1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T05:04:02.262924+00:00",4 "evaluator_version": "F3-conf-01/1.0",5 "notes": "Deterministic evaluation; reproducibility filled by the harness. Leak detection = declared information dates + exact naive + RMSE bound (h=1).",6 "oracle_sha256": "4bdc81b9911fd8af6b7eb61e560a8aed267a9e03218b07adc8afa72728fabe45",7 "quality_components": {8 "baseline": 1.0,9 "correctness": 1.0,10 "integrity": 1.0,11 "reporting": 1.0,12 "reproducibility": 1.013 },14 "quality_score": 1.0,15 "receipt_sha256": "c0bae976723248d506827c00519a438769cf33ab10e6ca1a7888066a45209ef3",16 "required_criteria": [17 {18 "description": "Naive RMSE/MAE at h=1 equal the lag-respecting reference (forecast = GDP growth of month t-2), rel 1e-6",19 "expected": {20 "mae_naive_h1": 0.6421395833333333,21 "rmse_naive_h1": 0.81362091487682422 },23 "id": "naive_h1",24 "observed": {25 "mae_naive_h1": 0.6421395833333333,26 "rmse_naive_h1": 0.81362091487682427 },28 "passed": true,29 "tolerance": {30 "mae_naive_h1": {31 "rel": 1e-0632 },33 "rmse_naive_h1": {34 "rel": 1e-0635 }36 }37 },38 {39 "description": "Naive RMSE/MAE at h=3 equal the lag-respecting reference, rel 1e-6",40 "expected": {41 "mae_naive_h3": 0.8715583333333333,42 "rmse_naive_h3": 1.139982716060496543 },44 "id": "naive_h3",45 "observed": {46 "mae_naive_h3": 0.8715583333333333,47 "rmse_naive_h3": 1.139982716060496548 },49 "passed": true,50 "tolerance": {51 "mae_naive_h3": {52 "rel": 1e-0653 },54 "rmse_naive_h3": {55 "rel": 1e-0656 }57 }58 },59 {60 "description": "n_origins = 48",61 "expected": {62 "n_origins": 4863 },64 "id": "counts",65 "observed": {66 "n_origins": 4867 },68 "passed": true,69 "tolerance": {70 "n_origins": {71 "abs": 072 }73 }74 },75 {76 "description": "forecasts.csv: 192 rows, targets = origin + h, naive = gdp_yoy(origin - 2), actuals = data, information dates within the rules",77 "expected": {78 "n_rows": 19279 },80 "id": "forecasts_chronology",81 "observed": {82 "actual_mismatches": 0,83 "misaligned_or_wrong_naive": 0,84 "model_rows": 96,85 "n_rows": 192,86 "naive_rows": 96,87 "rows_violating_information_dates": 088 },89 "passed": true,90 "tolerance": null91 },92 {93 "description": "model RMSE/MAE agree with forecasts.csv (rel 1e-5)",94 "expected": null,95 "id": "model_errors_consistent",96 "observed": {97 "h1": {98 "mae_from_csv": 0.6039917291666668,99 "mae_reported": 0.6039917578066155,100 "rmse_from_csv": 0.7429391431496228,101 "rmse_reported": 0.7429391714223801102 },103 "h3": {104 "mae_from_csv": 0.7534547083333333,105 "mae_reported": 0.7534546734385598,106 "rmse_from_csv": 0.9023000300820814,107 "rmse_reported": 0.9023000239646665108 }109 },110 "passed": true,111 "tolerance": {112 "rel": 1e-05113 }114 },115 {116 "description": "rel_improvement = 1 - rmse_model/rmse_naive (abs 1e-6)",117 "expected": null,118 "id": "rel_improvement_consistent",119 "observed": {120 "h1": {121 "expected": 0.08687306602134803,122 "reported": 0.08687306602134803123 },124 "h3": {125 "expected": 0.20849675065004825,126 "reported": 0.20849675065004825127 }128 },129 "passed": true,130 "tolerance": {131 "abs": 1e-06132 }133 },134 {135 "description": "last_target_date_available = last origin - 2 months; last_predictor_date_available = last origin - 1 month",136 "expected": {137 "last_predictor_date_available": "2026-03-01",138 "last_target_date_available": "2026-02-01"139 },140 "id": "information_dates_reported",141 "observed": {142 "last_predictor_date_available": "2026-03-01",143 "last_target_date_available": "2026-02-01"144 },145 "passed": true,146 "tolerance": null147 }148 ],149 "run_id": "RC0213",150 "schema_error": "",151 "schema_valid": true,152 "scientific_success": true,153 "task_id": "F3-conf-01"154}