Utility maximiser (ridge cost, prompt-numeric features)
This file is a seed-0 refit made on 2026-10-03. The original training run wrote predictions and did not save weights. This upload is the refit.
quality_router_v2 version 8 sets learned_downrouting to false. The served card loads no fitted weights. This file is a learned model from the same study, and the served card leaves it unloaded.
Role
The same ridge utility fit with the interface indicator removed. The paper reports this feature set separately. The served card does not load it.
Data
Measured pool https://huggingface.co/datasets/dhresearch/outcome-router-v2-measured-pool: pilot_tasks.jsonl, pilot_outcomes.jsonl, and splits.json.
Fit
fit_heads(..., cost_model='ridge', seed=0) on rows built with use_interface=False. This is utility_maximiser_prompt_numeric_only.
Seed 0. Software at refit time: python 3.14.2, sklearn 1.9.1, numpy 2.5.3, joblib 1.6.0, lightgbm 4.7.0, scipy 1.18.1.
Agreement
Rows: train 602, val 154, test 244. Routes: cheap_model, medium_model, code_specialist, code_specialist_repair, strong_model, strong_repair. Validation cost MAE matches data/real_v2/revalidation_report.json under utility_maximiser_prompt_numeric_only.validation_cost_mae, including strong_repair ridge MAE 0.00272177 against the training-mean MAE 0.00356339 (n=154). The validation rule stores no weight inside the failure budget. The original run did not save weights. This file is the seed-0 refit.
Load
joblib.load returns the fit_heads dict. Score with predicted_outcome.predict_routes. A constant head has no model entry.
Class: dict from predicted_outcome.fit_heads.
- Downloads last month
- -