{"abstract":"Confusion counts omit false negatives.","category":"Evaluation metric aggregation","checks":6,"contract":"Return [TP,FP,FN,TN] for binary labels 0 and 1.","contract_signature":"truth, pred","evaluation_group":"w3-eval-confusion-counts","failed_approach":"Deriving false negatives as total minus true positives counts true negatives too.","family":"w3-evaluation-metric-aggregation-confusion-counts","id":"FA-99946","implementations":{"attempt":{"sha256":"a6b2082cf4429d1e6697235bfaaed472a2e8939d3be605015740c099a3130418","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(truth, pred):\n    tp=sum(a==1 and b==1 for a,b in zip(truth,pred)); fp=sum(a==0 and b==1 for a,b in zip(truth,pred)); tn=sum(a==0 and b==0 for a,b in zip(truth,pred)); return [tp,fp,len(truth)-tp,tn]\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('each cell',solve([1,1,0,0],[1,0,1,0]),[1,1,1,1])\ncheck('all positive',solve([1]*N,[1]*N),[N,0,0,0])\ncheck('all negative',solve([0]*N,[0]*N),[0,0,0,N])\ncheck('empty',solve([],[]),[0,0,0,0])\ncheck('missed positive',solve([1],[0]),[0,0,1,0])\ncheck('false alarm',solve([0],[1]),[0,1,0,0])\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":"462965cc548cecb777ba41de240d2514fed4b0fda914987ab695059fcce194ce","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(truth, pred):\n    tp=sum(a==1 and b==1 for a,b in zip(truth,pred)); fp=sum(a==0 and b==1 for a,b in zip(truth,pred)); tn=sum(a==0 and b==0 for a,b in zip(truth,pred)); return [tp,fp,0,tn]\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('each cell',solve([1,1,0,0],[1,0,1,0]),[1,1,1,1])\ncheck('all positive',solve([1]*N,[1]*N),[N,0,0,0])\ncheck('all negative',solve([0]*N,[0]*N),[0,0,0,N])\ncheck('empty',solve([],[]),[0,0,0,0])\ncheck('missed positive',solve([1],[0]),[0,0,1,0])\ncheck('false alarm',solve([0],[1]),[0,1,0,0])\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-confusion-counts","generated_at":"2026-09-30T16:48:29.887669+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":"Only predicted-positive rows are accumulated, so missed positives vanish.","sha256":"681eb7db0a22105e7749e239a4613bdcc30bae79250fab5063d13e04c00a0fed","title":"Confusion counts omit false negatives · 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":31.986,"exit_code":1,"observations":[{"actual":[1,1,3,1],"check":"each cell","expected":[1,1,1,1],"passed":false},{"actual":[1,0,0,0],"check":"all positive","expected":[1,0,0,0],"passed":true},{"actual":[0,0,1,1],"check":"all negative","expected":[0,0,0,1],"passed":false},{"actual":[0,0,0,0],"check":"empty","expected":[0,0,0,0],"passed":true},{"actual":[0,0,1,0],"check":"missed positive","expected":[0,0,1,0],"passed":true},{"actual":[0,1,1,0],"check":"false alarm","expected":[0,1,0,0],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"each cell\", \"actual\": [1, 1, 3, 1], \"expected\": [1, 1, 1, 1], \"passed\": false}, {\"check\": \"all positive\", \"actual\": [1, 0, 0, 0], \"expected\": [1, 0, 0, 0], \"passed\": true}, {\"check\": \"all negative\", \"actual\": [0, 0, 1, 1], \"expected\": [0, 0, 0, 1], \"passed\": false}, {\"check\": \"empty\", \"actual\": [0, 0, 0, 0], \"expected\": [0, 0, 0, 0], \"passed\": true}, {\"check\": \"missed positive\", \"actual\": [0, 0, 1, 0], \"expected\": [0, 0, 1, 0], \"passed\": true}, {\"check\": \"false alarm\", \"actual\": [0, 1, 1, 0], \"expected\": [0, 1, 0, 0], \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":30.246,"exit_code":1,"observations":[{"actual":[1,1,0,1],"check":"each cell","expected":[1,1,1,1],"passed":false},{"actual":[1,0,0,0],"check":"all positive","expected":[1,0,0,0],"passed":true},{"actual":[0,0,0,1],"check":"all negative","expected":[0,0,0,1],"passed":true},{"actual":[0,0,0,0],"check":"empty","expected":[0,0,0,0],"passed":true},{"actual":[0,0,0,0],"check":"missed positive","expected":[0,0,1,0],"passed":false},{"actual":[0,1,0,0],"check":"false alarm","expected":[0,1,0,0],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"each cell\", \"actual\": [1, 1, 0, 1], \"expected\": [1, 1, 1, 1], \"passed\": false}, {\"check\": \"all positive\", \"actual\": [1, 0, 0, 0], \"expected\": [1, 0, 0, 0], \"passed\": true}, {\"check\": \"all negative\", \"actual\": [0, 0, 0, 1], \"expected\": [0, 0, 0, 1], \"passed\": true}, {\"check\": \"empty\", \"actual\": [0, 0, 0, 0], \"expected\": [0, 0, 0, 0], \"passed\": true}, {\"check\": \"missed positive\", \"actual\": [0, 0, 0, 0], \"expected\": [0, 0, 1, 0], \"passed\": false}, {\"check\": \"false alarm\", \"actual\": [0, 1, 0, 0], \"expected\": [0, 1, 0, 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."}}