{"abstract":"Acceptance count includes tokens after the first mismatch.","category":"Speculative decoding bookkeeping","checks":7,"contract":"Given equal-length draft and verified token lists, return the length of their common prefix.","contract_signature":"draft, verified","evaluation_group":"spec-accepted-prefix-length","failed_approach":"Comparing only the first token fixes immediate rejection but misses later mismatch positions.","family":"w3-speculative-decoding-bookkeeping-accepted-prefix-length","id":"FA-100641","implementations":{"attempt":{"sha256":"a58d771fc1acfe6ab6ce0acc4048b0cba0f6b775fefca3018b43d2e3cfd0e456","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(draft, verified):\n    return int(bool(draft) and bool(verified) and draft[0] == verified[0])\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('full match', solve([1,2,N],[1,2,N]),3)\ncheck('middle rejection', solve([1,2,3],[1,9,3]),1)\ncheck('first rejection', solve([1],[2]),0)\ncheck('empty draft', solve([],[]),0)\ncheck('short verified', solve([1,2],[1]),1)\ncheck('empty verified', solve([1],[]),0)\ncheck('single match', solve([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":"bc99fb29ea61f6b43fa88f93e5fc932ee8e87b3da3d2aa7b7c07a20a27e22acd","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(draft, verified):\n    return sum(a == b for a,b in zip(draft,verified))\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('full match', solve([1,2,N],[1,2,N]),3)\ncheck('middle rejection', solve([1,2,3],[1,9,3]),1)\ncheck('first rejection', solve([1],[2]),0)\ncheck('empty draft', solve([],[]),0)\ncheck('short verified', solve([1,2],[1]),1)\ncheck('empty verified', solve([1],[]),0)\ncheck('single match', solve([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":"These are finite toy sequences with explicit contracts; they make no claim about production decoder behavior or model quality. 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-speculative-decoding-bookkeeping-accepted-prefix-length","generated_at":"2026-09-30T16:48:38.067804+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"A self-contained bookkeeping model makes prefix and token-count semantics observable without a model runtime.","root_cause":"The count uses total equal positions rather than stopping at the first rejection.","sha256":"1e78447a6808f73bc14b339a481a573cda8505b390b3ad4ff62d43866396b713","title":"Decoding: Acceptance count includes tokens after the first mismatch · 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":28.97,"exit_code":1,"observations":[{"actual":1,"check":"full match","expected":3,"passed":false},{"actual":1,"check":"middle rejection","expected":1,"passed":true},{"actual":0,"check":"first rejection","expected":0,"passed":true},{"actual":0,"check":"empty draft","expected":0,"passed":true},{"actual":1,"check":"short verified","expected":1,"passed":true},{"actual":0,"check":"empty verified","expected":0,"passed":true},{"actual":1,"check":"single match","expected":1,"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"full match\", \"actual\": 1, \"expected\": 3, \"passed\": false}, {\"check\": \"middle rejection\", \"actual\": 1, \"expected\": 1, \"passed\": true}, {\"check\": \"first rejection\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"empty draft\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"short verified\", \"actual\": 1, \"expected\": 1, \"passed\": true}, {\"check\": \"empty verified\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"single match\", \"actual\": 1, \"expected\": 1, \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":28.597,"exit_code":1,"observations":[{"actual":3,"check":"full match","expected":3,"passed":true},{"actual":2,"check":"middle rejection","expected":1,"passed":false},{"actual":0,"check":"first rejection","expected":0,"passed":true},{"actual":0,"check":"empty draft","expected":0,"passed":true},{"actual":1,"check":"short verified","expected":1,"passed":true},{"actual":0,"check":"empty verified","expected":0,"passed":true},{"actual":1,"check":"single match","expected":1,"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"full match\", \"actual\": 3, \"expected\": 3, \"passed\": true}, {\"check\": \"middle rejection\", \"actual\": 2, \"expected\": 1, \"passed\": false}, {\"check\": \"first rejection\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"empty draft\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"short verified\", \"actual\": 1, \"expected\": 1, \"passed\": true}, {\"check\": \"empty verified\", \"actual\": 0, \"expected\": 0, \"passed\": true}, {\"check\": \"single match\", \"actual\": 1, \"expected\": 1, \"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."}}