{"abstract":"Character offsets are reported as UTF-8 byte offsets.","category":"Tokenization","checks":4,"contract":"Return UTF-8 byte start offsets of every ASCII letter run.","contract_signature":"x","evaluation_group":"model-18b914324f2f16f0","failed_approach":"The attempted repair handles the primary example but still violates a separate boundary of the same contract.","family":"xp-token-byte-offset","id":"FA-3776","implementations":{"attempt":{"sha256":"ade5925db26077035cf9cdd57efcff8151e135b6d090e4458198d04cf140b3ae","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\nimport re, unicodedata, json, csv, io, html, base64, binascii, codecs, struct\nfrom urllib.parse import quote, unquote, unquote_to_bytes, urlencode, parse_qsl, urlsplit, urlunsplit\nfrom email.header import decode_header, make_header\nfrom email.utils import getaddresses\nfrom xml.etree import ElementTree as ET\nimport shlex, string, textwrap\n\nN = 1\nobservations = []\ndef solve(x):\n    try:\n        return [len(x[:m.start()].encode('utf-16-le')) for m in re.finditer('[A-Za-z]+',x)]\n    except Exception as exc:\n        return {\"error\": type(exc).__name__}\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('boundary 1', solve('éabc'), [2])\ncheck('boundary 2', solve('😀 x'), [5])\ncheck('boundary 3', solve('a b'), [0, 2])\ncheck('boundary 4', solve(''), [])\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":"fe52a85943ef3048d35b0bb7a0a186a128c58f8cd4090e4b84547adbf73b06ce","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\nimport re, unicodedata, json, csv, io, html, base64, binascii, codecs, struct\nfrom urllib.parse import quote, unquote, unquote_to_bytes, urlencode, parse_qsl, urlsplit, urlunsplit\nfrom email.header import decode_header, make_header\nfrom email.utils import getaddresses\nfrom xml.etree import ElementTree as ET\nimport shlex, string, textwrap\n\nN = 1\nobservations = []\ndef solve(x):\n    try:\n        return [m.start() for m in re.finditer('[A-Za-z]+',x)]\n    except Exception as exc:\n        return {\"error\": type(exc).__name__}\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('boundary 1', solve('éabc'), [2])\ncheck('boundary 2', solve('😀 x'), [5])\ncheck('boundary 3', solve('a b'), [0, 2])\ncheck('boundary 4', solve(''), [])\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":" 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":"xp-token-byte-offset","generated_at":"2026-09-29T14:37:30.667880+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"A local executable model for consumers of structured text; oracle values are authored literals, not outputs copied from the repaired implementation.","root_cause":"The implementation applies an operation whose text or grammar semantics violate this contract: Return UTF-8 byte start offsets of every ASCII letter run.","sha256":"4412e6e746e191508194598026bfa26dfbf2ba79497c2ab14e4e850a6025b590","title":"Character offsets are reported as UTF-8 byte offsets · case 01","variant":1,"variant_policy":"Five numbered records share a model and may reuse boundary fixtures.","verified":true,"visibility":"public","verification":{"attempt":{"elapsed_ms":59.653,"exit_code":1,"observations":[{"actual":[2],"check":"boundary 1","expected":[2],"passed":true},{"actual":[6],"check":"boundary 2","expected":[5],"passed":false},{"actual":[0,4],"check":"boundary 3","expected":[0,2],"passed":false},{"actual":[],"check":"boundary 4","expected":[],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [2], \"expected\": [2], \"passed\": true}, {\"check\": \"boundary 2\", \"actual\": [6], \"expected\": [5], \"passed\": false}, {\"check\": \"boundary 3\", \"actual\": [0, 4], \"expected\": [0, 2], \"passed\": false}, {\"check\": \"boundary 4\", \"actual\": [], \"expected\": [], \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":53.159,"exit_code":1,"observations":[{"actual":[1],"check":"boundary 1","expected":[2],"passed":false},{"actual":[2],"check":"boundary 2","expected":[5],"passed":false},{"actual":[0,2],"check":"boundary 3","expected":[0,2],"passed":true},{"actual":[],"check":"boundary 4","expected":[],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [1], \"expected\": [2], \"passed\": false}, {\"check\": \"boundary 2\", \"actual\": [2], \"expected\": [5], \"passed\": false}, {\"check\": \"boundary 3\", \"actual\": [0, 2], \"expected\": [0, 2], \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": [], \"expected\": [], \"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."}}