1{2 "critical_violations": [],3 "evaluated_utc": "2026-10-30T03:54:53.614616+00:00",4 "evaluator_version": "F5-dev-01/1.0",5 "notes": "Deterministic evaluation; reproducibility is filled by the harness.",6 "oracle_sha256": "334a06225da779b3ff3761de8d5c19daa7c83995ead142316f2dd658c2d32b4d",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": "9a58a6d16748e122bc05a37956f07e715e6b4e712d034897a427011c7c41c112",16 "required_criteria": [17 {18 "description": "Marshallian demands within 1e-3 of the closed form (accepts a numerical optimiser)",19 "expected": {20 "x1_demand": 16.8,21 "x2_demand": 19.522 },23 "id": "demands",24 "observed": {25 "x1_demand": 16.8,26 "x2_demand": 19.527 },28 "passed": true,29 "tolerance": {30 "x1_demand": {31 "abs": 0.00132 },33 "x2_demand": {34 "abs": 0.00135 }36 }37 },38 {39 "description": "Indirect utility within 1e-4 of the closed form",40 "expected": {41 "indirect_utility": 2.918252012863530542 },43 "id": "indirect_utility",44 "observed": {45 "indirect_utility": 2.918252012863530546 },47 "passed": true,48 "tolerance": {49 "indirect_utility": {50 "abs": 0.000151 }52 }53 },54 {55 "description": "Reported budget identity residual p1*x1 + p2*x2 - m within 1e-6 of zero",56 "expected": {57 "budget_identity_residual": 0.058 },59 "id": "budget_identity",60 "observed": {61 "budget_identity_residual": 0.062 },63 "passed": true,64 "tolerance": {65 "budget_identity_residual": {66 "abs": 1e-0667 }68 }69 },70 {71 "description": "MRS at the optimum within 1e-3 of p1/p2 and price_ratio exact",72 "expected": {73 "mrs_at_optimum": 0.625,74 "price_ratio": 0.62575 },76 "id": "mrs_equals_price_ratio",77 "observed": {78 "mrs_at_optimum": 0.625,79 "price_ratio": 0.62580 },81 "passed": true,82 "tolerance": {83 "mrs_at_optimum": {84 "abs": 0.00185 },86 "price_ratio": {87 "abs": 1e-0988 }89 }90 },91 {92 "description": "Numerically maximised utility on the budget line within 1e-4 of the analytical indirect utility",93 "expected": {94 "indirect_utility_numerical": 2.918252012863530595 },96 "id": "numerical_validation",97 "observed": {98 "indirect_utility_numerical": 2.918252012863530599 },100 "passed": true,101 "tolerance": {102 "indirect_utility_numerical": {103 "abs": 0.0001104 }105 }106 },107 {108 "description": "report.md states the assumptions/scope of the closed form (regex: 'assum' and one of interior|positive|concav|monoton|Cobb|log)",109 "expected": "report states assumptions/scope",110 "id": "assumptions_stated",111 "observed": {112 "assum": true113 },114 "passed": true,115 "tolerance": null116 }117 ],118 "run_id": "RP0019",119 "schema_error": "",120 "schema_valid": true,121 "scientific_success": true,122 "task_id": "F5-dev-01"123}