{"abstract":"Multilabel micro recall counts samples instead of labels.","category":"Evaluation metric aggregation","checks":6,"contract":"Return total true label instances divided by total actual label instances; empty actual label sets yield 0.","contract_signature":"truth, pred","evaluation_group":"w3-eval-multilabel-micro","failed_approach":"Using union size penalizes extra predictions and calculates Jaccard similarity instead.","family":"w3-evaluation-metric-aggregation-multilabel-micro","id":"FA-100001","implementations":{"attempt":{"sha256":"e469fc79d2c9c9f48dd27116e6473da9d5c1c0511accb5ffb177e06beb55dee7","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(truth, pred):\n    hits=sum(len(set(a)&set(b)) for a,b in zip(truth,pred)); total=sum(len(set(a)|set(b)) for a,b in zip(truth,pred)); return hits/total if total else 0\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('multiple labels',solve([[1,2,3],[4]],[[1,2],[4]]),.75)\ncheck('extra predicted ignored',solve([[1]],[[1,2]]),1)\ncheck('missed all',solve([[1,2]], [[]]),0)\ncheck('empty',solve([],[]),0)\ncheck('no true labels',solve([[]],[ [1] ]),0)\ncheck('duplicates do not inflate',solve([[N,N]],[[N]]),1)\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":"0849b27f0eba96a34a645a662faacf9ff16e4977ab3fe101a558587f429723ed","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(truth, pred):\n    hits=sum(bool(set(a)&set(b)) for a,b in zip(truth,pred)); total=sum(len(a) for a in truth); return hits/total if total else 0\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('multiple labels',solve([[1,2,3],[4]],[[1,2],[4]]),.75)\ncheck('extra predicted ignored',solve([[1]],[[1,2]]),1)\ncheck('missed all',solve([[1,2]], [[]]),0)\ncheck('empty',solve([],[]),0)\ncheck('no true labels',solve([[]],[ [1] ]),0)\ncheck('duplicates do not inflate',solve([[N,N]],[[N]]),1)\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-micro","generated_at":"2026-09-30T16:48:30.810285+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":"The numerator is the number of examples with any hit instead of matching label instances.","sha256":"aaad5df355f16e2023b5e7ee334f2cd907685311e6696a2abea4d3f91bf33935","title":"Multilabel micro recall counts samples instead of 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":29.386,"exit_code":1,"observations":[{"actual":0.75,"check":"multiple labels","expected":0.75,"passed":true},{"actual":0.5,"check":"extra predicted ignored","expected":1,"passed":false},{"actual":0.0,"check":"missed all","expected":0,"passed":true},{"actual":0,"check":"empty","expected":0,"passed":true},{"actual":0.0,"check":"no true labels","expected":0,"passed":true},{"actual":1.0,"check":"duplicates do not inflate","expected":1,"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"multiple labels\", \"actual\": 0.75, \"expected\": 0.75, \"passed\": true}, {\"check\": \"extra predicted ignored\", \"actual\": 0.5, \"expected\": 1, \"passed\": false}, {\"check\": \"missed all\", \"actual\": 0.0, \"expected\": 0, \"passed\": true}, {\"check\": \"empty\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"no true labels\", \"actual\": 0.0, \"expected\": 0, \"passed\": true}, {\"check\": \"duplicates do not inflate\", \"actual\": 1.0, \"expected\": 1, \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":29.376,"exit_code":1,"observations":[{"actual":0.5,"check":"multiple labels","expected":0.75,"passed":false},{"actual":1.0,"check":"extra predicted ignored","expected":1,"passed":true},{"actual":0.0,"check":"missed all","expected":0,"passed":true},{"actual":0,"check":"empty","expected":0,"passed":true},{"actual":0,"check":"no true labels","expected":0,"passed":true},{"actual":0.5,"check":"duplicates do not inflate","expected":1,"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"multiple labels\", \"actual\": 0.5, \"expected\": 0.75, \"passed\": false}, {\"check\": \"extra predicted ignored\", \"actual\": 1.0, \"expected\": 1, \"passed\": true}, {\"check\": \"missed all\", \"actual\": 0.0, \"expected\": 0, \"passed\": true}, {\"check\": \"empty\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"no true labels\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"duplicates do not inflate\", \"actual\": 0.5, \"expected\": 1, \"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."}}