{
  "schema_version": 1,
  "id": "sheetpedia-ea9341457db5",
  "format": "xlsx",
  "title": "Sheetpedia: choosing one of the duplicate customer info testworkbook_unsort_optimize_customer_ ijulian _",
  "published_at_utc": "2026-09-20T16:48:42.720934+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_0929/262421d1378141889-choosing-one-of-the-duplicate-customer-info-testworkbook_unsort_optimize_customer_-ijulian-_.xlsx",
    "upstream_filename": "262421d1378141889-choosing-one-of-the-duplicate-customer-info-testworkbook_unsort_optimize_customer_-ijulian-_.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-ea9341457db5/source.xlsx",
    "url": "https://corpus.betteroffice.dev/sheetpedia-ea9341457db5/source.xlsx?sha256=ea9341457db5c66a9be2ba2fed6c64df94cb884a17b48f926ebb76a43d752c5b",
    "bytes": 171046,
    "sha256": "ea9341457db5c66a9be2ba2fed6c64df94cb884a17b48f926ebb76a43d752c5b"
  },
  "worksheet_count": 3,
  "features": {
    "styles": 11,
    "fonts": 18,
    "fills": 36,
    "borders": 10,
    "number_formats": 1,
    "cells": 342,
    "formulas": 94,
    "merged_cells": 0,
    "conditional_rules": 0,
    "tables": 1,
    "charts": 0,
    "images": 0,
    "pivot_tables": 1,
    "sparklines": 0,
    "validations": 0,
    "hidden_sheets": 1,
    "multiline_strings": 0,
    "formula_functions": {
      "COUNTIF": 14,
      "IF": 22,
      "AND": 14,
      "SUMPRODUCT": 60,
      "INDEX": 16,
      "MATCH": 16,
      "SUMIFS": 16,
      "SUM": 8,
      "SUBTOTAL": 4
    },
    "wrapped_styles": 0,
    "rotated_styles": 0,
    "custom_font_names": [
      "Calibri",
      "Cambria"
    ]
  },
  "worksheets": [
    {
      "index": 0,
      "name": "Sheet1",
      "state": "hidden",
      "cells": 121,
      "bounds": [
        1,
        1,
        33,
        4
      ],
      "formulas": 0,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    },
    {
      "index": 1,
      "name": "Sales",
      "state": "visible",
      "cells": 149,
      "bounds": [
        1,
        1,
        15,
        10
      ],
      "formulas": 42,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    },
    {
      "index": 2,
      "name": "Report",
      "state": "visible",
      "cells": 72,
      "bounds": [
        1,
        1,
        13,
        7
      ],
      "formulas": 52,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 1,
      "drawings": 0
    }
  ],
  "validation": {
    "archive_crc": "ok",
    "xml": "ok",
    "source_hash": "verified against pinned archive member",
    "expanded_bytes": 5657679,
    "reference": "one PDF page per recorded range; nonempty raster; source SHA-256 matched"
  },
  "selection": {
    "filename_group": "named",
    "layout_signature": "a906a1dd6e2022e56db542b5467e63796cf01d22d8668168dc0db25753b63819",
    "method_url": "https://corpus.betteroffice.dev/datasets/sheetpedia/import.json"
  },
  "reference": {
    "source": "ea9341457db5c66a9be2ba2fed6c64df94cb884a17b48f926ebb76a43d752c5b.xlsx",
    "sha256": "ea9341457db5c66a9be2ba2fed6c64df94cb884a17b48f926ebb76a43d752c5b",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "os": "26.2",
    "dpi": 150,
    "export": "local PDF",
    "status": "ok",
    "started_at_utc": "2026-09-20T16:48:38.311440+00:00",
    "capture_profile": {
      "scale_percent": 75,
      "margin_pt": 18,
      "pages": [
        {
          "sheet": 2,
          "range": "A1:H14",
          "width_px": 1754,
          "height_px": 1241,
          "width_pt": 841.8897705078125,
          "height_pt": 595.2755737304688
        },
        {
          "sheet": 1,
          "range": "A1:G16",
          "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": "ea9341457db5c66a9be2ba2fed6c64df94cb884a17b48f926ebb76a43d752c5b",
