1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T03:54:53.571202+00:00",4 "evaluator_version": "F6-dev-01/1.0",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": "f9ad2737d1a0325a515f2053b4904509146d5670cca59b75e3e741a9079236dc",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": "8d12eb41d29e541d4955577751885c5296adc22642ec72646a3176223b38866a",16 "required_criteria": [17 {18 "description": "analysis_year, n_analysed and n_excluded_missing exact (countries/economies only, aggregates excluded)",19 "expected": {20 "analysis_year": 2023,21 "n_analysed": 197,22 "n_excluded_missing": 2023 },24 "id": "year_and_counts",25 "observed": {26 "analysis_year": 2023,27 "n_analysed": 197,28 "n_excluded_missing": 2029 },30 "passed": true,31 "tolerance": {32 "analysis_year": {33 "abs": 034 },35 "n_analysed": {36 "abs": 037 },38 "n_excluded_missing": {39 "abs": 040 }41 }42 },43 {44 "description": "OLS slope of life expectancy on log GDP per capita within 0.02 of reference",45 "expected": {46 "effect_estimate": 5.26717345195869147 },48 "id": "slope",49 "observed": {50 "effect_estimate": 5.26717345195865551 },52 "passed": true,53 "tolerance": {54 "effect_estimate": {55 "abs": 0.0256 }57 }58 },59 {60 "description": "heteroskedasticity-robust SE within 5% of HC1 reference (HC0\u2013HC3 accepted, conventional OLS SE rejected)",61 "expected": {62 "effect_se": 0.2084255526375244463 },64 "id": "robust_se",65 "observed": {66 "effect_se": 0.2106752869116222767 },68 "passed": true,69 "tolerance": {70 "effect_se": {71 "rel": 0.0572 }73 }74 },75 {76 "description": "95% CI bounds within 0.03 of reference (t or normal critical values, any HC variant)",77 "expected": {78 "effect_ci_high": 5.678231171257736,79 "effect_ci_low": 4.85611573265964580 },81 "id": "ci",82 "observed": {83 "effect_ci_high": 5.6800894267380775,84 "effect_ci_low": 4.85425747717923385 },86 "passed": true,87 "tolerance": {88 "effect_ci_high": {89 "abs": 0.0390 },91 "effect_ci_low": {92 "abs": 0.0393 }94 }95 },96 {97 "description": "Pearson correlation and R\u00b2 within 0.005",98 "expected": {99 "pearson_r": 0.8613437957840087,100 "r_squared": 0.7419131345356038101 },102 "id": "correlation_baseline",103 "observed": {104 "pearson_r": 0.8613437957840087,105 "r_squared": 0.7419131345356038106 },107 "passed": true,108 "tolerance": {109 "pearson_r": {110 "abs": 0.005111 },112 "r_squared": {113 "abs": 0.005114 }115 }116 },117 {118 "description": "baseline RMSE (mean-only) and model RMSE within 1\u20131.5%",119 "expected": {120 "baseline_metric": 7.07645404460588,121 "model_metric": 3.5949979094078177122 },123 "id": "fit_metrics",124 "observed": {125 "baseline_metric": 7.07645404460588,126 "model_metric": 3.5949979094078177127 },128 "passed": true,129 "tolerance": {130 "baseline_metric": {131 "rel": 0.01132 },133 "model_metric": {134 "rel": 0.015135 }136 }137 },138 {139 "description": "conclusion code = positive_effect",140 "expected": "positive_effect",141 "id": "conclusion",142 "observed": "positive_effect",143 "passed": true,144 "tolerance": null145 },146 {147 "description": "out/figure1.png exists and is a valid PNG",148 "expected": "valid PNG",149 "id": "figure",150 "observed": true,151 "passed": true,152 "tolerance": null153 },154 {155 "description": "out/table1.csv parses with >= 2 data rows",156 "expected": ">= 2 data rows",157 "id": "table",158 "observed": 4,159 "passed": true,160 "tolerance": null161 }162 ],163 "run_id": "RP0016",164 "schema_error": "",165 "schema_valid": true,166 "scientific_success": true,167 "task_id": "F6-dev-01"168}