{
  "schema_version": 1,
  "id": "sheetpedia-e001b8b8d24b",
  "format": "xlsx",
  "title": "Sheetpedia: extracting names into respective columns name_extraction_sample",
  "published_at_utc": "2026-09-20T17:44:09.277990+00:00",
  "license": "CC-BY-SA-4.0",
  "license_url": "https://creativecommons.org/licenses/by-sa/4.0/",
  "scope": "Up to two recorded visible worksheet ranges per workbook. Workbook feature counts describe the source, not necessarily every captured range. This curated compact subset is not a representative estimate of all Sheetpedia workbooks.",
  "provenance": {
    "kind": "dataset",
    "dataset": "Sheetpedia",
    "authors": [
      "Zailong Tian",
      "Zhuoheng Han",
      "Houfeng Wang",
      "Lizi Liao"
    ],
    "dataset_url": "https://huggingface.co/datasets/tianzl66/Sheetpedia_xlsx",
    "project_url": "https://github.com/TTtianTT/Sheetpedia",
    "revision": "8d0e9c1d5f68e2389094bf739b1b7345a6822dee",
    "variant": "upstream PII-processed XLSX",
    "upstream_path": "pii_processed_xlsx_0929/788205d1658325029-extracting-names-into-respective-columns-name_extraction_sample.xlsx",
    "upstream_filename": "788205d1658325029-extracting-names-into-respective-columns-name_extraction_sample.xlsx",
    "source_url": "https://huggingface.co/datasets/tianzl66/Sheetpedia_xlsx/resolve/8d0e9c1d5f68e2389094bf739b1b7345a6822dee/pii_processed_xlsx_0929.tar.gz",
    "archive_sha256": "e4b3fd585cf9e3603c04b872df8348d759b24e1d11596bdc7cd484205fd54c99",
    "license": "CC-BY-SA-4.0",
    "license_declaration_url": "https://huggingface.co/datasets/tianzl66/Sheetpedia_xlsx/blob/8d0e9c1d5f68e2389094bf739b1b7345a6822dee/README.md",
    "license_url": "https://creativecommons.org/licenses/by-sa/4.0/",
    "license_text_url": "https://corpus.betteroffice.dev/datasets/sheetpedia/LICENSE.txt",
    "notice_url": "https://corpus.betteroffice.dev/datasets/sheetpedia/NOTICE.txt",
    "changes": "Workbook bytes unchanged from the upstream PII-processed archive. BetterOffice selected worksheet print ranges and generated Microsoft Excel PDF/PNG references; capture settings are recorded below. Generated reference assets are also offered under CC BY-SA 4.0."
  },
  "source": {
    "key": "sheetpedia-e001b8b8d24b/source.xlsx",
    "url": "https://corpus.betteroffice.dev/sheetpedia-e001b8b8d24b/source.xlsx?sha256=e001b8b8d24b0547cb3bd05699b73dae9b0a6337f5ae4e17c468a0e572d00cd4",
    "bytes": 7870,
    "sha256": "e001b8b8d24b0547cb3bd05699b73dae9b0a6337f5ae4e17c468a0e572d00cd4"
  },
  "worksheet_count": 1,
  "features": {
    "styles": 8,
    "fonts": 2,
    "fills": 8,
    "borders": 1,
    "number_formats": 0,
    "cells": 233,
    "formulas": 102,
    "merged_cells": 0,
    "conditional_rules": 0,
    "tables": 0,
    "charts": 0,
    "images": 0,
    "pivot_tables": 0,
    "sparklines": 0,
    "validations": 0,
    "hidden_sheets": 0,
    "multiline_strings": 0,
    "formula_functions": {
      "IFERROR": 68,
      "INDEX": 17,
      "SUM": 17,
      "IF": 17,
      "ISNUMBER": 17,
      "SEARCH": 51,
      "ROW": 17,
      "SUBSTITUTE": 374,
      "TRIM": 85,
      "CHAR": 153,
      "MID": 34,
      "_XLFN.FILTERXML": 17,
      "RIGHT": 17,
      "REPT": 17
    },
    "wrapped_styles": 0,
    "rotated_styles": 0,
    "custom_font_names": [
      "Calibri"
    ]
  },
  "worksheets": [
    {
      "index": 0,
      "name": "Sheet1",
      "state": "visible",
      "cells": 233,
      "bounds": [
        1,
        1,
        18,
        17
      ],
      "formulas": 102,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    }
  ],
  "validation": {
    "archive_crc": "ok",
    "xml": "ok",
    "source_hash": "verified against pinned archive member",
    "expanded_bytes": 43575,
    "reference": "one PDF page per recorded range; nonempty raster; source SHA-256 matched"
  },
  "selection": {
    "filename_group": "named",
    "layout_signature": "02d43e42d97b8de79e5f05f3689d04e08faa127e0758354df83b3ba3d9d4012e",
