{
 "critical_violations": [
  {
   "description": "claim marked 'supported' asserts weekday predictive content / an effect",
   "evidence": "C4",
   "id": "supported_effect_claim",
   "type": "invalid_inference"
  }
 ],
 "evaluated_utc": "2026-10-30T05:23:40.331397+00:00",
 "evaluator_version": "F6-conf-01/1.0",
 "notes": "Deterministic evaluation (stdlib only); figure checked by PNG magic bytes, table by CSV parse; reproducibility is filled by the harness.",
 "oracle_sha256": "c8e71dcfdde7f49c5a79be5ada24f89bf758aefd8b4e29181b2be6175f01fef1",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 0.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 0.8,
 "receipt_sha256": "a11b1e30e7b0d9d08e0209aa16bd28a9c33a79805fe4af443fcdf75078727f9c",
 "required_criteria": [
  {
   "description": "n_analysed (daily changes), n_missing_rows (blank DGS10 rows), n_train, n_test exact (\u00b11 for the edge convention)",
   "expected": {
    "n_analysed": 5001,
    "n_missing_rows": 215,
    "n_test": 2501,
    "n_train": 2500
   },
   "id": "counts",
   "observed": {
    "n_analysed": 5001,
    "n_missing_rows": 215,
    "n_test": 2501,
    "n_train": 2500
   },
   "passed": true,
   "tolerance": {
    "n_analysed": {
     "abs": 1
    },
    "n_missing_rows": {
     "abs": 0
    },
    "n_test": {
     "abs": 1
    },
    "n_train": {
     "abs": 1
    }
   }
  },
  {
   "description": "one-way ANOVA F statistic and p-value within 0.02 of the reference",
   "expected": {
    "anova_f_stat": 0.26346571680712016,
    "anova_p_value": 0.9015060507654888
   },
   "id": "anova",
   "observed": {
    "anova_f_stat": 0.2634657168,
    "anova_p_value": 0.9015060508
   },
   "passed": true,
   "tolerance": {
    "anova_f_stat": {
     "abs": 0.02
    },
    "anova_p_value": {
     "abs": 0.02
    }
   }
  },
  {
   "description": "Monday minus other-weekday mean change (bp) within 0.02 and its 95% CI bounds within 0.05 bp (Welch, pooled, HC or t/normal all accepted)",
   "expected": {
    "effect_ci_high": 0.41967597249749833,
    "effect_ci_low": -0.319335775694099,
    "effect_estimate": 0.05017009840169966
   },
   "id": "monday_contrast",
   "observed": {
    "effect_ci_high": 0.4196759725,
    "effect_ci_low": -0.3193357757,
    "effect_estimate": 0.0501700984
   },
   "passed": true,
   "tolerance": {
    "effect_ci_high": {
     "abs": 0.05
    },
    "effect_ci_low": {
     "abs": 0.05
    },
    "effect_estimate": {
     "abs": 0.02
    }
   }
  },
  {
   "description": "out-of-sample RMSE of the zero-change baseline and of the weekday-mean forecast within 0.01 bp",
   "expected": {
    "baseline_metric": 4.875704154642543,
    "model_metric": 4.883841522290305
   },
   "id": "oos_metrics",
   "observed": {
    "baseline_metric": 4.8757041546,
    "model_metric": 4.8838415223
   },
   "passed": true,
   "tolerance": {
    "baseline_metric": {
     "abs": 0.01
    },
    "model_metric": {
     "abs": 0.01
    }
   }
  },
  {
   "description": "conclusion code = no_detectable_effect (the correct negative result)",
   "expected": "no_detectable_effect",
   "id": "conclusion",
   "observed": "no_detectable_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": "RC0276",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": false,
 "task_id": "F6-conf-01"
}