Files
Jyotisha/references/rectification_sealed_holdout.v1.json
T
Jesse_Chen dc2879020a docs(rectification): bind sealed holdout metrics to the frozen scorer identity
The published six keys stay on the 2026-07-21 freeze. Current-tree sidecar numbers remain diagnostic and unlabeled as release metrics. Remove the unused v2 PILOT_REPORT_PATH.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-29 01:23:34 +08:00

49 lines
2.1 KiB
JSON

{
"sealed_benchmark_id": "minute_rectification_fact_ranker_v4_holdout_v3",
"status": "not_ready",
"valid_public_aa_cases": 20,
"required_cases": 20,
"top_1_rate": 0.15,
"confirmation_coverage_rate": 0.0,
"previous_pilot_id": "minute_rectification_holdout_v2",
"dataset_path": "references/real_case_calibration/minute_rectification_holdout_v3.json",
"report_path": "references/real_case_calibration/minute_rectification_holdout_v3_report.json",
"source_audit_status": "invalidated_after_replay",
"evaluated_on": "2026-07-21",
"report_status": "invalidated_after_source_audit",
"trial_count": 20,
"top_3_rate": 0.25,
"mean_absolute_minute_error": 6.95,
"metrics_produced_by": {
"implementation_sha256": "f41c298dd6cdcebe7a93e632f7191954be7987f6012ca2a34cecb6e447fbf196",
"algorithm_version": "birth-time-event-fact-ranker-v4-shadow",
"implementation_hash_matches_at_replay": true,
"source_report": "references/real_case_calibration/minute_rectification_holdout_v3_report.json",
"evaluated_on": "2026-07-21"
},
"current_tree_scorer": {
"implementation_sha256": "99730c84c6434f52669a05e4d9a4a87df0a218e3237b5436b933252f2028384e",
"matches_metrics_scorer": false,
"official_eval_implementation_hash_matches": false,
"official_eval_trial_count": 0,
"source_report": "references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic_report.json"
},
"current_tree_unfrozen_diagnostic": {
"is_blind_evaluation": false,
"results_already_seen": true,
"scorer_frozen": false,
"source_audit_passed": false,
"must_not_claim_as_release_metrics": true,
"must_not_use_for_tuning": true,
"report_path": "references/real_case_calibration/minute_rectification_holdout_v3_post_audit_diagnostic_report.json",
"implementation_sha256": "99730c84c6434f52669a05e4d9a4a87df0a218e3237b5436b933252f2028384e",
"trial_count": 20,
"top_1_rate": 0.45,
"top_3_rate": 0.5,
"mean_absolute_minute_error": 5.8,
"confirmation_coverage_rate": 0.0,
"metric_gates_passed": false,
"verified_minute_claim_allowed": false
}
}