{
  "schema_version": 1,
  "id": "office-quality",
  "samples": [
    "betteroffice-demo",
    "betteroffice-slides",
    "betteroffice-workbook",
    "bo-corpus-1",
    "bo-corpus-2",
    "bo-corpus-3",
    "bo-corpus-4",
    "bo-corpus-5",
    "bo-corpus-6",
    "bo-pptx-corpus-1",
    "bo-pptx-corpus-2",
    "smart-mailbox-lab-notebook",
    "smart-mailbox-final-report",
    "southeast-university-thesis",
    "beihang-university-thesis",
    "eventsphere-conference-brochure",
    "manchester-phd-thesis",
    "documize-business-requirements",
    "smart-mailbox-final-presentation",
    "bioinformatics-randomness-chaos",
    "bioinformatics-score-matrix",
    "physics-motion-real-life",
    "diagnosing-problems",
    "neural-network-excel",
    "sudoku-help",
    "vietnamese-lunar-calendar",
    "bootstrapping-calculator",
    "monolith-first-microservices",
    "nanogpt-excel",
    "ultimate-excel-gantt",
    "wazobia-valuation-model",
    "oxi-en-administrative-01",
    "oxi-en-administrative-02",
    "oxi-en-administrative-03",
    "oxi-en-administrative-04",
    "oxi-en-correspondence-01",
    "oxi-en-correspondence-02",
    "oxi-en-correspondence-03",
    "oxi-en-correspondence-04",
    "oxi-en-creative-01",
    "oxi-en-creative-02",
    "oxi-en-creative-03",
    "oxi-en-creative-04",
    "oxi-en-educational-01",
    "oxi-en-educational-02",
    "oxi-en-educational-03",
    "oxi-en-educational-04",
    "oxi-en-forms-01",
    "oxi-en-forms-02",
    "oxi-en-forms-03",
    "oxi-en-forms-04",
    "oxi-en-legal-01",
    "oxi-en-legal-03",
    "oxi-en-legal-04",
    "oxi-en-policies-01",
    "oxi-en-policies-02",
    "oxi-en-policies-03",
    "oxi-en-policies-04",
    "oxi-en-reference-01",
    "oxi-en-reference-02",
    "oxi-en-reference-03",
    "oxi-en-reference-04",
    "oxi-en-reports-01",
    "oxi-en-reports-02",
    "oxi-en-reports-03",
    "oxi-en-reports-04",
    "oxi-en-technical-01",
    "oxi-en-technical-02",
    "oxi-en-technical-03",
    "oxi-en-technical-04",
    "oxi-ja-administrative-01",
    "oxi-ja-correspondence-01",
    "oxi-ja-creative-01",
    "oxi-ja-educational-01",
    "oxi-ja-forms-01",
    "oxi-ja-legal-01",
    "oxi-ja-policies-01",
    "oxi-ja-reference-01",
    "oxi-ja-reports-01",
    "oxi-ja-technical-01",
    "pptx-prstgeom-600",
    "pptarena-001-original",
    "pptarena-002-original",
    "pptarena-003-original",
    "pptarena-004-original",
    "pptarena-005-original",
    "pptarena-006-original",
    "pptarena-007-original",
    "pptarena-008-original",
    "pptarena-009-original",
    "pptarena-010-original",
    "pptarena-011-original",
    "pptarena-013-original",
    "pptarena-014-original",
    "pptarena-015-original",
    "pptarena-016-original",
    "pptarena-018-original",
    "pptarena-019-original",
    "pptarena-021-original",
    "pptarena-022-original",
    "pptarena-023-original",
    "pptarena-024-original",
    "pptarena-025-original",
