{
  "schemaVersion": 1,
  "datasetId": "ai-text-artifact-corpus-v1",
  "title": "AnyFormatLocal Fixed Text Artifact Corpus v1",
  "license": "CC0-1.0",
  "publishedAt": "2026-09-05",
  "provenance": {
    "source": "Maintainer-authored synthetic formatting fixtures",
    "containsUserText": false,
    "prompt": null,
    "model": null,
    "modelVersion": null,
    "generationDate": "2026-09-05",
    "note": "No generative model was used. Null prompt and model fields are explicit provenance."
  },
  "measurement": {
    "engine": "local-format-cleaner",
    "method": "Execute each input with the listed rule IDs and compare the UTF-16 output string exactly with expectedOutput.",
    "counts": "Change counts are emitted change records; character counts use JavaScript string length."
  },
  "fixtures": [
    {
      "id": "hidden-unicode",
      "input": "Alpha​Beta",
      "rules": ["hidden-unicode"],
      "expectedOutput": "AlphaBeta"
    },
    {
      "id": "nbsp",
      "input": "Alpha Beta",
      "rules": ["normalize-nbsp"],
      "expectedOutput": "Alpha Beta"
    },
    {
      "id": "tabs",
      "input": "Name\tValue",
      "rules": ["normalize-tabs"],
      "expectedOutput": "Name Value"
    },
    {
      "id": "repeated-spaces",
      "input": "One   two",
      "rules": ["collapse-spaces"],
      "expectedOutput": "One two"
    },
    {
      "id": "blank-lines",
      "input": "One\n\n\n\nTwo",
      "rules": ["collapse-blank-lines"],
      "expectedOutput": "One\n\nTwo"
    },
    {
      "id": "markdown",
      "input": "## **Visible title**",
      "rules": ["remove-markdown-headings", "remove-markdown-emphasis"],
      "expectedOutput": "Visible title"
    },
    {
      "id": "punctuation-safe",
      "input": "“Keep” — this",
      "rules": [],
      "expectedOutput": "“Keep” — this"
    },
    {
      "id": "multilingual",
      "input": "中文 текст​ κόσμε",
      "rules": ["hidden-unicode", "normalize-nbsp"],
      "expectedOutput": "中文 текст κόσμε"
    }
  ]
}