{
  "schema": "kbatch-corpus-catalog-v1",
  "generated": "2026-07-23T20:24:06.153Z",
  "claim": "Complete open catalog list for KBatch corpora. No sacred-texts scrape · no lyric pirate · no Turner/OUP body.",
  "doctrine": {
    "allow": [
      "Gutenberg PD",
      "Wikidata CC0",
      "Open Library meta",
      "IA PD",
      "AnCEstory privacy-safe"
    ],
    "forbid": [
      "sacred-texts.com full-text scrape",
      "commercial lyric dumps",
      "OUP/Turner dictionary body"
    ]
  },
  "totalCatalogs": 19,
  "totalRowsApprox": 138400,
  "catalogs": [
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "ancestory-lineage",
      "label": "AnCEstory lineage (historical)",
      "path": "data/ancestory/index.json",
      "surface": "/labs/ancestory",
      "rows": 6587,
      "kind": "lineage",
      "note": "Privacy-safe · pre-cutoff only"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "charts-title-path",
      "label": "Chart title-path geometry",
      "path": "data/lyrics/charts/index.json",
      "surface": "/lyrics",
      "rows": 1141,
      "kind": "music",
      "note": "Title-path only · not commercial full lyrics"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "declaration-digital-edition",
      "label": "Declaration of Independence digital edition",
      "path": "labs/declaration-digital-edition/",
      "surface": "/labs/declaration-digital-edition/",
      "rows": 6,
      "kind": "paleography",
      "note": "NARA PD multi-treatment · paleography · keyboard path/braille/DDR/rhythm"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "declaration-keyboard-analysis",
      "label": "Declaration keyboard analysis",
      "path": "data/declaration/keyboard-analysis.json",
      "surface": "/labs/declaration-digital-edition/keyboard.html",
      "rows": 6,
      "kind": "scripts"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "deities",
      "label": "Open deities (Wikidata)",
      "path": "data/mythology/deities-index.json",
      "surface": "/labs/myth-names?track=myth",
      "rows": 6093,
      "kind": "names",
      "forbid": [
        "Turner/OUP body text"
      ]
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "gutenberg-stubs",
      "label": "Project Gutenberg full catalog stubs",
      "path": "data/living-books/gutenberg-stubs/index.json",
      "surface": "/labs/living-books?catalog=pg",
      "rows": 78760,
      "shards": 16,
      "kind": "books",
      "note": "Metadata only · full text on demand · never bulk-mirror"
    },
    {
      "status": "planned",
      "rights": "open-or-pd",
      "id": "lake-manifest",
      "label": "Data lake manifest",
      "path": "data/lake/manifest.json",
      "surface": "/data/lake/manifest.json",
      "kind": "meta"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "lang-tree",
      "label": "World language tree",
      "path": "data/lake/lang-tree.json",
      "surface": "/labs/lang-tree",
      "rows": 35,
      "kind": "scripts"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "language-alphabet-matrix",
      "label": "Language × alphabet matrix (88)",
      "path": "data/language-alphabet-matrix.json",
      "surface": "/dojo/",
      "rows": 88,
      "kind": "scripts"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "living-books-curated",
      "label": "Living books (curated PD + sacred)",
      "path": "data/living-books/entries.json",
      "surface": "/labs/living-books",
      "rows": 285,
      "kind": "books",
      "note": "Polished read-through set · Gutenberg IDs"
    },
    {
      "status": "planned",
      "rights": "open-or-pd",
      "id": "llm-train",
      "label": "LLM tool train pack",
      "path": "data/llm/train-pack.json",
      "surface": "/for-ai#llm-train",
      "kind": "agent"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "names-glance",
      "label": "Names glance dual-pane index",
      "path": "data/names-glance/index.json",
      "surface": "/labs/myth-names",
      "rows": 19580,
      "kind": "names"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "open-names",
      "label": "Open human names",
      "path": "data/open-names/names-index.json",
      "surface": "/labs/myth-names?track=names",
      "rows": 13862,
      "byTheme": {
        "given": 5267,
        "history": 2392,
        "family": 4421,
        "lineage-history": 1746,
        "etymology": 15,
        "history-event": 21
      },
      "kind": "names"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "rosetta-writing-systems",
      "label": "Rosetta writing & record systems",
      "path": "data/lake/writing-systems.json",
      "surface": "/labs/rosetta",
      "rows": 92,
      "kind": "scripts",
      "note": "Hieroglyphs · cuneiform · Maya/Aztec · quipu · carving media · Cyrillic · Unicode samples when encoded"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "scribe-glyph-library",
      "label": "Scribe glyph strips (any document)",
      "path": "labs/declaration-digital-edition/glyph-library.json",
      "surface": "/labs/declaration-digital-edition/scribe-glyphs.html",
      "rows": 2,
      "kind": "paleography",
      "note": "Codex-style numbered calligraphy tiles · portable handoff pipeline"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "senses",
      "label": "Open senses / glosses",
      "path": "data/senses/index.json",
      "surface": "/",
      "rows": 11250,
      "kind": "lexicon"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "skills",
      "label": "Learn skills",
      "path": "data/education/school-concepts.json",
      "surface": "/learn",
      "rows": 194,
      "kind": "education"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "staff",
      "label": "Music staff catalogue",
      "path": "data/music-staff/index.json",
      "surface": "/labs/music-staff",
      "rows": 408,
      "kind": "music",
      "note": "PD motifs · ET educational stand-ins · no lyric pirate"
    },
    {
      "status": "live",
      "rights": "open-or-pd",
      "id": "visual-projects",
      "label": "Visual / deep-zoom projects",
      "path": "data/living-books/visual-projects.json",
      "surface": "/labs/living-books",
      "rows": 11,
      "kind": "books"
    }
  ]
}