{"abstract":"Unicode word characters alter ASCII identifier boundaries.","category":"Regular expressions","checks":4,"contract":"Extract ASCII word runs using ASCII word and boundary semantics.","evaluation_group":"model-4e8d9d4eebede65a","failed_approach":"The attempted repair handles the primary example but still violates a separate boundary of the same contract.","family":"xp-regex-ascii-boundary","id":"FA-3111","implementations":{"attempt":{"sha256":"d3ab1d8b251a3754c452177ed8136958275cd8fee0c0ce6cfdc9fa8010de523d","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 re.findall(r'\\w+',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'), ['abc'])\ncheck('boundary 2', solve('a_b'), ['a_b'])\ncheck('boundary 3', solve('中42'), ['42'])\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":"8d6e1fc69a85eb1a6b40ba16eab4ea6df192fb9f842ef0176e4dd8ee69294fb2","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 re.findall(r'\\b[A-Za-z0-9_]+\\b',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'), ['abc'])\ncheck('boundary 2', solve('a_b'), ['a_b'])\ncheck('boundary 3', solve('中42'), ['42'])\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"},"fixed":{"sha256":"01fac8869c26587a063b141dc48d4c4bbd281bb4eb0b2746ed98a46e7f213cb6","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 re.findall(r'\\b\\w+\\b',x,re.ASCII)\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'), ['abc'])\ncheck('boundary 2', solve('a_b'), ['a_b'])\ncheck('boundary 3', solve('中42'), ['42'])\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-regex-ascii-boundary","generated_at":"2026-09-29T14:37:21.626172+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.","repair":"Implement the complete stated contract, including the boundary fixtures: Extract ASCII word runs using ASCII word and boundary semantics.","root_cause":"The implementation applies an operation whose text or grammar semantics violate this contract: Extract ASCII word runs using ASCII word and boundary semantics.","sha256":"28fffd922cc847eb1c92d8c9dc1dfe77bbec01d7768f7db594f0af95782c200f","title":"Unicode word characters alter ASCII identifier boundaries · case 01","variant":1,"variant_policy":"Five numbered records share a model and may reuse boundary fixtures.","verification":{"attempt":{"elapsed_ms":54.012,"exit_code":1,"observations":[{"actual":["éabc"],"check":"boundary 1","expected":["abc"],"passed":false},{"actual":["a_b"],"check":"boundary 2","expected":["a_b"],"passed":true},{"actual":["中42"],"check":"boundary 3","expected":["42"],"passed":false},{"actual":[],"check":"boundary 4","expected":[],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [\"éabc\"], \"expected\": [\"abc\"], \"passed\": false}, {\"check\": \"boundary 2\", \"actual\": [\"a_b\"], \"expected\": [\"a_b\"], \"passed\": true}, {\"check\": \"boundary 3\", \"actual\": [\"中42\"], \"expected\": [\"42\"], \"passed\": false}, {\"check\": \"boundary 4\", \"actual\": [], \"expected\": [], \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":56.249,"exit_code":1,"observations":[{"actual":[],"check":"boundary 1","expected":["abc"],"passed":false},{"actual":["a_b"],"check":"boundary 2","expected":["a_b"],"passed":true},{"actual":[],"check":"boundary 3","expected":["42"],"passed":false},{"actual":[],"check":"boundary 4","expected":[],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [], \"expected\": [\"abc\"], \"passed\": false}, {\"check\": \"boundary 2\", \"actual\": [\"a_b\"], \"expected\": [\"a_b\"], \"passed\": true}, {\"check\": \"boundary 3\", \"actual\": [], \"expected\": [\"42\"], \"passed\": false}, {\"check\": \"boundary 4\", \"actual\": [], \"expected\": [], \"passed\": true}], \"passed\": false}\n"},"fixed":{"elapsed_ms":59.22,"exit_code":0,"observations":[{"actual":["abc"],"check":"boundary 1","expected":["abc"],"passed":true},{"actual":["a_b"],"check":"boundary 2","expected":["a_b"],"passed":true},{"actual":["42"],"check":"boundary 3","expected":["42"],"passed":true},{"actual":[],"check":"boundary 4","expected":[],"passed":true}],"passed":true,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [\"abc\"], \"expected\": [\"abc\"], \"passed\": true}, {\"check\": \"boundary 2\", \"actual\": [\"a_b\"], \"expected\": [\"a_b\"], \"passed\": true}, {\"check\": \"boundary 3\", \"actual\": [\"42\"], \"expected\": [\"42\"], \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": [], \"expected\": [], \"passed\": true}], \"passed\": true}\n"}},"verified":true,"visibility":"public"}