{
 "critical_violations": [],
 "evaluated_utc": "2026-10-30T05:06:32.430138+00:00",
 "evaluator_version": "F3-conf-01/1.0",
 "notes": "Deterministic evaluation; reproducibility filled by the harness. Leak detection = declared information dates + exact naive + RMSE bound (h=1).",
 "oracle_sha256": "4bdc81b9911fd8af6b7eb61e560a8aed267a9e03218b07adc8afa72728fabe45",
 "quality_components": {
  "baseline": 1.0,
  "correctness": 1.0,
  "integrity": 1.0,
  "reporting": 1.0,
  "reproducibility": 1.0
 },
 "quality_score": 1.0,
 "receipt_sha256": "43da2a9708882ce3040cddd4ae9ed96d283bdb76ade7a8489fecb3f4aafd1c2d",
 "required_criteria": [
  {
   "description": "Naive RMSE/MAE at h=1 equal the lag-respecting reference (forecast = GDP growth of month t-2), rel 1e-6",
   "expected": {
    "mae_naive_h1": 0.6421395833333333,
    "rmse_naive_h1": 0.813620914876824
   },
   "id": "naive_h1",
   "observed": {
    "mae_naive_h1": 0.6421395833333333,
    "rmse_naive_h1": 0.813620914876824
   },
   "passed": true,
   "tolerance": {
    "mae_naive_h1": {
     "rel": 1e-06
    },
    "rmse_naive_h1": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "Naive RMSE/MAE at h=3 equal the lag-respecting reference, rel 1e-6",
   "expected": {
    "mae_naive_h3": 0.8715583333333333,
    "rmse_naive_h3": 1.1399827160604965
   },
   "id": "naive_h3",
   "observed": {
    "mae_naive_h3": 0.8715583333333333,
    "rmse_naive_h3": 1.1399827160604965
   },
   "passed": true,
   "tolerance": {
    "mae_naive_h3": {
     "rel": 1e-06
    },
    "rmse_naive_h3": {
     "rel": 1e-06
    }
   }
  },
  {
   "description": "n_origins = 48",
   "expected": {
    "n_origins": 48
   },
   "id": "counts",
   "observed": {
    "n_origins": 48
   },
   "passed": true,
   "tolerance": {
    "n_origins": {
     "abs": 0
    }
   }
  },
  {
   "description": "forecasts.csv: 192 rows, targets = origin + h, naive = gdp_yoy(origin - 2), actuals = data, information dates within the rules",
   "expected": {
    "n_rows": 192
   },
   "id": "forecasts_chronology",
   "observed": {
    "actual_mismatches": 0,
    "misaligned_or_wrong_naive": 0,
    "model_rows": 96,
    "n_rows": 192,
    "naive_rows": 96,
    "rows_violating_information_dates": 0
   },
   "passed": true,
   "tolerance": null
  },
  {
   "description": "model RMSE/MAE agree with forecasts.csv (rel 1e-5)",
   "expected": null,
   "id": "model_errors_consistent",
   "observed": {
    "h1": {
     "mae_from_csv": 0.6039917291666668,
     "mae_reported": 0.6039917578066155,
     "rmse_from_csv": 0.7429391431496228,
     "rmse_reported": 0.7429391714223801
    },
    "h3": {
     "mae_from_csv": 0.7534547083333333,
     "mae_reported": 0.7534546734385598,
     "rmse_from_csv": 0.9023000300820814,
     "rmse_reported": 0.9023000239646665
    }
   },
   "passed": true,
   "tolerance": {
    "rel": 1e-05
   }
  },
  {
   "description": "rel_improvement = 1 - rmse_model/rmse_naive (abs 1e-6)",
   "expected": null,
   "id": "rel_improvement_consistent",
   "observed": {
    "h1": {
     "expected": 0.08687306602134803,
     "reported": 0.08687306602134803
    },
    "h3": {
     "expected": 0.20849675065004825,
     "reported": 0.20849675065004825
    }
   },
   "passed": true,
   "tolerance": {
    "abs": 1e-06
   }
  },
  {
   "description": "last_target_date_available = last origin - 2 months; last_predictor_date_available = last origin - 1 month",
   "expected": {
    "last_predictor_date_available": "2026-03-01",
    "last_target_date_available": "2026-02-01"
   },
   "id": "information_dates_reported",
   "observed": {
    "last_predictor_date_available": "2026-03-01",
    "last_target_date_available": "2026-02-01"
   },
   "passed": true,
   "tolerance": null
  }
 ],
 "run_id": "RC0216",
 "schema_error": "",
 "schema_valid": true,
 "scientific_success": true,
 "task_id": "F3-conf-01"
}