{"abstract":"Multilabel subset accuracy counts matching labels.","category":"Evaluation metric aggregation","checks":6,"contract":"Return fraction of examples whose predicted label set equals its true label set; empty outer lists yield 0.","contract_signature":"truth, pred","evaluation_group":"w3-eval-multilabel-subset","failed_approach":"Comparing raw lists makes equivalent label sets depend on their ordering.","family":"w3-evaluation-metric-aggregation-multilabel-subset","id":"FA-99996","implementations":{"attempt":{"sha256":"a3b093171b296a7e4a2e613890cf0196039b04a0f6c250f11b7184a7c4b91b21","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(truth, pred):\n    return sum(a==b for a,b in zip(truth,pred))/len(truth) if truth else 0\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('partial overlap',solve([[1,2],[2]],[[1],[2]]),.5)\ncheck('ordering irrelevant',solve([[1,2]],[[2,1]]),1)\ncheck('empty label sets',solve([[],[]],[[],[1]]),.5)\ncheck('empty examples',solve([],[]),0)\ncheck('exact singleton',solve([[N]],[[N]]),1)\ncheck('different singleton',solve([[N]],[[N+1]]),0)\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":"2b1c6b9c513eab3ea4d3292c4c64a111f9770a145419ee8128ca588113f6ef3b","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(truth, pred):\n    return sum(bool(set(a)&set(b)) for a,b in zip(truth,pred))/len(truth) if truth else 0\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('partial overlap',solve([[1,2],[2]],[[1],[2]]),.5)\ncheck('ordering irrelevant',solve([[1,2]],[[2,1]]),1)\ncheck('empty label sets',solve([[],[]],[[],[1]]),.5)\ncheck('empty examples',solve([],[]),0)\ncheck('exact singleton',solve([[N]],[[N]]),1)\ncheck('different singleton',solve([[N]],[[N+1]]),0)\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":"Inputs are finite toy labels and scores; this defines no benchmark protocol, production metric library, or model quality claim. 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-evaluation-metric-aggregation-multilabel-subset","generated_at":"2026-09-30T16:48:30.387883+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"A small explicit evaluation contract makes aggregation behavior reproducible across labeled examples.","root_cause":"Partial label overlap is reported as a correct whole example.","sha256":"99103ba6cf2d055d0b77804cbbc360a53dbd873b7a6e7fccca3c856e7d49cc96","title":"Multilabel subset accuracy counts matching labels · 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":30.066,"exit_code":1,"observations":[{"actual":0.5,"check":"partial overlap","expected":0.5,"passed":true},{"actual":0.0,"check":"ordering irrelevant","expected":1,"passed":false},{"actual":0.5,"check":"empty label sets","expected":0.5,"passed":true},{"actual":0,"check":"empty examples","expected":0,"passed":true},{"actual":1.0,"check":"exact singleton","expected":1,"passed":true},{"actual":0.0,"check":"different singleton","expected":0,"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"partial overlap\", \"actual\": 0.5, \"expected\": 0.5, \"passed\": true}, {\"check\": \"ordering irrelevant\", \"actual\": 0.0, \"expected\": 1, \"passed\": false}, {\"check\": \"empty label sets\", \"actual\": 0.5, \"expected\": 0.5, \"passed\": true}, {\"check\": \"empty examples\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"exact singleton\", \"actual\": 1.0, \"expected\": 1, \"passed\": true}, {\"check\": \"different singleton\", \"actual\": 0.0, \"expected\": 0, \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":29.777,"exit_code":1,"observations":[{"actual":1.0,"check":"partial overlap","expected":0.5,"passed":false},{"actual":1.0,"check":"ordering irrelevant","expected":1,"passed":true},{"actual":0.0,"check":"empty label sets","expected":0.5,"passed":false},{"actual":0,"check":"empty examples","expected":0,"passed":true},{"actual":1.0,"check":"exact singleton","expected":1,"passed":true},{"actual":0.0,"check":"different singleton","expected":0,"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"partial overlap\", \"actual\": 1.0, \"expected\": 0.5, \"passed\": false}, {\"check\": \"ordering irrelevant\", \"actual\": 1.0, \"expected\": 1, \"passed\": true}, {\"check\": \"empty label sets\", \"actual\": 0.0, \"expected\": 0.5, \"passed\": false}, {\"check\": \"empty examples\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"exact singleton\", \"actual\": 1.0, \"expected\": 1, \"passed\": true}, {\"check\": \"different singleton\", \"actual\": 0.0, \"expected\": 0, \"passed\": true}], \"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."}}