SPB Git

spb/wp26_uqo

Public
1{2 "run_id": "validation_E_single_llm_mixed_random_mid",3 "arm": "E_single_llm",4 "arm_label": "E_single_llm",5 "protocol": "independent",6 "rounds": 0,7 "rounds_note": null,8 "k_repeats": null,9 "committee": "mixed_random",10 "tier": "mid",11 "models": [12  "claude-sonnet-5-5",13  "gpt-6.1-sol"14 ],15 "effort": "medium",16 "max_tokens": 4096,17 "mode": "live",18 "split": "validation",19 "n_requested": 40,20 "n_sampled": 40,21 "synthetic": false,22 "data_source": "data/processed/analytic.parquet",23 "features_source": "agentic_valuation.features",24 "geo_cache": "/Users/simon-pierreboucher/Desktop/Recherche-UQO/immobilier/agentic-valuation-quebec/data/processed/geo_features.parquet",25 "roles": [26  "generalist"27 ],28 "prompt_hashes": {29  "generalist": "ade12bb690d31dbe"30 },31 "config_hashes": {32  "budgets.yaml": "d6d368fd34b923ce",33  "data.yaml": "c20f448c79e39726",34  "models.yaml": "80e216f864e413ce",35  "treatments.yaml": "e1f71e68e67f7701"36 },37 "schema_hash": "b0170725f58da4ed",38 "package_version": "0.1.0",39 "git_commit": null,40 "python": "3.14.4",41 "host": "MacBookPro-de-simon-pierre-2.local",42 "seed": 20261027,43 "weights_source": "none (equal weights for inverse_variance/stacking; MAD scale for robust_bayes)",44 "spend_cap_usd": 500.0,45 "spend_cap_hit": false,46 "start_time": "2026-10-27T23:18:44.005904+00:00",47 "end_time": "2026-10-27T23:21:34.253000+00:00",48 "wall_clock_s": 170.2,49 "total_cost_usd_estimated": 0.8253,50 "total_tokens": 255257,51 "n_transcripts": 40,52 "n_ok_this_session": 40,53 "n_failed_this_session": 0,54 "n_resumed_skipped": 0,55 "n_turn_errors": 0,56 "stopped_early": [],57 "errors": [],58 "prediction_columns": [59  "tx_id",60  "split",61  "arm",62  "committee",63  "aggregation",64  "point",65  "q05",66  "q25",67  "q50",68  "q75",69  "q95",70  "cost_usd",71  "latency_s",72  "tokens",73  "run_id"74 ],75 "spec": {76  "arm": "E_single_llm",77  "rounds": null,78  "committee": "mixed_random",79  "split": "validation",80  "n": 40,81  "live": true,82  "tier": "mid",83  "run_id": "validation_E_single_llm_mixed_random_mid",84  "synthetic": false,85  "seed": 20261027,86  "effort": null,87  "property_concurrency": 5,88  "out_dir": null,89  "weights_path": null,90  "max_tokens": 409691 }92}
Files · main
Menu

Theme