{
  "schema_version": 1,
  "id": "sheetpedia-59391be4f5a0",
  "format": "xlsx",
  "title": "Sheetpedia: help with part number extraction from cell contents that contain text extract pn aligw",
  "published_at_utc": "2026-09-20T16:48:31.270103+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_0929/747834d1631718389-help-with-part-number-extraction-from-cell-contents-that-contain-text-extract-pn-aligw.xlsx",
    "upstream_filename": "747834d1631718389-help-with-part-number-extraction-from-cell-contents-that-contain-text-extract-pn-aligw.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-59391be4f5a0/source.xlsx",
    "url": "https://corpus.betteroffice.dev/sheetpedia-59391be4f5a0/source.xlsx?sha256=59391be4f5a022afd00e3383d3761897ac9ba9a04405abe8504846e847cc7a23",
    "bytes": 8387,
    "sha256": "59391be4f5a022afd00e3383d3761897ac9ba9a04405abe8504846e847cc7a23"
  },
  "worksheet_count": 1,
  "features": {
    "styles": 5,
    "fonts": 3,
    "fills": 3,
    "borders": 1,
    "number_formats": 0,
    "cells": 362,
    "formulas": 103,
    "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": {
      "TRIM": 82,
      "SUBSTITUTE": 175,
      "RIGHT": 10,
      "REPT": 64,
      "SUM": 27,
      "ROUND": 9,
      "MOD": 9,
      "SMALL": 9,
      "IFERROR": 9,
      "ROW": 220,
      "OFFSET": 54,
      "LEN": 54,
      "MID": 183,
      "N": 18,
      "ISNUMBER": 101,
      "LEFT": 45,
      "MIN": 81,
      "IF": 82
    },
    "wrapped_styles": 0,
    "rotated_styles": 0,
    "custom_font_names": [
      "Calibri",
      "Verdana"
    ]
  },
  "worksheets": [
    {
      "index": 0,
      "name": "Sheet1 (2)",
      "state": "visible",
      "cells": 362,
      "bounds": [
        1,
        1,
        100,
        17
      ],
      "formulas": 103,
      "merges": 0,
      "conditional_rules": 0,
      "tables": 0,
      "drawings": 0
    }
  ],
  "validation": {
    "archive_crc": "ok",
    "xml": "ok",
    "source_hash": "verified against pinned archive member",
    "expanded_bytes": 45619,
    "reference": "one PDF page per recorded range; nonempty raster; source SHA-256 matched"
  },
  "selection": {
    "filename_group": "named",
    "layout_signature": "8a20f8231d3dc9f6bb448dd52a9e84af75a4dfe78730dd9ac833a3fe21aacbe0",
    "method_url": "https://corpus.betteroffice.dev/datasets/sheetpedia/import.json"
  },
  "reference": {
    "source": "59391be4f5a022afd00e3383d3761897ac9ba9a04405abe8504846e847cc7a23.xlsx",
    "sha256": "59391be4f5a022afd00e3383d3761897ac9ba9a04405abe8504846e847cc7a23",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "os": "26.2",
    "dpi": 150,
    "export": "local PDF",
    "status": "ok",
    "started_at_utc": "2026-09-20T16:48:26.296224+00:00",
    "capture_profile": {
      "scale_percent": 75,
      "margin_pt": 18,
      "pages": [
        {
          "sheet": 0,
          "range": "A1:I44",
          "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": "59391be4f5a022afd00e3383d3761897ac9ba9a04405abe8504846e847cc7a23",
          "author": "",
          "subject": "",
          "keywords": "",
          "creator": "Excel",
          "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
          "creationDate": "D:20260920164827Z00'00'",
          "modDate": "D:20260920164827Z00'00'",
          "trapped": "",
          "encryption": null
        }
      ]
    },
    "pages": 1,
    "fonts": [
      "AAAAAC+Calibri-Bold",
      "AAAAAE+Calibri",
      "AAAAAF+Verdana"
    ],
    "pdf_metadata": {
      "format": "PDF 1.7",
      "title": "59391be4f5a022afd00e3383d3761897ac9ba9a04405abe8504846e847cc7a23",
      "author": "",
      "subject": "",
      "keywords": "",
      "creator": "Excel",
      "producer": "macOS Version 26.2 (Build 25C56) Quartz PDFContext",
      "creationDate": "D:20260920164827Z00'00'",
      "modDate": "D:20260920164827Z00'00'",
      "trapped": "",
      "encryption": null
    },
    "ms": 1429.722832981497,
    "finished_at_utc": "2026-09-20T16:48:27.727006+00:00"
  },
  "reference_pdf": {
    "key": "sheetpedia-59391be4f5a0/reference/reference.pdf",
    "url": "https://corpus.betteroffice.dev/sheetpedia-59391be4f5a0/reference/reference.pdf?sha256=4c636758042b06b381f09819beb75660dbed9b9d19a1d540951df3f1435b543d",
    "bytes": 47276,
    "sha256": "4c636758042b06b381f09819beb75660dbed9b9d19a1d540951df3f1435b543d"
  },
  "reference_result": {
    "key": "sheetpedia-59391be4f5a0/reference/result.json",
    "url": "https://corpus.betteroffice.dev/sheetpedia-59391be4f5a0/reference/result.json?sha256=01ecd284f7b959aa98e7922d6b646f9a4e6aad343345ef050a098d6f1ed08b1a",
    "bytes": 1878,
    "sha256": "01ecd284f7b959aa98e7922d6b646f9a4e6aad343345ef050a098d6f1ed08b1a"
  },
  "reference_pages": [
    {
      "key": "sheetpedia-59391be4f5a0/reference/page_0001.png",
      "url": "https://corpus.betteroffice.dev/sheetpedia-59391be4f5a0/reference/page_0001.png?sha256=ceef941bb0869d3e5eeca67ec4e8f9fb324f071f8107e490b84f1829696307ef",
      "bytes": 167826,
      "sha256": "ceef941bb0869d3e5eeca67ec4e8f9fb324f071f8107e490b84f1829696307ef"
    }
  ],
  "calculation": {
    "status": "ok",
    "method": "excel-full-rebuild-v1",
    "engine": "Microsoft Excel",
    "version": "16.112.3",
    "formula_cells": 103,
    "result_cells": 397,
    "empty_results": 0,
    "reference": {
      "key": "sheetpedia-59391be4f5a0/calculation/reference.json",
      "url": "https://corpus.betteroffice.dev/sheetpedia-59391be4f5a0/calculation/reference.json?sha256=b4d5fed8c0783427bdb5af79280a77a4eed1155d5faed62dd529c36dd973248a",
      "bytes": 73572,
      "sha256": "b4d5fed8c0783427bdb5af79280a77a4eed1155d5faed62dd529c36dd973248a"
    },
    "input": {
      "key": "sheetpedia-59391be4f5a0/calculation/input.xlsx",
      "url": "https://corpus.betteroffice.dev/sheetpedia-59391be4f5a0/calculation/input.xlsx?sha256=f38993e021773a06aec5c3b6a55a99f67a8ba96bfa5b2e96d5fe4a9255138006",
      "bytes": 8254,
      "sha256": "f38993e021773a06aec5c3b6a55a99f67a8ba96bfa5b2e96d5fe4a9255138006"
    }
  }
}