{
  "profile": "data-package",
  "name": "bookbinding-encyclopedia",
  "id": "https://doi.org/10.5281/zenodo.22182080",
  "title": "An Encyclopaedia of Bookbinding and the Printing Trades — entry dataset",
  "description": "5,460 dictionary entries on bookbinding, conservation, papermaking and printing, transcribed from nine works published 1683–1982.",
  "version": "2.1.0",
  "created": "2026-09-03T08:36:16+00:00",
  "homepage": "https://hibrkraft.com/resources/encyclopedia/",
  "keywords": [
    "bookbinding",
    "conservation",
    "printing",
    "papermaking",
    "terminology"
  ],
  "licenses": [
    {
      "name": "CC0-1.0",
      "path": "https://creativecommons.org/publicdomain/zero/1.0/",
      "title": "CC0 1.0 Universal — applies to the compilation and apparatus. Source texts vary; see rights_tier on every record."
    }
  ],
  "contributors": [
    {
      "title": "Ibrahim Anwar",
      "role": "author",
      "path": "https://hibrkraft.com/about/ibrahim-anwar/"
    }
  ],
  "sources": [
    {
      "title": "RE. Roberts, Matt T.; Etherington, Don (cool)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    },
    {
      "title": "DAP. Savage, William (pg77410)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    },
    {
      "title": "AMP. MacKellar, Thomas (pg56817)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    },
    {
      "title": "MAB. Nicholson, James B. (pg55056)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    },
    {
      "title": "ABB. Zaehnsdorf, Joseph W. (pg51213)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    },
    {
      "title": "NBL. Bailey, Arthur L. (pg47456)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    },
    {
      "title": "BCB. Cockerell, Douglas (pg26672)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    },
    {
      "title": "BIB. Sabin, Joseph (pg38946)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    },
    {
      "title": "MOX. Moxon, Joseph (pg78991)",
      "path": "https://hibrkraft.com/resources/encyclopedia/"
    }
  ],
  "resources": [
    {
      "name": "entries-jsonl",
      "path": "entries.jsonl",
      "title": "Entries",
      "description": "All 5,460 entries, one JSON object per line. Start here.",
      "format": "jsonl",
      "mediatype": "application/jsonlines",
      "encoding": "utf-8",
      "bytes": 8470264,
      "hash": "sha256:e91ef8239f7df44dd4f8e962b3b643e996f300255ef5a3af224ebba1d5923194",
      "schema": {
        "fields": [
          {
            "name": "id",
            "type": "string",
            "description": "Stable identifier for the entry. Either the source edition's own reference (RE and DAP, 4,614 records) or one composed from siglum, term and sense (the other seven sources, 846 records). Unique across the dataset and stable across rebuilds."
          },
          {
            "name": "term",
            "type": "string",
            "description": "The headword exactly as the source printed it."
          },
          {
            "name": "norm",
            "type": "string",
            "description": "The headword lowercased and normalised, for joining. NOT unique — see the multi-definition note in the description."
          },
          {
            "name": "sense",
            "type": "integer",
            "description": "Sense number where one source defines a term twice."
          },
          {
            "name": "kind",
            "type": "string",
            "description": "definition, or see for a bare cross-reference."
          },
          {
            "name": "letter",
            "type": "string",
            "description": "Alphabetical bucket the headword files under, folded to A–Z."
          },
          {
            "name": "letter_raw",
            "type": "string",
            "description": "The source's own first character before folding. For 12 records this is a quote mark or an accented letter, which no printed volume has a bucket for."
          },
          {
            "name": "volume",
            "type": "integer",
            "description": "Which printed volume carries this letter: 1, 2 or 3."
          },
          {
            "name": "variant",
            "type": "string",
            "description": "Variant spelling the source printed for this headword, where it gave one. Null for most records."
          },
          {
            "name": "dates",
            "type": "string",
            "description": "Dates the source attached to the headword, where it gave any. Null for most records."
          },
          {
            "name": "text",
            "type": "string",
            "description": "The definition. Paragraphs are joined by a blank line; split on \\n\\n to recover them, which is exact for every record."
          },
          {
            "name": "chars",
            "type": "integer",
            "description": "Character count of the definition."
          },
          {
            "name": "is_article",
            "type": "boolean",
            "description": "True for the 68 long-form entries that run as articles."
          },
          {
            "name": "figures",
            "type": "array",
            "description": "Figure identifiers printed with this entry. Empty for most records."
          },
          {
            "name": "source",
            "type": "object",
            "description": "The work this entry was transcribed from. Members: siglum — Printed short form of the source work: RE, DAP, MOX and so on.; id — Internal key for the source work: cool for Roberts & Etherington, pgNNNNN for the eight Project Gutenberg texts.; author — Who wrote the source work.; work — Title of the source work.; year — Year the source work was published, 1683 to 1982.; rights — Rights statement for that source work, in full."
          },
          {
            "name": "rights_tier",
            "type": "string",
            "description": "public-domain, or us-government-flagged. Read this before reuse."
          },
          {
            "name": "reference_numbers",
            "type": "array",
            "description": "Numbers into the 373-work bibliography, as the source printed them."
          },
          {
            "name": "citations",
            "type": "array",
            "description": "Those numbers already resolved to full citation strings."
          },
          {
            "name": "landing_page",
            "type": "string",
            "description": "The dataset's landing page, repeated on every record so a row that travels alone keeps its provenance."
