{"abstract":"Long sequences dominate a sequence-mean objective.","category":"Gradient accumulation weighting","checks":7,"contract":"Compute each nonempty sequence mean and then average sequences equally; sequences with zero tokens are skipped.","contract_signature":"sequence_sums, token_counts","evaluation_group":"gradient-accumulation-sequence_equal","failed_approach":"Dividing each sequence mean by the number of sequences loses the empty-sequence boundary.","family":"w3-gradient-accumulation-weighting-sequence-equal","id":"FA-98871","implementations":{"attempt":{"sha256":"14813ad8c4b6e41f87861ea6bd5f3c7578bcf2d2c554acf4ba32214d51a9f1de","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(sequence_sums, token_counts):\n    return sum(s / c for s,c in zip(sequence_sums,token_counts) if c) / max(1,len(sequence_sums))\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('different lengths',solve([2*N,12*N],[N,3*N]),3)\ncheck('same lengths',solve([2*N,4*N],[N,N]),3)\ncheck('single sequence',solve([6*N],[2*N]),3)\ncheck('empty',solve([],[]),0)\ncheck('empty sequence',solve([0,8*N],[0,2*N]),4)\ncheck('zero objective',solve([0,9*N],[N,3*N]),1.5)\ncheck('three means',solve([N,6*N,8*N],[1,2,4]),2*N)\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":"0f089282c3172b86666d196e63f059cc8144e4e772db903abecabdbfaaaa2d46","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(sequence_sums, token_counts):\n    return sum(sequence_sums) / sum(token_counts) if sum(token_counts) else 0\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('different lengths',solve([2*N,12*N],[N,3*N]),3)\ncheck('same lengths',solve([2*N,4*N],[N,N]),3)\ncheck('single sequence',solve([6*N],[2*N]),3)\ncheck('empty',solve([],[]),0)\ncheck('empty sequence',solve([0,8*N],[0,2*N]),4)\ncheck('zero objective',solve([0,9*N],[N,3*N]),1.5)\ncheck('three means',solve([N,6*N,8*N],[1,2,4]),2*N)\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 scalar or short-list summaries and do not model autodiff, devices, or an optimizer. 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-gradient-accumulation-weighting-sequence-equal","generated_at":"2026-09-30T16:48:17.605394+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"A deterministic toy model isolates one local accumulation contract.","root_cause":"The broken path pools token sums and counts, weighting longer sequences more heavily.","sha256":"1be406497d2d6d692fc9750afba0831321675ec30540dc23fd8c89ae4d119339","title":"Long sequences dominate a sequence-mean objective · 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":26.089,"exit_code":1,"observations":[{"actual":3.0,"check":"different lengths","expected":3,"passed":true},{"actual":3.0,"check":"same lengths","expected":3,"passed":true},{"actual":3.0,"check":"single sequence","expected":3,"passed":true},{"actual":0.0,"check":"empty","expected":0,"passed":true},{"actual":2.0,"check":"empty sequence","expected":4,"passed":false},{"actual":1.5,"check":"zero objective","expected":1.5,"passed":true},{"actual":2.0,"check":"three means","expected":2,"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"different lengths\", \"actual\": 3.0, \"expected\": 3, \"passed\": true}, {\"check\": \"same lengths\", \"actual\": 3.0, \"expected\": 3, \"passed\": true}, {\"check\": \"single sequence\", \"actual\": 3.0, \"expected\": 3, \"passed\": true}, {\"check\": \"empty\", \"actual\": 0.0, \"expected\": 0, \"passed\": true}, {\"check\": \"empty sequence\", \"actual\": 2.0, \"expected\": 4, \"passed\": false}, {\"check\": \"zero objective\", \"actual\": 1.5, \"expected\": 1.5, \"passed\": true}, {\"check\": \"three means\", \"actual\": 2.0, \"expected\": 2, \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":27.634,"exit_code":1,"observations":[{"actual":3.5,"check":"different lengths","expected":3,"passed":false},{"actual":3.0,"check":"same lengths","expected":3,"passed":true},{"actual":3.0,"check":"single sequence","expected":3,"passed":true},{"actual":0,"check":"empty","expected":0,"passed":true},{"actual":4.0,"check":"empty sequence","expected":4,"passed":true},{"actual":2.25,"check":"zero objective","expected":1.5,"passed":false},{"actual":2.142857142857143,"check":"three means","expected":2,"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"different lengths\", \"actual\": 3.5, \"expected\": 3, \"passed\": false}, {\"check\": \"same lengths\", \"actual\": 3.0, \"expected\": 3, \"passed\": true}, {\"check\": \"single sequence\", \"actual\": 3.0, \"expected\": 3, \"passed\": true}, {\"check\": \"empty\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"empty sequence\", \"actual\": 4.0, \"expected\": 4, \"passed\": true}, {\"check\": \"zero objective\", \"actual\": 2.25, \"expected\": 1.5, \"passed\": false}, {\"check\": \"three means\", \"actual\": 2.142857142857143, \"expected\": 2, \"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."}}