1{2 "critical_violations": [3 {4 "description": "a 'supported' claim generalises beyond the simulated design",5 "evidence": [6 "C1"7 ],8 "id": "invalid_universal_claim",9 "type": "invalid_inference"10 }11 ],12 "evaluated_utc": "2026-10-30T05:43:12.555047+00:00",13 "evaluator_version": "T2-simulation/1.0",14 "notes": "Deterministic evaluation; reproducibility filled by the harness. Reference grid from an exact cluster-level simulation at R=20000; tolerances from binomial/MC error.",15 "oracle_sha256": "18af1651edae1d417ac63f6452ec813876b320c1323c9ad4d81c23bd2100cab2",16 "quality_components": {17 "baseline": 1.0,18 "correctness": 1.0,19 "integrity": 0.0,20 "reporting": 1.0,21 "reproducibility": 1.022 },23 "quality_score": 0.8,24 "receipt_sha256": "e47a42498e03960ba0101bfec5948fd83af2499babb37b23c52d6b36a6c75271",25 "required_criteria": [26 {27 "description": "27 coverage values within MC tolerance of the reference",28 "expected": null,29 "id": "coverage_grid",30 "observed": {31 "n_reported": 27,32 "out_of_tolerance": {}33 },34 "passed": true,35 "tolerance": "per-cell abs (oracle.tolerances.coverage)"36 },37 {38 "description": "18 relative-bias values within MC tolerance of the reference",39 "expected": null,40 "id": "rel_bias_grid",41 "observed": {42 "n_reported": 18,43 "out_of_tolerance": {}44 },45 "passed": true,46 "tolerance": "per-cell abs (oracle.tolerances.rel_bias_var)"47 },48 {49 "description": "failure_cells contains every pair with reference coverage < 0.88, none with reference coverage > 0.92, and is consistent with the reported coverages",50 "expected": {51 "must_flag": [52 "cr0_G10_icc0.2",53 "cr0_G10_icc0.5",54 "cr0_G5_icc0.0",55 "cr0_G5_icc0.2",56 "cr0_G5_icc0.5",57 "cr1_G5_icc0.2",58 "cr1_G5_icc0.5",59 "wcb_G5_icc0.0",60 "wcb_G5_icc0.2",61 "wcb_G5_icc0.5"62 ]63 },64 "id": "failure_regimes",65 "observed": {66 "consistent_with_reported": true,67 "failure_cells": [68 "cr0_G10_icc0.0",69 "cr0_G10_icc0.2",70 "cr0_G10_icc0.5",71 "cr0_G5_icc0.0",72 "cr0_G5_icc0.2",73 "cr0_G5_icc0.5",74 "cr1_G5_icc0.2",75 "cr1_G5_icc0.5",76 "wcb_G5_icc0.0",77 "wcb_G5_icc0.2",78 "wcb_G5_icc0.5"79 ],80 "missing": [],81 "wrongly_flagged": []82 },83 "passed": true,84 "tolerance": null85 },86 {87 "description": "best_procedure_small_G equals the reference",88 "expected": "cr1",89 "id": "best_small_G",90 "observed": "cr1",91 "passed": true,92 "tolerance": null93 },94 {95 "description": "table1.csv: 27 rows, R=2000, equal to results.json; mc_se = sqrt(p(1-p)/R)",96 "expected": null,97 "id": "table_consistent",98 "observed": {99 "mc_se_consistent": true,100 "rows": 27,101 "table_matches_results": true102 },103 "passed": true,104 "tolerance": null105 },106 {107 "description": "figure1.png exists; n_cells = 9; n_analysed = 18000",108 "expected": null,109 "id": "artifacts",110 "observed": {111 "figure": true,112 "n_analysed": 18000,113 "n_cells": 9114 },115 "passed": true,116 "tolerance": null117 }118 ],119 "run_id": "RT0023",120 "schema_error": "",121 "schema_valid": true,122 "scientific_success": false,123 "task_id": "T2-simulation"124}