{
  "schema_version": 1,
  "id": "sheetpedia-6f3940c8975e",
  "format": "xlsx",
  "title": "Sheetpedia: extract and sum numerical values using string matching from single multi value cell submission",
  "published_at_utc": "2026-09-20T16:47:04.648020+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_0929/708841d1608046541-extract-and-sum-numerical-values-using-string-matching-from-single-multi-value-cell-submission.xlsx",
    "upstream_filename": "708841d1608046541-extract-and-sum-numerical-values-using-string-matching-from-single-multi-value-cell-submission.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-6f3940c8975e/source.xlsx",
    "url": "https://corpus.betteroffice.dev/sheetpedia-6f3940c8975e/source.xlsx?sha256=6f3940c8975e48844a5aa5d2b57b4fa848ba49d6efcd0eab4b7a9545207368f3",
    "bytes": 16142,
    "sha256": "6f3940c8975e48844a5aa5d2b57b4fa848ba49d6efcd0eab4b7a9545207368f3"
  },
  "worksheet_count": 4,
  "features": {
    "styles": 45,
    "fonts": 3,
    "fills": 16,
    "borders": 4,
    "number_formats": 1,
    "cells": 560,
    "formulas": 196,
    "merged_cells": 1,
    "conditional_rules": 0,
    "tables": 0,
    "charts": 0,
    "images": 0,
    "pivot_tables": 0,
    "sparklines": 0,
    "validations": 0,
    "hidden_sheets": 0,
    "multiline_strings": 0,
    "formula_functions": {
      "MID": 42,
      "IFERROR": 30,
      "LEN": 55,
      "_XLFN.TEXTJOIN": 21,
      "IF": 34,
      "SEARCH": 34,
      "FIND": 89,
      "CHAR": 12,
      "SUBSTITUTE": 6,
      "SUM": 7,
      "LEFT": 5,
      "TEXT": 15,
      "RIGHT": 5,
      "ROUND": 2,
      "INDEX": 2,
      "MATCH": 2
    },
    "wrapped_styles": 3,
    "rotated_styles": 0,
    "custom_font_names": [
      "Calibri"
    ]
  },
  "worksheets": [
    {
      "index": 0,
      "name": "Sheet4 (2)",
      "state": "visible",
      "cells": 94,
      "bounds": [
        1,
        1,
        40,
        16
      ],
      "formulas": 38,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    },
    {
      "index": 1,
      "name": "For Internet Help",
      "state": "visible",
      "cells": 38,
      "bounds": [
        1,
        1,
        21,
        7
      ],
      "formulas": 4,
      "merges": 1,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    },
    {
      "index": 2,
      "name": "Real Actual (2)",
      "state": "visible",
      "cells": 351,
      "bounds": [
        1,
        1,
        91,
        34
      ],
      "formulas": 128,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    },
    {
      "index": 3,
      "name": "Sheet4",
      "state": "visible",
      "cells": 77,
      "bounds": [
        1,
        1,
        40,
        14
      ],
      "formulas": 26,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    }
  ],
  "validation": {
    "archive_crc": "ok",
    "xml": "ok",
    "source_hash": "verified against pinned archive member",
    "expanded_bytes": 80163,
    "reference": "one PDF page per recorded range; nonempty raster; source SHA-256 matched"
  },
  "selection": {
    "filename_group": "named",
    "layout_signature": "3d52e5290f72b15816565ee2221afb43d514e46435ef564f57b102273dfa14b4",
    "method_url": "https://corpus.betteroffice.dev/datasets/sheetpedia/import.json"
  },
  "reference": {
    "source": "6f3940c8975e48844a5aa5d2b57b4fa848ba49d6efcd0eab4b7a9545207368f3.xlsx",
    "sha256": "6f3940c8975e48844a5aa5d2b57b4fa848ba49d6efcd0eab4b7a9545207368f3",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "os": "26.2",
