1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T05:38:59.083352+00:00",4 "evaluator_version": "T2-simulation/1.0",5 "notes": "Deterministic evaluation; reproducibility filled by the harness. Reference grid from an exact cluster-level simulation at R=20000; tolerances from binomial/MC error.",6 "oracle_sha256": "18af1651edae1d417ac63f6452ec813876b320c1323c9ad4d81c23bd2100cab2",7 "quality_components": {8 "baseline": 1.0,9 "correctness": 1.0,10 "integrity": 1.0,11 "reporting": 1.0,12 "reproducibility": 1.013 },14 "quality_score": 1.0,15 "receipt_sha256": "6785e8cd8951ff71ff1096f68c65f6f27fc02fd7cbcefc393750623ee99f32cc",16 "required_criteria": [17 {18 "description": "27 coverage values within MC tolerance of the reference",19 "expected": null,20 "id": "coverage_grid",21 "observed": {22 "n_reported": 27,23 "out_of_tolerance": {}24 },25 "passed": true,26 "tolerance": "per-cell abs (oracle.tolerances.coverage)"27 },28 {29 "description": "18 relative-bias values within MC tolerance of the reference",30 "expected": null,31 "id": "rel_bias_grid",32 "observed": {33 "n_reported": 18,34 "out_of_tolerance": {}35 },36 "passed": true,37 "tolerance": "per-cell abs (oracle.tolerances.rel_bias_var)"38 },39 {40 "description": "failure_cells contains every pair with reference coverage < 0.88, none with reference coverage > 0.92, and is consistent with the reported coverages",41 "expected": {42 "must_flag": [43 "cr0_G10_icc0.2",44 "cr0_G10_icc0.5",45 "cr0_G5_icc0.0",46 "cr0_G5_icc0.2",47 "cr0_G5_icc0.5",48 "cr1_G5_icc0.2",49 "cr1_G5_icc0.5",50 "wcb_G5_icc0.0",51 "wcb_G5_icc0.2",52 "wcb_G5_icc0.5"53 ]54 },55 "id": "failure_regimes",56 "observed": {57 "consistent_with_reported": true,58 "failure_cells": [59 "cr0_G10_icc0.0",60 "cr0_G10_icc0.2",61 "cr0_G10_icc0.5",62 "cr0_G5_icc0.0",63 "cr0_G5_icc0.2",64 "cr0_G5_icc0.5",65 "cr1_G5_icc0.2",66 "cr1_G5_icc0.5",67 "wcb_G5_icc0.0",68 "wcb_G5_icc0.2",69 "wcb_G5_icc0.5"70 ],71 "missing": [],72 "wrongly_flagged": []73 },74 "passed": true,75 "tolerance": null76 },77 {78 "description": "best_procedure_small_G equals the reference",79 "expected": "cr1",80 "id": "best_small_G",81 "observed": "cr1",82 "passed": true,83 "tolerance": null84 },85 {86 "description": "table1.csv: 27 rows, R=2000, equal to results.json; mc_se = sqrt(p(1-p)/R)",87 "expected": null,88 "id": "table_consistent",89 "observed": {90 "mc_se_consistent": true,91 "rows": 27,92 "table_matches_results": true93 },94 "passed": true,95 "tolerance": null96 },97 {98 "description": "figure1.png exists; n_cells = 9; n_analysed = 18000",99 "expected": null,100 "id": "artifacts",101 "observed": {102 "figure": true,103 "n_analysed": 18000,104 "n_cells": 9105 },106 "passed": true,107 "tolerance": null108 }109 ],110 "run_id": "RT0017",111 "schema_error": "",112 "schema_valid": true,113 "scientific_success": true,114 "task_id": "T2-simulation"115}