          "author": "",
          "subject": "",
          "keywords": "",
          "creator": "Excel",
          "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
          "creationDate": "D:20260920164839Z00'00'",
          "modDate": "D:20260920164839Z00'00'",
          "trapped": "",
          "encryption": null
        },
        {
          "format": "PDF 1.3",
          "title": "ea9341457db5c66a9be2ba2fed6c64df94cb884a17b48f926ebb76a43d752c5b",
          "author": "",
          "subject": "",
          "keywords": "",
          "creator": "Excel",
          "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
          "creationDate": "D:20260920164839Z00'00'",
          "modDate": "D:20260920164839Z00'00'",
          "trapped": "",
          "encryption": null
        }
      ]
    },
    "pages": 2,
    "fonts": [
      "AAAAAC+Calibri",
      "AAAAAE+Calibri-Bold"
    ],
    "pdf_metadata": {
      "format": "PDF 1.7",
      "title": "ea9341457db5c66a9be2ba2fed6c64df94cb884a17b48f926ebb76a43d752c5b",
      "author": "",
      "subject": "",
      "keywords": "",
      "creator": "Excel",
      "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
      "creationDate": "D:20260920164839Z00'00'",
      "modDate": "D:20260920164839Z00'00'",
      "trapped": "",
      "encryption": null
    },
    "ms": 1885.0972499931231,
    "finished_at_utc": "2026-09-20T16:48:40.196211+00:00"
  },
  "reference_pdf": {
    "key": "sheetpedia-ea9341457db5/reference/reference.pdf",
    "url": "https://corpus.betteroffice.dev/sheetpedia-ea9341457db5/reference/reference.pdf?sha256=c249a34b31ec1ed9ab53f9e872b3ed5f71b9b78edd1542091b2b5c01d19954be",
    "bytes": 69913,
    "sha256": "c249a34b31ec1ed9ab53f9e872b3ed5f71b9b78edd1542091b2b5c01d19954be"
  },
  "reference_result": {
    "key": "sheetpedia-ea9341457db5/reference/result.json",
    "url": "https://corpus.betteroffice.dev/sheetpedia-ea9341457db5/reference/result.json?sha256=fbab9cc622b350b31061d5f25495e13d36c777ee5369eaa8d42084c0acb4ddba",
    "bytes": 2525,
    "sha256": "fbab9cc622b350b31061d5f25495e13d36c777ee5369eaa8d42084c0acb4ddba"
  },
  "reference_pages": [
    {
      "key": "sheetpedia-ea9341457db5/reference/page_0001.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-ea9341457db5/reference/page_0001.png?sha256=5668d693ee06c0c59d33d62e406d2c7bf6408864f280c6dee14d5bb8f41cf19f",
      "bytes": 89864,
      "sha256": "5668d693ee06c0c59d33d62e406d2c7bf6408864f280c6dee14d5bb8f41cf19f"
    },
    {
      "key": "sheetpedia-ea9341457db5/reference/page_0002.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-ea9341457db5/reference/page_0002.png?sha256=74ec6d1ff5c8a221dd0de55ceea24a1313c1bc1e0d1c00dc8757298701a4817b",
      "bytes": 134367,
      "sha256": "74ec6d1ff5c8a221dd0de55ceea24a1313c1bc1e0d1c00dc8757298701a4817b"
    }
  ],
  "calculation": {
    "status": "ok",
    "method": "excel-full-rebuild-v1",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "formula_cells": 94,
    "result_cells": 94,
    "empty_results": 0,
    "reference": {
      "key": "sheetpedia-ea9341457db5/calculation/reference.json",
      "url": "https://corpus.betteroffice.dev/sheetpedia-ea9341457db5/calculation/reference.json?sha256=63ffbb44b427de13a8776b28e220b3b008581b4beaeb867e9daace1cfc290fd9",
      "bytes": 18840,
      "sha256": "63ffbb44b427de13a8776b28e220b3b008581b4beaeb867e9daace1cfc290fd9"
    },
    "input": {
      "key": "sheetpedia-ea9341457db5/calculation/input.xlsx",
      "url": "https://corpus.betteroffice.dev/sheetpedia-ea9341457db5/calculation/input.xlsx?sha256=264d66a2a26dd3eac02acd659d87ee6a007624911469aada371e2c960c2580af",
      "bytes": 171135,
      "sha256": "264d66a2a26dd3eac02acd659d87ee6a007624911469aada371e2c960c2580af"
    }
  }
}