    "pptarena-026-original",
    "pptarena-027-original",
    "pptarena-028-original",
    "pptarena-029-original",
    "pptarena-030-original",
    "pptarena-031-original",
    "pptarena-032-original",
    "pptarena-033-original",
    "pptarena-034-original",
    "pptarena-036-original",
    "pptarena-037-original",
    "pptarena-038-original",
    "pptarena-039-original",
    "pptarena-040-original",
    "pptarena-041-original",
    "pptarena-042-original",
    "pptarena-043-original",
    "pptarena-044-original",
    "pptarena-045-original",
    "pptarena-046-original",
    "pptarena-047-original",
    "pptarena-048-original",
    "pptarena-049-original",
    "pptarena-050-original",
    "pptarena-051-original",
    "pptarena-052-original",
    "pptarena-053-original",
    "pptarena-054-original",
    "pptarena-055-original",
    "pptarena-056-original",
    "pptarena-057-original",
    "pptarena-058-original",
    "pptarena-059-original",
    "pptarena-060-original",
    "pptarena-061-original",
    "pptarena-062-original",
    "pptarena-063-original",
    "pptarena-064-original",
    "pptarena-065-original",
    "pptarena-067-original",
    "pptarena-068-original",
    "pptarena-069-original",
    "pptarena-070-original",
    "pptarena-071-original",
    "pptarena-072-original",
    "pptarena-073-original",
    "pptarena-074-original",
    "pptarena-075-original",
    "pptarena-076-original",
    "pptarena-077-original",
    "pptarena-078-original",
    "pptarena-079-original",
    "pptarena-080-original",
    "pptarena-081-original",
    "pptarena-082-original",
    "pptarena-083-original",
    "pptarena-084-original",
    "pptarena-085-original",
    "pptarena-086-original",
    "pptarena-087-original",
    "pptarena-089-original",
    "pptarena-090-original",
    "pptarena-092-original",
    "pptarena-093-original",
    "pptarena-094-original",
    "pptarena-095-original",
    "pptarena-096-original",
    "pptarena-097-original",
    "pptarena-098-original",
    "pptarena-099-original",
    "pptarena-100-original",
    "sheetpedia-7347e836f3f2",
    "sheetpedia-06dfb94ff719",
    "sheetpedia-42b483f5c39a",
    "sheetpedia-74473dadbea7",
    "sheetpedia-dd558ef9c3db",
    "sheetpedia-34f529371b9a",
    "sheetpedia-105ac0842f63",
    "sheetpedia-6bd30227165d",
    "sheetpedia-20d67552f967",
    "sheetpedia-8a3dfc6b3060",
    "sheetpedia-4d2cd2b10a09",
    "sheetpedia-4082e5cdf31e",
    "sheetpedia-59391be4f5a0",
    "sheetpedia-902731188490",
    "sheetpedia-6aa341ed337f",
    "sheetpedia-985b1b709b16",
    "sheetpedia-43f7ab807328",
    "sheetpedia-ea9341457db5",
    "sheetpedia-28f9a8c508de",
    "sheetpedia-139476188761",
    "sheetpedia-6a7796525d96",
    "sheetpedia-517dc2896b7e",
    "sheetpedia-18185ead4857",
    "sheetpedia-3d93bb64f768",
    "sheetpedia-5bbcdf167180",
    "sheetpedia-0ff81d043db0",
    "sheetpedia-ee4a6cf692ec",
    "sheetpedia-c70e22c95a64",