    "method_url": "https://corpus.betteroffice.dev/datasets/sheetpedia/import.json"
  },
  "reference": {
    "source": "e001b8b8d24b0547cb3bd05699b73dae9b0a6337f5ae4e17c468a0e572d00cd4.xlsx",
    "sha256": "e001b8b8d24b0547cb3bd05699b73dae9b0a6337f5ae4e17c468a0e572d00cd4",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "os": "26.2",
    "dpi": 150,
    "export": "local PDF",
    "status": "ok",
    "started_at_utc": "2026-09-20T17:44:06.353612+00:00",
    "capture_profile": {
      "scale_percent": 75,
      "margin_pt": 18,
      "pages": [
        {
          "sheet": 0,
          "range": "A1:L19",
          "width_px": 1754,
          "height_px": 1241,
          "width_pt": 841.8897705078125,
          "height_pt": 595.2755737304688
        }
      ],
      "paper": "landscape; Office paper size recorded per page",
      "gridlines": true,
      "headings": false,
      "pagination": "one recorded range per page; fixed print scale",
      "office_pdf_metadata": [
        {
          "format": "PDF 1.3",
          "title": "Untitled",
          "author": "",
          "subject": "",
          "keywords": "",
          "creator": "Excel",
          "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
          "creationDate": "D:20260920174408Z00'00'",
          "modDate": "D:20260920174408Z00'00'",
          "trapped": "",
          "encryption": null
        }
      ]
    },
    "pages": 1,
    "fonts": [
      "AAAAAC+Calibri-Bold",
      "AAAAAE+Calibri"
    ],
    "pdf_metadata": {
      "format": "PDF 1.7",
      "title": "Untitled",
      "author": "",
      "subject": "",
      "keywords": "",
      "creator": "Excel",
      "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
      "creationDate": "D:20260920174408Z00'00'",
      "modDate": "D:20260920174408Z00'00'",
      "trapped": "",
      "encryption": null
    },
    "ms": 2076.9872079836205,
    "finished_at_utc": "2026-09-20T17:44:08.430382+00:00"
  },
  "reference_pdf": {
    "key": "sheetpedia-e001b8b8d24b/reference/reference.pdf",
    "url": "https://corpus.betteroffice.dev/sheetpedia-e001b8b8d24b/reference/reference.pdf?sha256=81340bebee9c40d813ce0d3d37782ed25252222bc4118064d2de2989ba11e668",
    "bytes": 37954,
    "sha256": "81340bebee9c40d813ce0d3d37782ed25252222bc4118064d2de2989ba11e668"
  },
  "reference_result": {
    "key": "sheetpedia-e001b8b8d24b/reference/result.json",
    "url": "https://corpus.betteroffice.dev/sheetpedia-e001b8b8d24b/reference/result.json?sha256=9ea48ecfa770608832839e82a9f3249f2605df820183fdedc240c37735004ce8",
    "bytes": 1769,
    "sha256": "9ea48ecfa770608832839e82a9f3249f2605df820183fdedc240c37735004ce8"
  },
  "reference_pages": [
    {
      "key": "sheetpedia-e001b8b8d24b/reference/page_0001.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-e001b8b8d24b/reference/page_0001.png?sha256=49311083b867fb2dfa4d4aa466454c5edf89987d7890826063773d8d9bd2c9b3",
      "bytes": 113048,
      "sha256": "49311083b867fb2dfa4d4aa466454c5edf89987d7890826063773d8d9bd2c9b3"
    }
  ],
  "calculation": {
    "status": "ok",
    "method": "excel-full-rebuild-v1",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "formula_cells": 102,
    "result_cells": 102,
    "empty_results": 0,
    "reference": {
      "key": "sheetpedia-e001b8b8d24b/calculation/reference.json",
      "url": "https://corpus.betteroffice.dev/sheetpedia-e001b8b8d24b/calculation/reference.json?sha256=6643b1ab7f8dd7cee150425cd1ad27976f33ac31c79e85f55c043a2fefb1c228",
      "bytes": 20061,
      "sha256": "6643b1ab7f8dd7cee150425cd1ad27976f33ac31c79e85f55c043a2fefb1c228"
    },
    "input": {
      "key": "sheetpedia-e001b8b8d24b/calculation/input.xlsx",
      "url": "https://corpus.betteroffice.dev/sheetpedia-e001b8b8d24b/calculation/input.xlsx?sha256=89b3cd481dee292377030031679733e9360c6e899471e3632c4e86d636a5e7a3",
      "bytes": 7934,
      "sha256": "89b3cd481dee292377030031679733e9360c6e899471e3632c4e86d636a5e7a3"
    }
  }
}
