{"abstract":"Whitespace removal shifts token source offsets.","category":"Tokenization","checks":4,"contract":"Return start/end offsets of ASCII word runs in the original text.","contract_signature":"x","evaluation_group":"model-075a1362ddc6b45c","failed_approach":"The attempted repair handles the primary example but still violates a separate boundary of the same contract.","family":"xp-token-offset-original","id":"FA-3771","implementations":{"attempt":{"sha256":"0d7684a42af3f1aa78c57919013c7c06d84cbb93d399bce03d56231778110de7","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(),m.end()] for m in re.finditer('[A-Za-z]+',x.strip())]\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('  ab cd'), [[2, 4], [5, 7]])\ncheck('boundary 2', solve('a  b'), [[0, 1], [3, 4]])\ncheck('boundary 3', solve(''), [])\ncheck('boundary 4', solve('\\nx'), [[1, 2]])\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":"0058c8ea64b2b40ba3417a9ffbad1ab7678c2625978d62b502c4b9c4b4afe1ce","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(),m.end()] for m in re.finditer('[A-Za-z]+',x.replace(' ',''))]\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('  ab cd'), [[2, 4], [5, 7]])\ncheck('boundary 2', solve('a  b'), [[0, 1], [3, 4]])\ncheck('boundary 3', solve(''), [])\ncheck('boundary 4', solve('\\nx'), [[1, 2]])\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-offset-original","generated_at":"2026-09-29T14:37:30.443548+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 start/end offsets of ASCII word runs in the original text.","sha256":"42ad0f5751b4221f35ceaf9c7ed2fbbc3ae87daa377af35327b92d81f8e7303d","title":"Whitespace removal shifts token source 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":46.066,"exit_code":1,"observations":[{"actual":[[0,2],[3,5]],"check":"boundary 1","expected":[[2,4],[5,7]],"passed":false},{"actual":[[0,1],[3,4]],"check":"boundary 2","expected":[[0,1],[3,4]],"passed":true},{"actual":[],"check":"boundary 3","expected":[],"passed":true},{"actual":[[0,1]],"check":"boundary 4","expected":[[1,2]],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [[0, 2], [3, 5]], \"expected\": [[2, 4], [5, 7]], \"passed\": false}, {\"check\": \"boundary 2\", \"actual\": [[0, 1], [3, 4]], \"expected\": [[0, 1], [3, 4]], \"passed\": true}, {\"check\": \"boundary 3\", \"actual\": [], \"expected\": [], \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": [[0, 1]], \"expected\": [[1, 2]], \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":57.233,"exit_code":1,"observations":[{"actual":[[0,4]],"check":"boundary 1","expected":[[2,4],[5,7]],"passed":false},{"actual":[[0,2]],"check":"boundary 2","expected":[[0,1],[3,4]],"passed":false},{"actual":[],"check":"boundary 3","expected":[],"passed":true},{"actual":[[1,2]],"check":"boundary 4","expected":[[1,2]],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [[0, 4]], \"expected\": [[2, 4], [5, 7]], \"passed\": false}, {\"check\": \"boundary 2\", \"actual\": [[0, 2]], \"expected\": [[0, 1], [3, 4]], \"passed\": false}, {\"check\": \"boundary 3\", \"actual\": [], \"expected\": [], \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": [[1, 2]], \"expected\": [[1, 2]], \"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."}}