{"abstract":"Ignored examples remain in the supervised loss mask.","category":"Training label alignment","checks":7,"contract":"Given labels and ignore_id, return 1 for trainable positions and 0 exactly where label equals ignore_id.","contract_signature":"labels, ignore_id","evaluation_group":"training-label-alignment-sentinel-loss-mask","failed_approach":"Treating every zero-valued label as ignored also suppresses a valid class zero.","family":"w3-training-label-alignment-ignored-label-mask","id":"FA-97986","implementations":{"attempt":{"sha256":"f5dbe196f5c32c51cb57b59e824f4f1e279e5aa93f67d78e40d8c4abc5e70d68","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(labels, ignore_id):\n    return [int(bool(y) and y!=ignore_id) for y in labels]\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('sentinel masked',solve([N,-100,0],-100),[1,0,1])\ncheck('zero is class',solve([0,1],-1),[1,1])\ncheck('all ignored',solve([-1,-1],-1),[0,0])\ncheck('empty labels',solve([],-1),[])\ncheck('single ignored',solve([N],N),[0])\ncheck('sentinel at end',solve([0,0,N],N),[1,1,0])\ncheck('valid negative class',solve([-2,-1],-1),[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":"48319526e55d940455d2802f4f7b63141f5086a12d58909bfe6882377685260c","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(labels, ignore_id):\n    return [1]*len(labels)\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('sentinel masked',solve([N,-100,0],-100),[1,0,1])\ncheck('zero is class',solve([0,1],-1),[1,1])\ncheck('all ignored',solve([-1,-1],-1),[0,0])\ncheck('empty labels',solve([],-1),[])\ncheck('single ignored',solve([N],N),[0])\ncheck('sentinel at end',solve([0,0,N],N),[1,1,0])\ncheck('valid negative class',solve([-2,-1],-1),[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":"Labels and ignore_id are scalar values with equality semantics. 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-training-label-alignment-ignored-label-mask","generated_at":"2026-09-30T16:48:07.976744+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"A small deterministic training-data operation makes label ownership and ordering explicit.","root_cause":"The mask is derived from example presence rather than the sentinel label value.","sha256":"f7f5e8a4ec1c9386611e1d3a20d86a0f539b71dddc949857191146f9e2a609e8","title":"Ignored examples remain in the supervised loss mask · 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":27.071,"exit_code":1,"observations":[{"actual":[1,0,0],"check":"sentinel masked","expected":[1,0,1],"passed":false},{"actual":[0,1],"check":"zero is class","expected":[1,1],"passed":false},{"actual":[0,0],"check":"all ignored","expected":[0,0],"passed":true},{"actual":[],"check":"empty labels","expected":[],"passed":true},{"actual":[0],"check":"single ignored","expected":[0],"passed":true},{"actual":[0,0,0],"check":"sentinel at end","expected":[1,1,0],"passed":false},{"actual":[1,0],"check":"valid negative class","expected":[1,0],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"sentinel masked\", \"actual\": [1, 0, 0], \"expected\": [1, 0, 1], \"passed\": false}, {\"check\": \"zero is class\", \"actual\": [0, 1], \"expected\": [1, 1], \"passed\": false}, {\"check\": \"all ignored\", \"actual\": [0, 0], \"expected\": [0, 0], \"passed\": true}, {\"check\": \"empty labels\", \"actual\": [], \"expected\": [], \"passed\": true}, {\"check\": \"single ignored\", \"actual\": [0], \"expected\": [0], \"passed\": true}, {\"check\": \"sentinel at end\", \"actual\": [0, 0, 0], \"expected\": [1, 1, 0], \"passed\": false}, {\"check\": \"valid negative class\", \"actual\": [1, 0], \"expected\": [1, 0], \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":24.762,"exit_code":1,"observations":[{"actual":[1,1,1],"check":"sentinel masked","expected":[1,0,1],"passed":false},{"actual":[1,1],"check":"zero is class","expected":[1,1],"passed":true},{"actual":[1,1],"check":"all ignored","expected":[0,0],"passed":false},{"actual":[],"check":"empty labels","expected":[],"passed":true},{"actual":[1],"check":"single ignored","expected":[0],"passed":false},{"actual":[1,1,1],"check":"sentinel at end","expected":[1,1,0],"passed":false},{"actual":[1,1],"check":"valid negative class","expected":[1,0],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"sentinel masked\", \"actual\": [1, 1, 1], \"expected\": [1, 0, 1], \"passed\": false}, {\"check\": \"zero is class\", \"actual\": [1, 1], \"expected\": [1, 1], \"passed\": true}, {\"check\": \"all ignored\", \"actual\": [1, 1], \"expected\": [0, 0], \"passed\": false}, {\"check\": \"empty labels\", \"actual\": [], \"expected\": [], \"passed\": true}, {\"check\": \"single ignored\", \"actual\": [1], \"expected\": [0], \"passed\": false}, {\"check\": \"sentinel at end\", \"actual\": [1, 1, 1], \"expected\": [1, 1, 0], \"passed\": false}, {\"check\": \"valid negative class\", \"actual\": [1, 1], \"expected\": [1, 0], \"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."}}