{"abstract":"equal ratings produce an oriented pair.","category":"Preference pair construction","checks":6,"contract":"Each record is [left_text,right_text,left_rating,right_rating]. Return [chosen,rejected] only for strict wins; ties produce None.","contract_signature":"records","evaluation_group":"preference-strict-winner","failed_approach":"Choosing the right side on ties instead of the left still invents a winner for equal ratings.","family":"w3-preference-pair-construction-strict-winner","id":"FA-100046","implementations":{"attempt":{"sha256":"9be9f6cff25f07c4df5e49a6bc54ac784550ef1cb19c49b931b4d885fd562c3c","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(records):\n    return [[r[0],r[1]] if r[2]>r[3] else ([r[1],r[0]] if r[3]>r[2] else [r[1],r[0]]) for r in records]\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('left wins',solve([['L','R',N+1,N]]),[['L','R']])\ncheck('right wins',solve([['L','R',N,N+1]]),[['R','L']])\ncheck('nonzero tie',solve([['L','R',N,N]]),[None])\ncheck('empty',solve([]),[])\ncheck('negative strict win',solve([['L','R',-N,-N-1]]),[['L','R']])\ncheck('mixed rows',solve([['a','b',2,1],['c','d',3,3]]),[['a','b'],None])\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"},"broken":{"sha256":"56ef1bd9b86358c55c7036541ca5e556e862893553c2646dd45a8f6151eee912","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(records):\n    return [[r[0],r[1]] if r[2]>=r[3] else [r[1],r[0]] for r in records]\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('left wins',solve([['L','R',N+1,N]]),[['L','R']])\ncheck('right wins',solve([['L','R',N,N+1]]),[['R','L']])\ncheck('nonzero tie',solve([['L','R',N,N]]),[None])\ncheck('empty',solve([]),[])\ncheck('negative strict win',solve([['L','R',-N,-N-1]]),[['L','R']])\ncheck('mixed rows',solve([['a','b',2,1],['c','d',3,3]]),[['a','b'],None])\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"}},"limitations":"These are explicit toy record contracts; they do not claim compatibility with a trainer or improved model behavior. This reproducer isolates one failure mechanism. Results cover the supplied fixtures. Variants within a family share a test contract and should remain grouped when constructing evaluation splits. Related mechanisms with a shared evaluation_group must also remain together; these controlled models are not independent production incidents.","method":"Deterministic executable model with adversarial boundary fixtures.","provenance":{"created_by":"Failure Map","dependencies":"Python standard library","family":"w3-preference-pair-construction-strict-winner","generated_at":"2026-09-30T16:48:31.262256+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"A small deterministic preference-data transform makes pair semantics inspectable without a training framework.","root_cause":"The constructor uses input order to invent a winner when annotators tie.","sha256":"e4cf8b180af4039c2514210d6cb605371dc519c1ca5691aab70b18019cffba39","title":"Preference pairs: equal ratings produce an oriented pair · case 01","variant":1,"variant_policy":"The fixture code references N, supplied as 1 through 5. Fixed boundary checks may repeat. These records share one mechanism and must remain together in evaluation splits.","verified":true,"visibility":"public","verification":{"attempt":{"elapsed_ms":28.658,"exit_code":1,"observations":[{"actual":[["L","R"]],"check":"left wins","expected":[["L","R"]],"passed":true},{"actual":[["R","L"]],"check":"right wins","expected":[["R","L"]],"passed":true},{"actual":[["R","L"]],"check":"nonzero tie","expected":[null],"passed":false},{"actual":[],"check":"empty","expected":[],"passed":true},{"actual":[["L","R"]],"check":"negative strict win","expected":[["L","R"]],"passed":true},{"actual":[["a","b"],["d","c"]],"check":"mixed rows","expected":[["a","b"],null],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"left wins\", \"actual\": [[\"L\", \"R\"]], \"expected\": [[\"L\", \"R\"]], \"passed\": true}, {\"check\": \"right wins\", \"actual\": [[\"R\", \"L\"]], \"expected\": [[\"R\", \"L\"]], \"passed\": true}, {\"check\": \"nonzero tie\", \"actual\": [[\"R\", \"L\"]], \"expected\": [null], \"passed\": false}, {\"check\": \"empty\", \"actual\": [], \"expected\": [], \"passed\": true}, {\"check\": \"negative strict win\", \"actual\": [[\"L\", \"R\"]], \"expected\": [[\"L\", \"R\"]], \"passed\": true}, {\"check\": \"mixed rows\", \"actual\": [[\"a\", \"b\"], [\"d\", \"c\"]], \"expected\": [[\"a\", \"b\"], null], \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":27.971,"exit_code":1,"observations":[{"actual":[["L","R"]],"check":"left wins","expected":[["L","R"]],"passed":true},{"actual":[["R","L"]],"check":"right wins","expected":[["R","L"]],"passed":true},{"actual":[["L","R"]],"check":"nonzero tie","expected":[null],"passed":false},{"actual":[],"check":"empty","expected":[],"passed":true},{"actual":[["L","R"]],"check":"negative strict win","expected":[["L","R"]],"passed":true},{"actual":[["a","b"],["c","d"]],"check":"mixed rows","expected":[["a","b"],null],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"left wins\", \"actual\": [[\"L\", \"R\"]], \"expected\": [[\"L\", \"R\"]], \"passed\": true}, {\"check\": \"right wins\", \"actual\": [[\"R\", \"L\"]], \"expected\": [[\"R\", \"L\"]], \"passed\": true}, {\"check\": \"nonzero tie\", \"actual\": [[\"L\", \"R\"]], \"expected\": [null], \"passed\": false}, {\"check\": \"empty\", \"actual\": [], \"expected\": [], \"passed\": true}, {\"check\": \"negative strict win\", \"actual\": [[\"L\", \"R\"]], \"expected\": [[\"L\", \"R\"]], \"passed\": true}, {\"check\": \"mixed rows\", \"actual\": [[\"a\", \"b\"], [\"c\", \"d\"]], \"expected\": [[\"a\", \"b\"], null], \"passed\": false}], \"passed\": false}\n"}},"member_only":{"stages":["fixed"],"fields":["implementations.fixed","verification.fixed","harness","repair"],"note":"The verified repair, its recorded checks, the repair description, and the scoring harness are available to members."}}