{
  "schema_version": 1,
  "id": "sheetpedia-4eec0efcd659",
  "format": "xlsx",
  "title": "Sheetpedia: sheetpedia-4eec0efcd659",
  "published_at_utc": "2026-09-20T17:48:45.857252+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_0929/01a866f4-2106-4381-bfb5-a5c4202017cb.xlsx",
    "upstream_filename": "01a866f4-2106-4381-bfb5-a5c4202017cb.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-4eec0efcd659/source.xlsx",
    "url": "https://corpus.betteroffice.dev/sheetpedia-4eec0efcd659/source.xlsx?sha256=4eec0efcd659274faf389c3f1a803ad1dfd652921ecbf521ee15e0c48010dde7",
    "bytes": 53521,
    "sha256": "4eec0efcd659274faf389c3f1a803ad1dfd652921ecbf521ee15e0c48010dde7"
  },
  "worksheet_count": 2,
  "features": {
    "styles": 191,
    "fonts": 7,
    "fills": 5,
    "borders": 113,
    "number_formats": 0,
    "cells": 750,
    "formulas": 0,
    "merged_cells": 66,
    "conditional_rules": 0,
    "tables": 0,
    "charts": 0,
    "images": 0,
    "pivot_tables": 0,
    "sparklines": 0,
    "validations": 0,
    "hidden_sheets": 0,
    "multiline_strings": 2,
    "formula_functions": {},
    "wrapped_styles": 96,
    "rotated_styles": 0,
    "custom_font_names": [
      "Calibri"
    ]
  },
  "worksheets": [
    {
      "index": 0,
      "name": "2003",
      "state": "visible",
      "cells": 308,
      "bounds": [
        2,
        1,
        186,
        2
      ],
      "formulas": 0,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    },
    {
      "index": 1,
      "name": "2012",
      "state": "visible",
      "cells": 442,
      "bounds": [
        1,
        1,
        154,
        4
      ],
      "formulas": 0,
      "merges": 66,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    }
  ],
  "validation": {
    "archive_crc": "ok",
    "xml": "ok",
    "source_hash": "verified against pinned archive member",
    "expanded_bytes": 483910,
    "reference": "one PDF page per recorded range; nonempty raster; source SHA-256 matched"
  },
  "selection": {
    "filename_group": "identifier",
    "layout_signature": "d9e5f444c200ee02518dae3579d8f95f8a1ba3d1afcae273e98240d95e93cbe5",
    "method_url": "https://corpus.betteroffice.dev/datasets/sheetpedia/import.json"
  },
  "reference": {
    "source": "4eec0efcd659274faf389c3f1a803ad1dfd652921ecbf521ee15e0c48010dde7.xlsx",
    "sha256": "4eec0efcd659274faf389c3f1a803ad1dfd652921ecbf521ee15e0c48010dde7",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "os": "26.2",
    "dpi": 150,
    "export": "local PDF",
    "status": "ok",
    "started_at_utc": "2026-09-20T17:48:42.780480+00:00",
    "capture_profile": {
      "scale_percent": 75,
      "margin_pt": 18,
      "pages": [
        {
          "sheet": 1,
          "range": "A1:E14",
          "width_px": 1650,
          "height_px": 1275,
          "width_pt": 792.0,
          "height_pt": 612.0
        },
        {
          "sheet": 0,
          "range": "A1:C18",
          "width_px": 1650,
          "height_px": 1275,
          "width_pt": 792.0,
          "height_pt": 612.0
        }
      ],
      "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:20260920174844Z00'00'",
          "modDate": "D:20260920174844Z00'00'",
          "trapped": "",
          "encryption": null
        },
        {
          "format": "PDF 1.3",
          "title": "Untitled",
          "author": "",
          "subject": "",
          "keywords": "",
          "creator": "Excel",
          "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
          "creationDate": "D:20260920174844Z00'00'",
          "modDate": "D:20260920174844Z00'00'",
          "trapped": "",
          "encryption": null
        }
      ]
    },
    "pages": 2,
    "fonts": [
      "AAAAAC+Calibri",
      "AAAAAC+Calibri-Bold",
      "AAAAAE+Calibri",
      "AAAAAE+Calibri-Bold"
    ],
    "pdf_metadata": {
      "format": "PDF 1.7",
      "title": "Untitled",
      "author": "",
      "subject": "",
      "keywords": "",
      "creator": "Excel",
      "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
      "creationDate": "D:20260920174844Z00'00'",
      "modDate": "D:20260920174844Z00'00'",
      "trapped": "",
      "encryption": null
    },
    "ms": 2040.6269170343876,
    "finished_at_utc": "2026-09-20T17:48:44.820976+00:00"
  },
  "reference_pdf": {
    "key": "sheetpedia-4eec0efcd659/reference/reference.pdf",
    "url": "https://corpus.betteroffice.dev/sheetpedia-4eec0efcd659/reference/reference.pdf?sha256=61a5792d05a7618769ca9b3cee61ac78f08b9b41eda2aec8d0f33862612071ba",
    "bytes": 84737,
    "sha256": "61a5792d05a7618769ca9b3cee61ac78f08b9b41eda2aec8d0f33862612071ba"
  },
  "reference_result": {
    "key": "sheetpedia-4eec0efcd659/reference/result.json",
    "url": "https://corpus.betteroffice.dev/sheetpedia-4eec0efcd659/reference/result.json?sha256=0b7c3c15bbe39802ec7c5b53366f2fa732bd3d30a17f769b7a9bc2dd215609c1",
    "bytes": 2358,
    "sha256": "0b7c3c15bbe39802ec7c5b53366f2fa732bd3d30a17f769b7a9bc2dd215609c1"
  },
  "reference_pages": [
    {
      "key": "sheetpedia-4eec0efcd659/reference/page_0001.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-4eec0efcd659/reference/page_0001.png?sha256=ee16b28574fe953c2bf4e520825b5487cd8b428ce78853ef91cccc9f5e623251",
      "bytes": 229515,
      "sha256": "ee16b28574fe953c2bf4e520825b5487cd8b428ce78853ef91cccc9f5e623251"
    },
    {
      "key": "sheetpedia-4eec0efcd659/reference/page_0002.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-4eec0efcd659/reference/page_0002.png?sha256=df8c2f4e7dc4c65988de00c1daf5f925096361ca1e7370c554c8cdb9a1b0201a",
      "bytes": 141881,
      "sha256": "df8c2f4e7dc4c65988de00c1daf5f925096361ca1e7370c554c8cdb9a1b0201a"
    }
  ],
  "calculation": {
    "status": "not_applicable",
    "formula_cells": 0
  }
}