{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T05:41:12.868051+00:00",
 "evaluator_version": "T2-simulation/1.0",
 "notes": "Deterministic evaluation; reproducibility filled by the harness. Reference grid from an exact cluster-level simulation at R=20000; tolerances from binomial/MC error.",
 "oracle_sha256": "18af1651edae1d417ac63f6452ec813876b320c1323c9ad4d81c23bd2100cab2",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "0b1fee24aea9804bd824461472cac556bd7d37341142aa19585c06062f1a3556",
 "required_criteria": [
  {
   "description": "27 coverage values within MC tolerance of the reference",
   "expected": null,
   "id": "coverage_grid",
   "observed": {
    "n_reported": 27,
    "out_of_tolerance": {}
   },
   "passed": true,
   "tolerance": "per-cell abs (oracle.tolerances.coverage)"
  },
  {
   "description": "18 relative-bias values within MC tolerance of the reference",
   "expected": null,
   "id": "rel_bias_grid",
   "observed": {
    "n_reported": 18,
    "out_of_tolerance": {}
   },
   "passed": true,
   "tolerance": "per-cell abs (oracle.tolerances.rel_bias_var)"
  },
  {
   "description": "failure_cells contains every pair with reference coverage < 0.88, none with reference coverage > 0.92, and is consistent with the reported coverages",
   "expected": {
    "must_flag": [
     "cr0_G10_icc0.2",
     "cr0_G10_icc0.5",
     "cr0_G5_icc0.0",
     "cr0_G5_icc0.2",
     "cr0_G5_icc0.5",
     "cr1_G5_icc0.2",
     "cr1_G5_icc0.5",
     "wcb_G5_icc0.0",
     "wcb_G5_icc0.2",
     "wcb_G5_icc0.5"
    ]
   },
   "id": "failure_regimes",
   "observed": {
    "consistent_with_reported": true,
    "failure_cells": [
     "cr0_G10_icc0.0",
     "cr0_G10_icc0.2",
     "cr0_G10_icc0.5",
     "cr0_G5_icc0.0",
     "cr0_G5_icc0.2",
     "cr0_G5_icc0.5",
     "cr1_G5_icc0.2",
     "cr1_G5_icc0.5",
     "wcb_G5_icc0.0",
     "wcb_G5_icc0.2",
     "wcb_G5_icc0.5"
    ],
    "missing": [],
    "wrongly_flagged": []
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "best_procedure_small_G equals the reference",
   "expected": "cr1",
   "id": "best_small_G",
   "observed": "cr1",
   "passed": true,
   "tolerance": null
  },
  {
   "description": "table1.csv: 27 rows, R=2000, equal to results.json; mc_se = sqrt(p(1-p)/R)",
   "expected": null,
   "id": "table_consistent",
   "observed": {
    "mc_se_consistent": true,
    "rows": 27,
    "table_matches_results": true
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "figure1.png exists; n_cells = 9; n_analysed = 18000",
   "expected": null,
   "id": "artifacts",
   "observed": {
    "figure": true,
    "n_analysed": 18000,
    "n_cells": 9
   },
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RT0022",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "T2-simulation"
}