1{2 "critical_violations": [3 {4 "description": "claim marked 'supported' asserts weekday predictive content / an effect",5 "evidence": "C4",6 "id": "supported_effect_claim",7 "type": "invalid_inference"8 }9 ],10 "evaluated_utc": "2026-10-30T05:23:40.331397+00:00",11 "evaluator_version": "F6-conf-01/1.0",12 "notes": "Deterministic evaluation (stdlib only); figure checked by PNG magic bytes, table by CSV parse; reproducibility is filled by the harness.",13 "oracle_sha256": "c8e71dcfdde7f49c5a79be5ada24f89bf758aefd8b4e29181b2be6175f01fef1",14 "quality_components": {15 "baseline": 1.0,16 "correctness": 1.0,17 "integrity": 0.0,18 "reporting": 1.0,19 "reproducibility": 1.020 },21 "quality_score": 0.8,22 "receipt_sha256": "a11b1e30e7b0d9d08e0209aa16bd28a9c33a79805fe4af443fcdf75078727f9c",23 "required_criteria": [24 {25 "description": "n_analysed (daily changes), n_missing_rows (blank DGS10 rows), n_train, n_test exact (\u00b11 for the edge convention)",26 "expected": {27 "n_analysed": 5001,28 "n_missing_rows": 215,29 "n_test": 2501,30 "n_train": 250031 },32 "id": "counts",33 "observed": {34 "n_analysed": 5001,35 "n_missing_rows": 215,36 "n_test": 2501,37 "n_train": 250038 },39 "passed": true,40 "tolerance": {41 "n_analysed": {42 "abs": 143 },44 "n_missing_rows": {45 "abs": 046 },47 "n_test": {48 "abs": 149 },50 "n_train": {51 "abs": 152 }53 }54 },55 {56 "description": "one-way ANOVA F statistic and p-value within 0.02 of the reference",57 "expected": {58 "anova_f_stat": 0.26346571680712016,59 "anova_p_value": 0.901506050765488860 },61 "id": "anova",62 "observed": {63 "anova_f_stat": 0.2634657168,64 "anova_p_value": 0.901506050865 },66 "passed": true,67 "tolerance": {68 "anova_f_stat": {69 "abs": 0.0270 },71 "anova_p_value": {72 "abs": 0.0273 }74 }75 },76 {77 "description": "Monday minus other-weekday mean change (bp) within 0.02 and its 95% CI bounds within 0.05 bp (Welch, pooled, HC or t/normal all accepted)",78 "expected": {79 "effect_ci_high": 0.41967597249749833,80 "effect_ci_low": -0.319335775694099,81 "effect_estimate": 0.0501700984016996682 },83 "id": "monday_contrast",84 "observed": {85 "effect_ci_high": 0.4196759725,86 "effect_ci_low": -0.3193357757,87 "effect_estimate": 0.050170098488 },89 "passed": true,90 "tolerance": {91 "effect_ci_high": {92 "abs": 0.0593 },94 "effect_ci_low": {95 "abs": 0.0596 },97 "effect_estimate": {98 "abs": 0.0299 }100 }101 },102 {103 "description": "out-of-sample RMSE of the zero-change baseline and of the weekday-mean forecast within 0.01 bp",104 "expected": {105 "baseline_metric": 4.875704154642543,106 "model_metric": 4.883841522290305107 },108 "id": "oos_metrics",109 "observed": {110 "baseline_metric": 4.8757041546,111 "model_metric": 4.8838415223112 },113 "passed": true,114 "tolerance": {115 "baseline_metric": {116 "abs": 0.01117 },118 "model_metric": {119 "abs": 0.01120 }121 }122 },123 {124 "description": "conclusion code = no_detectable_effect (the correct negative result)",125 "expected": "no_detectable_effect",126 "id": "conclusion",127 "observed": "no_detectable_effect",128 "passed": true,129 "tolerance": null130 },131 {132 "description": "out/figure1.png exists and is a valid PNG",133 "expected": "valid PNG",134 "id": "figure",135 "observed": true,136 "passed": true,137 "tolerance": null138 },139 {140 "description": "out/table1.csv parses with >= 2 data rows",141 "expected": ">= 2 data rows",142 "id": "table",143 "observed": 5,144 "passed": true,145 "tolerance": null146 }147 ],148 "run_id": "RC0276",149 "schema_error": "",150 "schema_valid": true,151 "scientific_success": false,152 "task_id": "F6-conf-01"153}