    "sheetpedia-08ebe4583658",
    "sheetpedia-8c5593ba9fce",
    "sheetpedia-1c26b6e9518d",
    "sheetpedia-6c82599b29f3",
    "sheetpedia-f0f02fe53bb5",
    "sheetpedia-776bf812eada",
    "sheetpedia-93e5b9168301",
    "sheetpedia-e0bfa459074e",
    "sheetpedia-68cce866f789",
    "sheetpedia-919b230e45a7",
    "sheetpedia-8d1a4c6dd4f9",
    "sheetpedia-d72939b08fd0",
    "sheetpedia-1dc7ab583225",
    "sheetpedia-34e6bcc63f17",
    "sheetpedia-6801ea3eb08e",
    "sheetpedia-bef6e2bb3ccd",
    "sheetpedia-fa8fe2628005",
    "sheetpedia-3277e228c0a4",
    "sheetpedia-ee99f92f597a",
    "sheetpedia-43fcd35581c4",
    "sheetpedia-d599ac62355a",
    "sheetpedia-28858919ff39",
    "sheetpedia-56d536795ccf",
    "sheetpedia-e8ee46be829a",
    "sheetpedia-def4407b7c16",
    "sheetpedia-8dc99d663d40",
    "sheetpedia-6f3940c8975e",
    "sheetpedia-99f6de9c3ac2",
    "sheetpedia-9eaec72339d9",
    "sheetpedia-99b56786f452",
    "sheetpedia-45ffadcd6932",
    "sheetpedia-854bc567af10",
    "sheetpedia-9cd644ecf8b4",
    "sheetpedia-8c0c8ce37e02",
    "sheetpedia-07937e67f4e6",
    "sheetpedia-c58f053127b9",
    "sheetpedia-d1974a271800",
    "sheetpedia-bbac0126884a",
    "sheetpedia-83e5752a57eb",
    "sheetpedia-188abb653c0e",
    "sheetpedia-49b8fcfc6e20",
    "sheetpedia-439df6bf4b6f",
    "sheetpedia-f9fd91a97d12",
    "sheetpedia-58e0d15358b7",
    "sheetpedia-26bb0bfaf865",
    "sheetpedia-0b956612356a",
    "sheetpedia-96fa93ce94ea",
    "sheetpedia-572302a00041",
    "sheetpedia-17f1b6fefcf7",
    "sheetpedia-4d18668f1d35",
    "sheetpedia-9022dc77351f",
    "sheetpedia-591b7ed44ccc",
    "sheetpedia-be8a562bd31f",
    "sheetpedia-15aca2e9bcc6",
    "sheetpedia-e001b8b8d24b",
    "sheetpedia-f45771248847",
    "sheetpedia-2975539b5a6b",
    "sheetpedia-926aa416109c",
    "sheetpedia-62d9544d67c0",
    "sheetpedia-1f19bbd44081",
    "sheetpedia-8bebcded83a6",
    "sheetpedia-6283745cfcad",
    "sheetpedia-39216b0e11e0",
    "sheetpedia-3467cf953d51",
    "sheetpedia-eb5de1652388",
    "sheetpedia-19a4d7b0950a",
    "sheetpedia-95669c96cc24",
    "sheetpedia-9b13ef8593b1",
    "sheetpedia-9eaddd49cfb3",
    "sheetpedia-56615b805d7a",
    "sheetpedia-491800d7851b",
    "sheetpedia-441e60078db9",
    "sheetpedia-4737a0c9b501",
    "sheetpedia-4d821c56ff0d",
    "sheetpedia-a7e9f56a267e",
    "sheetpedia-4dac2b7d543f",
    "sheetpedia-a3ff9cc8c544",
    "sheetpedia-2460d329d97a",
    "sheetpedia-9e69d08e70b2",
    "sheetpedia-65e61fa006c0",
    "sheetpedia-c1ed94ab5c8e",
    "sheetpedia-d71f614397dd",
    "sheetpedia-10410220661b",
    "sheetpedia-e10ab3ab294e",
    "sheetpedia-a4a33f2313cb",
    "sheetpedia-fecbca069584",
    "sheetpedia-d99e54f77be9",
    "sheetpedia-f155b9332371",
    "sheetpedia-f30c42b48da1",
    "sheetpedia-17652b4e3c54",
    "sheetpedia-2776218cd789",
    "sheetpedia-ec83209e6108",
    "sheetpedia-fd5e0893788b",
    "sheetpedia-5b3f56dd2f3c",