    "dpi": 150,
    "export": "local PDF",
    "status": "ok",
    "started_at_utc": "2026-09-20T16:46:43.186464+00:00",
    "capture_profile": {
      "scale_percent": 75,
      "margin_pt": 18,
      "pages": [
        {
          "sheet": 1,
          "range": "A1:F22",
          "width_px": 1754,
          "height_px": 1241,
          "width_pt": 841.8897705078125,
          "height_pt": 595.2755737304688
        },
        {
          "sheet": 0,
          "range": "A1:G41",
          "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:20260920164644Z00'00'",
          "modDate": "D:20260920164644Z00'00'",
          "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:20260920164645Z00'00'",
          "modDate": "D:20260920164645Z00'00'",
          "trapped": "",
          "encryption": null
        }
      ]
    },
    "pages": 2,
    "fonts": [
      "AAAAAC+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:20260920164644Z00'00'",
      "modDate": "D:20260920164644Z00'00'",
      "trapped": "",
      "encryption": null
    },
    "ms": 2454.678917012643,
    "finished_at_utc": "2026-09-20T16:46:45.640996+00:00"
  },
  "reference_pdf": {
    "key": "sheetpedia-6f3940c8975e/reference/reference.pdf",
    "url": "https://corpus.betteroffice.dev/sheetpedia-6f3940c8975e/reference/reference.pdf?sha256=9e6601a4a196093363847daca032b8bbc140e927f95ed21ec4cef409ca92fa3e",
    "bytes": 67184,
    "sha256": "9e6601a4a196093363847daca032b8bbc140e927f95ed21ec4cef409ca92fa3e"
  },
  "reference_result": {
    "key": "sheetpedia-6f3940c8975e/reference/result.json",
    "url": "https://corpus.betteroffice.dev/sheetpedia-6f3940c8975e/reference/result.json?sha256=f069cfca606ca975cfd0f33e1e8c06ef9b6b7c4e0bcdc568bbd55d3ba28855cb",
    "bytes": 2356,
    "sha256": "f069cfca606ca975cfd0f33e1e8c06ef9b6b7c4e0bcdc568bbd55d3ba28855cb"
  },
  "reference_pages": [
    {
      "key": "sheetpedia-6f3940c8975e/reference/page_0001.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-6f3940c8975e/reference/page_0001.png?sha256=b62b8b63102736357988941af10ec68077eb6980f66d4bbd9a2729329ab31596",
      "bytes": 63021,
      "sha256": "b62b8b63102736357988941af10ec68077eb6980f66d4bbd9a2729329ab31596"
    },
    {
      "key": "sheetpedia-6f3940c8975e/reference/page_0002.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-6f3940c8975e/reference/page_0002.png?sha256=4296cc6c6a2463d4ca14adf67afd64a88be43ee95e680b63a2eca0681512f514",
      "bytes": 146076,
      "sha256": "4296cc6c6a2463d4ca14adf67afd64a88be43ee95e680b63a2eca0681512f514"
    }
  ],
  "calculation": {
    "status": "ok",
    "method": "excel-full-rebuild-v1",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "formula_cells": 196,
    "result_cells": 196,
    "empty_results": 0,
    "reference": {
      "key": "sheetpedia-6f3940c8975e/calculation/reference.json",
      "url": "https://corpus.betteroffice.dev/sheetpedia-6f3940c8975e/calculation/reference.json?sha256=68973ed9cf51d8607e4ad332458de8c6b0f9a5de1759accd27bbf1feb8fa56e5",
      "bytes": 38421,
      "sha256": "68973ed9cf51d8607e4ad332458de8c6b0f9a5de1759accd27bbf1feb8fa56e5"
    },
    "input": {
      "key": "sheetpedia-6f3940c8975e/calculation/input.xlsx",
      "url": "https://corpus.betteroffice.dev/sheetpedia-6f3940c8975e/calculation/input.xlsx?sha256=8bccfff8b6b54e7e62cef0ebc153e178c05a7ec6dad5679cf2dd3860dd6b0b9d",
      "bytes": 16282,
      "sha256": "8bccfff8b6b54e7e62cef0ebc153e178c05a7ec6dad5679cf2dd3860dd6b0b9d"
    }
  }
}