1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T04:44:23.070097+00:00",4 "evaluator_version": "F1-conf-02/1.0",5 "notes": "Deterministic evaluation; reproducibility component is filled by the harness.",6 "oracle_sha256": "88041d60bfa1855cd036fae779e20faa54360c97a27f3bd8cce7e8f3e114e979",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": "518977a0b7459efc1fa323cf057637ec8a2932df23756f6409a1dac16ef2616b",16 "required_criteria": [17 {18 "description": "n_countries_total, n_countries_balanced, n_countries_incomplete and n_analysed exact",19 "expected": {20 "n_analysed": 345,21 "n_countries_balanced": 15,22 "n_countries_incomplete": 5,23 "n_countries_total": 2024 },25 "id": "counts",26 "observed": {27 "n_analysed": 345,28 "n_countries_balanced": 15,29 "n_countries_incomplete": 5,30 "n_countries_total": 2031 },32 "passed": true,33 "tolerance": {34 "n_analysed": {35 "abs": 036 },37 "n_countries_balanced": {38 "abs": 039 },40 "n_countries_incomplete": {41 "abs": 042 },43 "n_countries_total": {44 "abs": 045 }46 }47 },48 {49 "description": "balanced-panel means for 2000 and 2022 within 0.01 years and their change within 0.02",50 "expected": {51 "change_2000_2022_balanced": 3.4927999999999884,52 "mean_2000_balanced": 78.06026666666666,53 "mean_2022_balanced": 81.5530666666666554 },55 "id": "balanced_means",56 "observed": {57 "change_2000_2022_balanced": 3.4928,58 "mean_2000_balanced": 78.060267,59 "mean_2022_balanced": 81.55306760 },61 "passed": true,62 "tolerance": {63 "change_2000_2022_balanced": {64 "abs": 0.0265 },66 "mean_2000_balanced": {67 "abs": 0.0168 },69 "mean_2022_balanced": {70 "abs": 0.0171 }72 }73 },74 {75 "description": "balanced_countries lists exactly the 15 complete countries (ISO3)",76 "expected": [77 "AUS",78 "AUT",79 "BEL",80 "CAN",81 "DEU",82 "ESP",83 "FRA",84 "GBR",85 "ITA",86 "JPN",87 "KOR",88 "NLD",89 "SWE",90 "TUR",91 "USA"92 ],93 "id": "balanced_set",94 "observed": [95 "AUS",96 "AUT",97 "BEL",98 "CAN",99 "DEU",100 "ESP",101 "FRA",102 "GBR",103 "ITA",104 "JPN",105 "KOR",106 "NLD",107 "SWE",108 "TUR",109 "USA"110 ],111 "passed": true,112 "tolerance": "exact set"113 },114 {115 "description": "out/analytic.csv has exactly n_analysed rows, one per (iso3, year) of the balanced panel, with no duplicates",116 "expected": {117 "countries": [118 "AUS",119 "AUT",120 "BEL",121 "CAN",122 "DEU",123 "ESP",124 "FRA",125 "GBR",126 "ITA",127 "JPN",128 "KOR",129 "NLD",130 "SWE",131 "TUR",132 "USA"133 ],134 "rows": 345135 },136 "id": "analytic_rows",137 "observed": {138 "iso_col": "iso3",139 "rows": 345,140 "unique_pairs": 345,141 "year_col": "year"142 },143 "passed": true,144 "tolerance": {145 "abs": 0146 }147 },148 {149 "description": "out/exclusions.csv exists, has the required columns, is internally consistent, starts at the file row count and ends at n_analysed",150 "expected": {151 "first_before": 439,152 "last_after": 345153 },154 "id": "ledger",155 "observed": {156 "exists": true,157 "first_before": 439,158 "last_after": 345,159 "n_removed_list": [160 23,161 0,162 1,163 70164 ],165 "n_rows": 4,166 "total_removed": 94167 },168 "passed": true,169 "tolerance": null170 },171 {172 "description": "data_issues documents the duplicated country rows and the incomplete coverage (changing universe / missing value)",173 "expected": [174 "duplic|twice|two names|turkey|turkiye|repeated",175 "missing|incomplete|not available|absent|only from|from 2011|coverage|unbalanced|universe|gap|blank|empty"176 ],177 "id": "issues_detected",178 "observed": {179 "n_issues": 7,180 "text": "tur: 23 duplicated (iso3, year) rows from the two extractions, under country names ['turkey', 'turkiye']; values identical in every duplicated year kept one row per (iso3, year) (first occurrence); country identified by iso3; removed rows logged in exclusions.csv tur: multiple country_name spellings"181 },182 "passed": true,183 "tolerance": null184 }185 ],186 "run_id": "RC0145",187 "schema_error": "",188 "schema_valid": true,189 "scientific_success": true,190 "task_id": "F1-conf-02"191}