfP8 | 1.0 | "Looking at this problem, I need to:\n1. For each vertex v, consider all paths from ancestors u to v(...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[9764,728,22903,411,3377,25,271,16,13,1165,599,264,4757,39527,506,11597,220,16,198,17,13,8618,11597(...TRUNCATED) | [[-0.4305039346218109,-7.033308520476567e-6,-0.25007522106170654,-0.00020859426876995713,-0.00325257(...TRUNCATED) |
[{"content":"","role":"user"},{"content":"<think>Let me analyze this problem step by step.\n\n**Prob(...TRUNCATED) | opencode | vllm/1783248090454759 | vllm | 2026-07-05T15:22:54.831345Z | code_contests-9087 | episode-5 | 464d6fbc-3f3b-4070-b77b-de827b0e17ad | code_contests-9087__qRw4jHW | 0.0 | "Looking at this problem, I need to understand the key constraints:\n\n1. Each bag capacity `ai` mus(...TRUNCATED) | "============================= test session starts ==============================\nplatform linux --(...TRUNCATED) | [[248045,8678,198,2,13455,271,2523,599,2528,310,279,2614,5568,25,271,27,15449,29,198,4754,1267,763,3(...TRUNCATED) | [[9764,728,22903,411,3377,2923,539,2923,13,271,332,30177,43934,64700,198,12,1165,599,307,17363,440,4(...TRUNCATED) | [[-0.21084578335285187,-4.768348389916355e-6,-0.11596918106079102,-0.000025391202143509872,-0.007674(...TRUNCATED) |
End of preview.
Agent trace dataset
Decoding the literal token IDs
The prompt_token_ids / completion_token_ids / logprobs columns are the
verbatim tokens the serving engine emitted, stored PER AGENT STEP as a
list-of-lists (one inner list per turn). To turn them back into text you MUST
use the exact tokenizer the model was served with — a generic same-family
tokenizer will decode word tokens to garbage.
Served model / tokenizer source: Qwen/Qwen3.5-122B-A10B-FP8
from transformers import AutoTokenizer
# Use the served model's own tokenizer (pull from the ref above; if it is a
# gs:// mirror, copy tokenizer.json/tokenizer_config.json/vocab.json/merges.txt
# locally first and point AutoTokenizer at that dir).
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-122B-A10B-FP8")
# token_ids are list-of-lists (one list per turn) — decode each turn:
text = [tok.decode(turn, skip_special_tokens=False) for turn in completion_token_ids]
Engine-reported served model name: 1783165012733068
See tokenizer_provenance.json for a machine-readable version.
- Downloads last month
- 56