{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T04:07:34.612046+00:00",
 "evaluator_version": "F6-conf-04/1.0",
 "notes": "Deterministic evaluation (stdlib only); figure checked by PNG magic bytes, table by CSV parse; reproducibility is filled by the harness.",
 "oracle_sha256": "0c9223f343f191437ea26a918a2a77e21882e6c16a0a86b30fd200135eedc7b7",
 "quality_components": {
  "baseline": 0.5,
  "correctness": 0.75,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 0.85,
 "receipt_sha256": "ea4d55d68453ae7b0f1feaa8ff1942a07e3206f51bb1511686f38d71670b94b9",
 "required_criteria": [
  {
   "description": "n_analysed = 1200",
   "expected": {
    "n_analysed": 1200
   },
   "id": "counts",
   "observed": {
    "n_analysed": 1188
   },
   "passed": false,
   "tolerance": {
    "n_analysed": {
     "abs": 0
    }
   }
  },
  {
   "description": "unadjusted slope and its 95% CI match the reference (abs 0.003 / 0.006)",
   "expected": {
    "naive_ci_high": -0.10792450180373739,
    "naive_ci_low": -0.162454708281857,
    "naive_estimate": -0.1351896050427972
   },
   "id": "naive",
   "observed": {
    "naive_ci_high": -0.10304397995314195,
    "naive_ci_low": -0.1603518326928757,
    "naive_estimate": -0.13169790632300882
   },
   "passed": false,
   "tolerance": {
    "naive_ci_high": {
     "abs": 0.006
    },
    "naive_ci_low": {
     "abs": 0.006
    },
    "naive_estimate": {
     "abs": 0.003
    }
   }
  },
  {
   "description": "confounder-adjusted slope within 0.003, SE within 10% (OLS/HC variants), CI bounds within 0.005",
   "expected": {
    "effect_ci_high": 0.27082150943837385,
    "effect_ci_low": 0.23362748302781414,
    "effect_estimate": 0.252224496233094,
    "effect_se": 0.009478852176649417
   },
   "id": "adjusted",
   "observed": {
    "effect_ci_high": 0.27276978871330976,
    "effect_ci_low": 0.2343066231767153,
    "effect_estimate": 0.25353820594501253,
    "effect_se": 0.009812212326345536
   },
   "passed": true,
   "tolerance": {
    "effect_ci_high": {
     "abs": 0.005
    },
    "effect_ci_low": {
     "abs": 0.005
    },
    "effect_estimate": {
     "abs": 0.003
    },
    "effect_se": {
     "rel": 0.1
    }
   }
  },
  {
   "description": "coefficient on the skill index within 0.03",
   "expected": {
    "skill_index_coefficient": -4.630436409471264
   },
   "id": "skill_index_coef",
   "observed": {
    "skill_index_coefficient": -4.624620879345756
   },
   "passed": true,
   "tolerance": {
    "skill_index_coefficient": {
     "abs": 0.03
    }
   }
  },
  {
   "description": "naive (baseline) and adjusted (model) residual RMSE within 1-1.5%",
   "expected": {
    "baseline_metric": 3.860935650765891,
    "model_metric": 1.9773229272347403
   },
   "id": "fit_metrics",
   "observed": {
    "baseline_metric": 3.8601022336733584,
    "model_metric": 1.9758571828823268
   },
   "passed": true,
   "tolerance": {
    "baseline_metric": {
     "rel": 0.01
    },
    "model_metric": {
     "rel": 0.015
    }
   }
  },
  {
   "description": "conclusion code = positive_effect (the adjusted estimate)",
   "expected": "positive_effect",
   "id": "conclusion",
   "observed": "positive_effect",
   "passed": true,
   "tolerance": null
  },
  {
   "description": "out/figure1.png exists and is a valid PNG",
   "expected": "valid PNG",
   "id": "figure",
   "observed": true,
   "passed": true,
   "tolerance": null
  },
  {
   "description": "out/table1.csv parses with >= 2 data rows",
   "expected": ">= 2 data rows",
   "id": "table",
   "observed": 5,
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RC0016",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": false,
 "task_id": "F6-conf-04"
}