          }
        ],
        "primaryKey": "id"
      }
    },
    {
      "name": "entries-jsonl-gz",
      "path": "entries.jsonl.gz",
      "title": "Entries, gzipped",
      "description": "The same 5,460 entries, gzipped. The server does not compress on the fly, so this is a real saving.",
      "format": "gz",
      "mediatype": "application/gzip",
      "encoding": "utf-8",
      "bytes": 1745923,
      "hash": "sha256:05384e7922eb7d276bce0c5edede736945ab594afdabc1afe0d86c48914b0a5c"
    },
    {
      "name": "entries-public-domain-jsonl",
      "path": "entries-public-domain.jsonl",
      "title": "Entries — public domain only",
      "description": "The 1,599 entries from the eight pre-1930 sources.",
      "format": "jsonl",
      "mediatype": "application/jsonlines",
      "encoding": "utf-8",
      "bytes": 3055488,
      "hash": "sha256:b0b0ebf5ef72c05302786b05aeafe62b1fb32b9cb4e45970463a2d72cdfe50dd",
      "schema": {
        "fields": [
          {
            "name": "id",
            "type": "string",
            "description": "Stable identifier for the entry. Either the source edition's own reference (RE and DAP, 4,614 records) or one composed from siglum, term and sense (the other seven sources, 846 records). Unique across the dataset and stable across rebuilds."
          },
          {
            "name": "term",
            "type": "string",
            "description": "The headword exactly as the source printed it."
          },
          {
            "name": "norm",
            "type": "string",
            "description": "The headword lowercased and normalised, for joining. NOT unique — see the multi-definition note in the description."
          },
          {
            "name": "sense",
            "type": "integer",
            "description": "Sense number where one source defines a term twice."
          },
          {
            "name": "kind",
            "type": "string",
            "description": "definition, or see for a bare cross-reference."
          },
          {
            "name": "letter",
            "type": "string",
            "description": "Alphabetical bucket the headword files under, folded to A–Z."
          },
          {
            "name": "letter_raw",
            "type": "string",
            "description": "The source's own first character before folding. For 12 records this is a quote mark or an accented letter, which no printed volume has a bucket for."
          },
          {
            "name": "volume",
            "type": "integer",
            "description": "Which printed volume carries this letter: 1, 2 or 3."
          },
          {
            "name": "variant",
            "type": "string",
            "description": "Variant spelling the source printed for this headword, where it gave one. Null for most records."
          },
          {
            "name": "dates",
            "type": "string",
            "description": "Dates the source attached to the headword, where it gave any. Null for most records."
          },
          {
            "name": "text",
            "type": "string",
            "description": "The definition. Paragraphs are joined by a blank line; split on \\n\\n to recover them, which is exact for every record."
          },
          {
            "name": "chars",
            "type": "integer",
            "description": "Character count of the definition."
          },
          {
            "name": "is_article",
            "type": "boolean",
            "description": "True for the 68 long-form entries that run as articles."
          },
          {
            "name": "figures",
            "type": "array",
            "description": "Figure identifiers printed with this entry. Empty for most records."
          },
          {
            "name": "source",
            "type": "object",
            "description": "The work this entry was transcribed from. Members: siglum — Printed short form of the source work: RE, DAP, MOX and so on.; id — Internal key for the source work: cool for Roberts & Etherington, pgNNNNN for the eight Project Gutenberg texts.; author — Who wrote the source work.; work — Title of the source work.; year — Year the source work was published, 1683 to 1982.; rights — Rights statement for that source work, in full."
          },
          {
            "name": "rights_tier",
            "type": "string",
            "description": "public-domain, or us-government-flagged. Read this before reuse."
          },
          {
            "name": "reference_numbers",
            "type": "array",
            "description": "Numbers into the 373-work bibliography, as the source printed them."
          },
          {
            "name": "citations",
            "type": "array",
            "description": "Those numbers already resolved to full citation strings."
          },
          {
            "name": "landing_page",
            "type": "string",
            "description": "The dataset's landing page, repeated on every record so a row that travels alone keeps its provenance."
          }
        ],
        "primaryKey": "id"
      }
    },
    {
      "name": "bibliography-json",
      "path": "bibliography.json",
      "title": "Bibliography",
      "description": "373 works cited by number from the entries.",
      "format": "json",
      "mediatype": "application/json",
      "encoding": "utf-8",
      "bytes": 60085,
      "hash": "sha256:4921c07d087eae5544d6f27ba970ef77545d534d6211fb0b1d66fb0705ec4167"
    },
    {
      "name": "sources-json",
      "path": "sources.json",
      "title": "Sources",
      "description": "The nine source works, with rights.",
      "format": "json",
      "mediatype": "application/json",
      "encoding": "utf-8",
      "bytes": 3515,
      "hash": "sha256:4c8adce9516f3013fa72082503e335a5874e1dea02a505127f0fc8256452587d"
    },
    {
      "name": "bookbinding-encyclopedia-v2-json",
      "path": "bookbinding-encyclopedia-v2.json",
      "title": "Compiled source file",
      "description": "The build's own output, one JSON object wrapping the entry array. Prefer entries.jsonl: reaching the first entry here means parsing the whole file.",
      "format": "json",
      "mediatype": "application/json",
      "encoding": "utf-8",
      "bytes": 7498023,
      "hash": "sha256:fcf0005bf00b490adc2e21d1c545589b683345b035e2205e4e0c488241547d82"
    },
    {
      "name": "croissant-json",
      "path": "croissant.json",
      "title": "Croissant descriptor",
      "description": "MLCommons Croissant 1.0 description of this same dataset.",
      "format": "json",
      "mediatype": "application/ld+json",
      "encoding": "utf-8",
      "bytes": 18090,
      "hash": "sha256:908e28d23278dd56281dd06fabd3ad05b9c26c92f76369cb04f37c9e25c919bc"
    },
    {
      "name": "README-md",
      "path": "README.md",
      "title": "README",
      "description": "Field dictionary, provenance, rights and how to cite it.",
      "format": "md",
      "mediatype": "text/markdown",
      "encoding": "utf-8"
    }
  ]
}