{
  "title": "Binary byte identity casebook",
  "version": "1.0.0",
  "publishedDate": "2026-10-15",
  "canonicalOwner": "binarytranslator.dev",
  "implementation": {
    "commit": "dfd9459db521ad3eab5f8b25afd81b67ab224930",
    "sourceSha256": "5ae5c4b21520e62a6338fa42454be6666698d7e11fdfa72040790ef58ab40b74"
  },
  "selection": "20 explicitly selected scalar-value text cases and 16 selected byte sequences; constructed coverage examples, not random sampling.",
  "procedure": [
    "Encode text cases with the actual site encodeText function and compare with explicit bytes.",
    "Feed every byte case to actual decodeBinary in strict 8-bit grouping.",
    "Record strict UTF-8 validity separately from the site output and notices.",
    "Re-encode the returned text and compare the exact byte sequence.",
    "Independently validate every row using Python standard-library codecs; UTF-8-sig models the initial BOM removal."
  ],
  "importantDistinction": "The site maps all bytes through Latin-1 code points when the entire input fails UTF-8 validation. This is not the WHATWG Windows-1252 mapping associated with many web latin1 labels.",
  "summary": {
    "cases": 36,
    "byteIdentityPreserved": 23,
    "byteIdentityChanged": 13,
    "strictUtf8Invalid": 10
  },
  "dataLicense": "CC0-1.0 for the constructed cases and result tables. Script MIT. External standards retain their own licenses.",
  "corrections": "https://binarytranslator.dev/contact",
  "limitations": [
    "No personal input or traffic data. Case frequencies are not measured.",
    "No inference of unknown original encoding from bytes.",
    "Visual appearance depends on fonts; code points and bytes are authoritative.",
    "No Unicode normalization is performed by the site.",
    "Only disclosed scalar-value input and explicit 8-bit grouping are covered; malformed JavaScript surrogate strings and automatic direction detection are outside this dataset."
  ]
}