{"abstract":"Tokenization drops punctuation needed by the parser.","category":"Tokenization","checks":4,"contract":"Split into ASCII word runs or individual nonspace punctuation tokens.","evaluation_group":"model-d093b3e452ab8d1e","failed_approach":"The attempted repair handles the primary example but still violates a separate boundary of the same contract.","family":"xp-split-keep-delimiters","id":"FA-3886","implementations":{"attempt":{"sha256":"3dacd0ae8722fdae038f6ce0354d08019938ebc0ef751538647336bc3bc4d72e","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'[A-Za-z]+|[^\\w\\s]+',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('a+b'), ['a', '+', 'b'])\ncheck('boundary 2', solve('a<=b'), ['a', '<', '=', 'b'])\ncheck('boundary 3', solve('abc'), ['abc'])\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":"ebd41e43dfbc3973d071646458524337baf9ab1090fcb8ef7f76e11a9207f653","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('a+b'), ['a', '+', 'b'])\ncheck('boundary 2', solve('a<=b'), ['a', '<', '=', 'b'])\ncheck('boundary 3', solve('abc'), ['abc'])\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":"61e469912b7f7289cc2e253e2e0d3d5eb629816c73316c60f02c948f0451b644","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'[A-Za-z]+|[^A-Za-z\\s]',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('a+b'), ['a', '+', 'b'])\ncheck('boundary 2', solve('a<=b'), ['a', '<', '=', 'b'])\ncheck('boundary 3', solve('abc'), ['abc'])\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-split-keep-delimiters","generated_at":"2026-09-29T14:37:32.364777+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: Split into ASCII word runs or individual nonspace punctuation tokens.","root_cause":"The implementation applies an operation whose text or grammar semantics violate this contract: Split into ASCII word runs or individual nonspace punctuation tokens.","sha256":"153d54a2a7c1696e6acb9931b54bf5687bcbcfaa38cdac48759cadb10455b443","title":"Tokenization drops punctuation needed by the parser · case 01","variant":1,"variant_policy":"Five numbered records share a model and may reuse boundary fixtures.","verification":{"attempt":{"elapsed_ms":59.678,"exit_code":1,"observations":[{"actual":["a","+","b"],"check":"boundary 1","expected":["a","+","b"],"passed":true},{"actual":["a","<=","b"],"check":"boundary 2","expected":["a","<","=","b"],"passed":false},{"actual":["abc"],"check":"boundary 3","expected":["abc"],"passed":true},{"actual":[],"check":"boundary 4","expected":[],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [\"a\", \"+\", \"b\"], \"expected\": [\"a\", \"+\", \"b\"], \"passed\": true}, {\"check\": \"boundary 2\", \"actual\": [\"a\", \"<=\", \"b\"], \"expected\": [\"a\", \"<\", \"=\", \"b\"], \"passed\": false}, {\"check\": \"boundary 3\", \"actual\": [\"abc\"], \"expected\": [\"abc\"], \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": [], \"expected\": [], \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":59.2,"exit_code":1,"observations":[{"actual":["a","b"],"check":"boundary 1","expected":["a","+","b"],"passed":false},{"actual":["a","b"],"check":"boundary 2","expected":["a","<","=","b"],"passed":false},{"actual":["abc"],"check":"boundary 3","expected":["abc"],"passed":true},{"actual":[],"check":"boundary 4","expected":[],"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [\"a\", \"b\"], \"expected\": [\"a\", \"+\", \"b\"], \"passed\": false}, {\"check\": \"boundary 2\", \"actual\": [\"a\", \"b\"], \"expected\": [\"a\", \"<\", \"=\", \"b\"], \"passed\": false}, {\"check\": \"boundary 3\", \"actual\": [\"abc\"], \"expected\": [\"abc\"], \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": [], \"expected\": [], \"passed\": true}], \"passed\": false}\n"},"fixed":{"elapsed_ms":61.799,"exit_code":0,"observations":[{"actual":["a","+","b"],"check":"boundary 1","expected":["a","+","b"],"passed":true},{"actual":["a","<","=","b"],"check":"boundary 2","expected":["a","<","=","b"],"passed":true},{"actual":["abc"],"check":"boundary 3","expected":["abc"],"passed":true},{"actual":[],"check":"boundary 4","expected":[],"passed":true}],"passed":true,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": [\"a\", \"+\", \"b\"], \"expected\": [\"a\", \"+\", \"b\"], \"passed\": true}, {\"check\": \"boundary 2\", \"actual\": [\"a\", \"<\", \"=\", \"b\"], \"expected\": [\"a\", \"<\", \"=\", \"b\"], \"passed\": true}, {\"check\": \"boundary 3\", \"actual\": [\"abc\"], \"expected\": [\"abc\"], \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": [], \"expected\": [], \"passed\": true}], \"passed\": true}\n"}},"verified":true,"visibility":"public"}