{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T04:26:18.086757+00:00",
 "evaluator_version": "F3-conf-04/1.0",
 "notes": "Deterministic evaluation; reproducibility filled by the harness. HAC band recomputed from the executor's own h=4 loss differentials.",
 "oracle_sha256": "e4d1358d226ad618b91a80bf40bd5faca84e88da6cdfcca828d5c14cf5fc5e42",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "8a0327a351b27e6d0d60c28fb985b2f4d2312c0073a23d74f8e019b8613078de",
 "required_criteria": [
  {
   "description": "Seasonal-naive RMSE/MAE at h=1 exact (rel 1e-6)",
   "expected": {
    "mae_snaive_h1": 2.1374736750000003,
    "rmse_snaive_h1": 2.849125860156572
   },
   "id": "snaive_h1",
   "observed": {
    "mae_snaive_h1": 2.1374736750000003,
    "rmse_snaive_h1": 2.849125860156572
   },
   "passed": true,
   "tolerance": {
    "mae_snaive_h1": {
     "rel": 1e-06
    },
    "rmse_snaive_h1": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "Seasonal-naive RMSE/MAE at h=2 exact",
   "expected": {
    "mae_snaive_h2": 2.1259446750000004,
    "rmse_snaive_h2": 2.846674080377472
   },
   "id": "snaive_h2",
   "observed": {
    "mae_snaive_h2": 2.1259446750000004,
    "rmse_snaive_h2": 2.846674080377472
   },
   "passed": true,
   "tolerance": {
    "mae_snaive_h2": {
     "rel": 1e-06
    },
    "rmse_snaive_h2": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "Seasonal-naive RMSE/MAE at h=4 exact",
   "expected": {
    "mae_snaive_h4": 2.181266125,
    "rmse_snaive_h4": 2.8823159392575315
   },
   "id": "snaive_h4",
   "observed": {
    "mae_snaive_h4": 2.181266125,
    "rmse_snaive_h4": 2.8823159392575315
   },
   "passed": true,
   "tolerance": {
    "mae_snaive_h4": {
     "rel": 1e-06
    },
    "rmse_snaive_h4": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "n_origins = 40",
   "expected": {
    "n_origins": 40
   },
   "id": "counts",
   "observed": {
    "n_origins": 40
   },
   "passed": true,
   "tolerance": {
    "n_origins": {
     "abs": 0
    }
   }
  },
  {
   "description": "forecasts.csv: 240 rows, targets = origin + h quarters, seasonal-naive rows exact, actuals = data",
   "expected": {
    "n_rows": 240
   },
   "id": "forecasts_chronology",
   "observed": {
    "actual_mismatches": 0,
    "bad_rows": 0,
    "counts": {
     "model_h1": 40,
     "model_h2": 40,
     "model_h4": 40,
     "snaive_h1": 40,
     "snaive_h2": 40,
     "snaive_h4": 40
    },
    "n_rows": 240
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "model RMSE/MAE per horizon agree with forecasts.csv (rel 1e-5)",
   "expected": null,
   "id": "model_errors_consistent",
   "observed": {
    "h1": {
     "mae_from_csv": 1.5610943,
     "mae_reported": 1.5610943812457803,
     "rmse_from_csv": 2.1974413047827923,
     "rmse_reported": 2.1974413926289347
    },
    "h2": {
     "mae_from_csv": 1.532854175,
     "mae_reported": 1.532854153098179,
     "rmse_from_csv": 2.36077440702847,
     "rmse_reported": 2.3607744099808405
    },
    "h4": {
     "mae_from_csv": 1.6015151500000002,
     "mae_reported": 1.6015151795416702,
     "rmse_from_csv": 2.3551335554100112,
     "rmse_reported": 2.355133607575277
    }
   },
   "passed": true,
   "tolerance": {
    "rel": 1e-05
   }
  },
  {
   "description": "rel_improvement = 1 - rmse_model/rmse_snaive (abs 1e-6)",
   "expected": null,
   "id": "rel_improvement_consistent",
   "observed": {
    "h1": {
     "expected": 0.22873137218719586,
     "reported": 0.22873137218719586
    },
    "h2": {
     "expected": 0.17069030618784453,
     "reported": 0.17069030618784453
    },
    "h4": {
     "expected": 0.18290234061504496,
     "reported": 0.18290234061504496
    }
   },
   "passed": true,
   "tolerance": {
    "abs": 1e-06
   }
  },
  {
   "description": "loss_diff_mean_h4 = mean(e_snaive^2 - e_model^2) at h=4 from forecasts.csv (rel 1e-5)",
   "expected": null,
   "id": "loss_diff_mean_h4",
   "observed": {
    "from_csv": 2.7610911098798248,
    "reported": 2.7610908641674845
   },
   "passed": true,
   "tolerance": {
    "rel": 1e-05
   }
  },
  {
   "description": "loss_diff_se_h4 equals (rel 3%) the HAC standard error recomputed from the executor's own h=4 loss differentials with the reported kernel and truncation lag (lag in [3, 8]; Bartlett with either weight convention, rectangular or Parzen; small-sample factor n/(n-1) covered)",
   "expected": {
    "informational_band_bartlett_3_8": [
     1.2252063557413557,
     2.147723939252431
    ]
   },
   "id": "hac_se_h4",
   "observed": {
    "iid_se": 2.0479214147612916,
    "kernel": "bartlett",
    "lags": 3,
    "reported": 2.147724001358359,
    "valid_ses_for_reported_kernel_and_lag": [
     2.147723939252431,
     2.264670924258995
    ]
   },
   "passed": true,
   "tolerance": 0.03
  },
  {
   "description": "hac_lags_h4 integer in [3, 8]",
   "expected": [
    3,
    8
   ],
   "id": "hac_lags_h4",
   "observed": 3,
   "passed": true,
   "tolerance": null
  },
  {
   "description": "dm_stat_h4 = mean/se (rel 1e-3) and dm_pvalue_h4 consistent (normal or t(39), with/without HLN correction, abs 0.005)",
   "expected": {
    "pvalue_band": [
     0.19358645432611787,
     0.25291446673879137
    ]
   },
   "id": "dm_stat_h4",
   "observed": {
    "dm_pvalue": 0.19858645432611777,
    "dm_stat": 1.2855892388506125
   },
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RC0079",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F3-conf-04"
}