{ "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 }