1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T04:49:57.542123+00:00",4 "evaluator_version": "F6-conf-03/1.0",5 "notes": "Deterministic evaluation (stdlib only); figure checked by PNG magic bytes, table by CSV parse; reproducibility is filled by the harness.",6 "oracle_sha256": "e605f4646a87a44aa733c28992c93adb555b9c9bed004be061cc3bef0506accf",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": "5d2aed300d6a7596efe16c6d4081b34e2fb21006f241b187a157fd354594c9b4",16 "required_criteria": [17 {18 "description": "n_analysed = 240, n_sub1 = 96, n_sub2 = 144 (exact)",19 "expected": {20 "n_analysed": 240,21 "n_sub1": 96,22 "n_sub2": 14423 },24 "id": "counts",25 "observed": {26 "n_analysed": 240,27 "n_sub1": 96,28 "n_sub2": 14429 },30 "passed": true,31 "tolerance": {32 "n_analysed": {33 "abs": 034 },35 "n_sub1": {36 "abs": 037 },38 "n_sub2": {39 "abs": 040 }41 }42 },43 {44 "description": "full-sample Okun coefficient within 0.004 and intercept within 0.01",45 "expected": {46 "effect_estimate": -0.2557677277487258,47 "intercept": 0.1843883541821070848 },49 "id": "okun_coefficient",50 "observed": {51 "effect_estimate": -0.2557677277487258,52 "intercept": 0.1843883541821071453 },54 "passed": true,55 "tolerance": {56 "effect_estimate": {57 "abs": 0.00458 },59 "intercept": {60 "abs": 0.0161 }62 }63 },64 {65 "description": "HAC (Newey-West) SE within 15% of the 4-lag Bartlett reference (lags 1-12 accepted; conventional or HC-only SEs rejected)",66 "expected": {67 "effect_se": 0.0358346333029656868 },69 "id": "hac_se",70 "observed": {71 "effect_se": 0.0359848839967587872 },73 "passed": true,74 "tolerance": {75 "effect_se": {76 "rel": 0.1577 }78 }79 },80 {81 "description": "95% CI bounds within 0.012 of reference",82 "expected": {83 "effect_ci_high": -0.18517416202443931,84 "effect_ci_low": -0.326361293473012385 },86 "id": "ci",87 "observed": {88 "effect_ci_high": -0.18523865112722682,89 "effect_ci_low": -0.326296804370224890 },91 "passed": true,92 "tolerance": {93 "effect_ci_high": {94 "abs": 0.01295 },96 "effect_ci_low": {97 "abs": 0.01298 }99 }100 },101 {102 "description": "subperiod slopes within 0.004",103 "expected": {104 "beta_sub1": -0.2590210534568058,105 "beta_sub2": -0.27339263306757894106 },107 "id": "subperiods",108 "observed": {109 "beta_sub1": -0.25902105345680587,110 "beta_sub2": -0.27339263306757905111 },112 "passed": true,113 "tolerance": {114 "beta_sub1": {115 "abs": 0.004116 },117 "beta_sub2": {118 "abs": 0.004119 }120 }121 },122 {123 "description": "classical Chow F within 0.15 and p-value within 0.003; stability_conclusion = unstable",124 "expected": {125 "chow_f_stat": 6.090333006233783,126 "chow_p_value": 0.0026363238517333825,127 "stability_conclusion": "unstable"128 },129 "id": "chow",130 "observed": {131 "chow_f_stat": 6.0903330062337675,132 "chow_p_value": 0.002636323851733417,133 "stability_conclusion": "unstable"134 },135 "passed": true,136 "tolerance": {137 "chow_f_stat": {138 "abs": 0.15139 },140 "chow_p_value": {141 "abs": 0.003142 }143 }144 },145 {146 "description": "baseline RMSE (mean-only) and model RMSE within 1-1.5%",147 "expected": {148 "baseline_metric": 0.32465793964999184,149 "model_metric": 0.24974388166362527150 },151 "id": "fit_metrics",152 "observed": {153 "baseline_metric": 0.32465793964999184,154 "model_metric": 0.2497438816636253155 },156 "passed": true,157 "tolerance": {158 "baseline_metric": {159 "rel": 0.01160 },161 "model_metric": {162 "rel": 0.015163 }164 }165 },166 {167 "description": "conclusion code = negative_effect",168 "expected": "negative_effect",169 "id": "conclusion",170 "observed": "negative_effect",171 "passed": true,172 "tolerance": null173 },174 {175 "description": "out/figure1.png exists and is a valid PNG",176 "expected": "valid PNG",177 "id": "figure",178 "observed": true,179 "passed": true,180 "tolerance": null181 },182 {183 "description": "out/table1.csv parses with >= 2 data rows",184 "expected": ">= 2 data rows",185 "id": "table",186 "observed": 3,187 "passed": true,188 "tolerance": null189 }190 ],191 "run_id": "RC0170",192 "schema_error": "",193 "schema_valid": true,194 "scientific_success": true,195 "task_id": "F6-conf-03"196}