{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T04:27:10.334932+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": "f2b9332d74ee8b5e5264d67ccf71585879fbc39e2b23213f98233de7d74743e5",
 "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": 1.52811415,
     "mae_reported": 1.5281140859976232,
     "rmse_from_csv": 2.301335021462194,
     "rmse_reported": 2.30133505858441
    },
    "h2": {
     "mae_from_csv": 1.5710263,
     "mae_reported": 1.5710263249573677,
     "rmse_from_csv": 2.441031366090561,
     "rmse_reported": 2.4410313887152637
    },
    "h4": {
     "mae_from_csv": 1.6697848999999998,
     "mae_reported": 1.669784899861287,
     "rmse_from_csv": 2.3949482148608245,
     "rmse_reported": 2.3949481801248482
    }
   },
   "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": 0.19226626988744489,
     "reported": 0.19226626988744489
    },
    "h2": {
     "expected": 0.1424970615562775,
     "reported": 0.1424970615562775
    },
    "h4": {
     "expected": 0.1690889442391338,
     "reported": 0.1690889442391338
    }
   },
   "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": 2.571968221832975,
    "reported": 2.571968388214702
   },
   "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": [
     1.2223018758376674,
     2.1575735041872885
    ]
   },
   "id": "hac_se_h4",
   "observed": {
    "iid_se": 2.050530581732508,
    "kernel": "bartlett",
    "lags": 4,
    "reported": 1.920034189330262,
    "valid_ses_for_reported_kernel_and_lag": [
     1.9200342475869951,
     2.1575735041872885
    ]
   },
   "passed": true,
   "tolerance": 0.03
  },
  {
   "description": "hac_lags_h4 integer in [3, 8]",
   "expected": [
    3,
    8
   ],
   "id": "hac_lags_h4",
   "observed": 4,
   "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": [
     0.17539396063974927,
     0.23396073669095632
    ]
   },
   "id": "dm_stat_h4",
   "observed": {
    "dm_pvalue": 0.18039396063974922,
    "dm_stat": 1.3395430156959054
   },
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RC0082",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F3-conf-04"
}