{
  "schema_version": 1,
  "id": "sheetpedia-8d1a4c6dd4f9",
  "format": "xlsx",
  "title": "Sheetpedia: trying to get data from a spreadsheet and break it down per customer and per tech raw data",
  "published_at_utc": "2026-09-20T16:50:08.794365+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_0929/853612d1703522105-trying-to-get-data-from-a-spreadsheet-and-break-it-down-per-customer-and-per-tech-raw-data.xlsx",
    "upstream_filename": "853612d1703522105-trying-to-get-data-from-a-spreadsheet-and-break-it-down-per-customer-and-per-tech-raw-data.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-8d1a4c6dd4f9/source.xlsx",
    "url": "https://corpus.betteroffice.dev/sheetpedia-8d1a4c6dd4f9/source.xlsx?sha256=8d1a4c6dd4f92ac669fa1d2f7308a1705c75d8b63b5912250eb4015b8a2ebacb",
    "bytes": 6544,
    "sha256": "8d1a4c6dd4f92ac669fa1d2f7308a1705c75d8b63b5912250eb4015b8a2ebacb"
  },
  "worksheet_count": 1,
  "features": {
    "styles": 1,
    "fonts": 18,
    "fills": 33,
    "borders": 10,
    "number_formats": 0,
    "cells": 51,
    "formulas": 1,
    "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": {
      "_XLFN.DROP": 1,
      "_XLFN.REDUCE": 1,
      "_XLFN.UNIQUE": 2,
      "_XLFN._XLWS.FILTER": 2,
      "_XLFN.LAMBDA": 1,
      "_XLFN.LET": 1,
      "_XLFN.VSTACK": 2,
      "_XLFN.EXPAND": 2,
      "_XLFN.HSTACK": 1,
      "SUMIFS": 1,
      "ROWS": 1
    },
    "wrapped_styles": 0,
    "rotated_styles": 0,
    "custom_font_names": [
      "Calibri",
      "Calibri Light"
    ]
  },
  "worksheets": [
    {
      "index": 0,
      "name": "timeentrysearch (43)",
      "state": "visible",
      "cells": 51,
      "bounds": [
        1,
        1,
        13,
        8
      ],
      "formulas": 1,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    }
  ],
  "validation": {
    "archive_crc": "ok",
    "xml": "ok",
    "source_hash": "verified against pinned archive member",
    "expanded_bytes": 27783,
    "reference": "one PDF page per recorded range; nonempty raster; source SHA-256 matched"
  },
  "selection": {
    "filename_group": "named",
    "layout_signature": "54d1206b7984b2ab191236c75907129d273e6ed3175cfa56b4542cd1e1beff88",
    "method_url": "https://corpus.betteroffice.dev/datasets/sheetpedia/import.json"
  },
  "reference": {
    "source": "8d1a4c6dd4f92ac669fa1d2f7308a1705c75d8b63b5912250eb4015b8a2ebacb.xlsx",
    "sha256": "8d1a4c6dd4f92ac669fa1d2f7308a1705c75d8b63b5912250eb4015b8a2ebacb",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "os": "26.2",
    "dpi": 150,
    "export": "local PDF",
    "status": "ok",
    "started_at_utc": "2026-09-20T16:49:51.284805+00:00",
    "capture_profile": {
      "scale_percent": 75,
      "margin_pt": 18,
      "pages": [
        {
          "sheet": 0,
          "range": "A1:I14",
          "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:20260920164952Z00'00'",
          "modDate": "D:20260920164952Z00'00'",
          "trapped": "",
          "encryption": null
        }
      ]
    },
    "pages": 1,
    "fonts": [
      "AAAAAC+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:20260920164952Z00'00'",
      "modDate": "D:20260920164952Z00'00'",
      "trapped": "",
      "encryption": null
    },
    "ms": 1476.9603330059908,
    "finished_at_utc": "2026-09-20T16:49:52.761572+00:00"
  },
  "reference_pdf": {
    "key": "sheetpedia-8d1a4c6dd4f9/reference/reference.pdf",
    "url": "https://corpus.betteroffice.dev/sheetpedia-8d1a4c6dd4f9/reference/reference.pdf?sha256=4e1cf77256edbd39ed4de6adfdb32b7886029f6c28f4aed2a0d30b0cf2333fde",
    "bytes": 22424,
    "sha256": "4e1cf77256edbd39ed4de6adfdb32b7886029f6c28f4aed2a0d30b0cf2333fde"
  },
  "reference_result": {
    "key": "sheetpedia-8d1a4c6dd4f9/reference/result.json",
    "url": "https://corpus.betteroffice.dev/sheetpedia-8d1a4c6dd4f9/reference/result.json?sha256=4a0214d8fab45ad6d1efe21e764208676091e1f86f54682ab11aaca3ec0c0855",
    "bytes": 1742,
    "sha256": "4a0214d8fab45ad6d1efe21e764208676091e1f86f54682ab11aaca3ec0c0855"
  },
  "reference_pages": [
    {
      "key": "sheetpedia-8d1a4c6dd4f9/reference/page_0001.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-8d1a4c6dd4f9/reference/page_0001.png?sha256=004cfb531bedc6753370efd31a38cdb56b361dffbae1f62ad1018b07311c8a9f",
      "bytes": 52554,
      "sha256": "004cfb531bedc6753370efd31a38cdb56b361dffbae1f62ad1018b07311c8a9f"
    }
  ],
  "calculation": {
    "status": "ok",
    "method": "excel-full-rebuild-v1",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "formula_cells": 1,
    "result_cells": 22,
    "empty_results": 0,
    "reference": {
      "key": "sheetpedia-8d1a4c6dd4f9/calculation/reference.json",
      "url": "https://corpus.betteroffice.dev/sheetpedia-8d1a4c6dd4f9/calculation/reference.json?sha256=5ae257889acf29e983e6c9e04a76e9089d2bf3a54fc854c779fe0240b4e50f89",
      "bytes": 6158,
      "sha256": "5ae257889acf29e983e6c9e04a76e9089d2bf3a54fc854c779fe0240b4e50f89"
    },
    "input": {
      "key": "sheetpedia-8d1a4c6dd4f9/calculation/input.xlsx",
      "url": "https://corpus.betteroffice.dev/sheetpedia-8d1a4c6dd4f9/calculation/input.xlsx?sha256=89e9f80d91ba16d19bb5ae1fc319c2e4ab76f14f5e7985a1a274efd8ae6076d4",
      "bytes": 6591,
      "sha256": "89e9f80d91ba16d19bb5ae1fc319c2e4ab76f14f5e7985a1a274efd8ae6076d4"
    }
  }
}
