{"abstract":"Invalid UTF-8 bytes silently disappear.","category":"Encodings","checks":4,"contract":"Decode UTF-8 using one standard replacement sequence per decoding error.","evaluation_group":"model-53ba98a56989ea1f","failed_approach":"The attempted repair handles the primary example but still violates a separate boundary of the same contract.","family":"xp-utf8-replacement","id":"FA-2961","implementations":{"attempt":{"sha256":"4c5083ce59e3cf8046cb159a55d8c683717dbda53b3826b562ff04fbb51e1cf9","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 bytes.fromhex(x).decode('latin1')\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('61ff62'), 'a�b')\ncheck('boundary 2', solve('e282'), '�')\ncheck('boundary 3', solve('f09f9880'), '😀')\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":"356364cfa1c0ea9409bc8d946309bd3f078048ddb96a3b9a6e75eec6139cf0a6","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 bytes.fromhex(x).decode('utf-8','ignore')\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('61ff62'), 'a�b')\ncheck('boundary 2', solve('e282'), '�')\ncheck('boundary 3', solve('f09f9880'), '😀')\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":"13cba4421fef998874aeac31168f551c8834f195f66537dd7cd9c9789d550adb","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 bytes.fromhex(x).decode('utf-8','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('61ff62'), 'a�b')\ncheck('boundary 2', solve('e282'), '�')\ncheck('boundary 3', solve('f09f9880'), '😀')\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-utf8-replacement","generated_at":"2026-09-29T14:37:19.511211+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: Decode UTF-8 using one standard replacement sequence per decoding error.","root_cause":"The implementation applies an operation whose text or grammar semantics violate this contract: Decode UTF-8 using one standard replacement sequence per decoding error.","sha256":"e47c64f7487051a014eda6247ee6dd8258c42c71443557422c8fec04d08fa8cd","title":"Invalid UTF-8 bytes silently disappear · case 01","variant":1,"variant_policy":"Five numbered records share a model and may reuse boundary fixtures.","verification":{"attempt":{"elapsed_ms":108.312,"exit_code":1,"observations":[{"actual":"aÿb","check":"boundary 1","expected":"a�b","passed":false},{"actual":"â‚","check":"boundary 2","expected":"�","passed":false},{"actual":"😀","check":"boundary 3","expected":"😀","passed":false},{"actual":"","check":"boundary 4","expected":"","passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": \"aÿb\", \"expected\": \"a�b\", \"passed\": false}, {\"check\": \"boundary 2\", \"actual\": \"â‚\", \"expected\": \"�\", \"passed\": false}, {\"check\": \"boundary 3\", \"actual\": \"😀\", \"expected\": \"😀\", \"passed\": false}, {\"check\": \"boundary 4\", \"actual\": \"\", \"expected\": \"\", \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":52.961,"exit_code":1,"observations":[{"actual":"ab","check":"boundary 1","expected":"a�b","passed":false},{"actual":"","check":"boundary 2","expected":"�","passed":false},{"actual":"😀","check":"boundary 3","expected":"😀","passed":true},{"actual":"","check":"boundary 4","expected":"","passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"boundary 1\", \"actual\": \"ab\", \"expected\": \"a�b\", \"passed\": false}, {\"check\": \"boundary 2\", \"actual\": \"\", \"expected\": \"�\", \"passed\": false}, {\"check\": \"boundary 3\", \"actual\": \"😀\", \"expected\": \"😀\", \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": \"\", \"expected\": \"\", \"passed\": true}], \"passed\": false}\n"},"fixed":{"elapsed_ms":48.523,"exit_code":0,"observations":[{"actual":"a�b","check":"boundary 1","expected":"a�b","passed":true},{"actual":"�","check":"boundary 2","expected":"�","passed":true},{"actual":"😀","check":"boundary 3","expected":"😀","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\": \"�\", \"expected\": \"�\", \"passed\": true}, {\"check\": \"boundary 3\", \"actual\": \"😀\", \"expected\": \"😀\", \"passed\": true}, {\"check\": \"boundary 4\", \"actual\": \"\", \"expected\": \"\", \"passed\": true}], \"passed\": true}\n"}},"verified":true,"visibility":"public"}