    "sheetpedia-547ebdb53982",
    "sheetpedia-3bdba19fedb1",
    "sheetpedia-0cf1a24127a2",
    "sheetpedia-ad3cdb669ec6",
    "sheetpedia-a6ee0804e49b",
    "sheetpedia-eef92b8f29bb",
    "sheetpedia-70a5b34f16bb",
    "sheetpedia-738df30d7382",
    "sheetpedia-97b21cacd0ad",
    "sheetpedia-5abb5323f99f",
    "sheetpedia-b8c6f0158a9d",
    "sheetpedia-1a05d6ba7060",
    "sheetpedia-8e264b584575",
    "sheetpedia-82e6ebae682a",
    "sheetpedia-c428c71f6910",
    "sheetpedia-af32b6c57e5d",
    "sheetpedia-d74a46f39665",
    "sheetpedia-44c2bd8982c5",
    "sheetpedia-0bf768c09e0f",
    "sheetpedia-e45090697973",
    "sheetpedia-4bab9e672741",
    "sheetpedia-e784e67e038c",
    "sheetpedia-3f7200a3296a",
    "sheetpedia-2bc185c5a657",
    "sheetpedia-d2927d7e358e",
    "sheetpedia-caa20c2b6f69",
    "sheetpedia-3396a481f802",
    "sheetpedia-d360e047f5b1",
    "sheetpedia-1f8ed604a172",
    "sheetpedia-3ecc6a08b5dc",
    "sheetpedia-83e6c6474ea4",
    "sheetpedia-cb9ed597be7b",
    "sheetpedia-b615abf0c060",
    "sheetpedia-4511182b7a84",
    "sheetpedia-3292b63fc3cb",
    "sheetpedia-7db33690232e",
    "sheetpedia-39eedb9db980",
    "sheetpedia-5a1219ad18cd",
    "sheetpedia-54e65a10c0cf",
    "sheetpedia-37214dd14b6c",
    "sheetpedia-4f81471db9f0",
    "sheetpedia-169681ab5618",
    "sheetpedia-7ba2d52635e9",
    "sheetpedia-a2989efe5873",
    "sheetpedia-91e613e07d4c",
    "sheetpedia-55592fb4c917",
    "sheetpedia-12563fd12dac",
    "sheetpedia-e11da71f6bc3",
    "sheetpedia-17828546dc1f",
    "sheetpedia-6fb6e15f8028",
    "sheetpedia-813bf3bbd814",
    "sheetpedia-f2cd5b022055",
    "sheetpedia-6a14da74d219",
    "sheetpedia-ee8652dae9e9",
    "sheetpedia-a8cbf140a275",
    "sheetpedia-acbc9a804621",
    "sheetpedia-534968835445",
    "sheetpedia-32191cadabe5",
    "sheetpedia-2d79536d42ef",
    "sheetpedia-a89721f02598",
    "sheetpedia-ba534ed2827e",
    "sheetpedia-410dfc9dc73c",
    "sheetpedia-ba40611964da",
    "sheetpedia-429c0fa955d2",
    "sheetpedia-25354e52a7b6",
    "sheetpedia-9f53a01ab0cb",
    "sheetpedia-f816aa5a71ce",
    "sheetpedia-1e96498cd91a",
    "sheetpedia-3e1902bccbb4",
    "sheetpedia-46ea135b2e94",
    "sheetpedia-6a33413924cc",
    "sheetpedia-c75dec45c005",
    "sheetpedia-0836a4ee7416",
    "sheetpedia-f0bf23e833f9",
    "sheetpedia-4eec0efcd659",
    "sheetpedia-096efab987c6",
    "sheetpedia-c77e98a3c316",
    "sheetpedia-0f83a00cef46"
  ],
  "community_report": "https://corpus.betteroffice.dev/reports/community-20260913.json",
  "title": "BetterOffice corpus",
  "summary": {
    "samples": 374,
    "pptarena_decks": 93,
    "pptarena_reference_pages": 835,
    "pptarena_source_bytes": 145952340,
    "formats": {
      "docx": 63,
      "pptx": 103,
      "xlsx": 208
    },
    "sheetpedia_workbooks": 200,
    "sheetpedia_reference_pages": 281,
    "sheetpedia_source_bytes": 5234641
  },
  "datasets": [
    {
      "id": "pptarena",
      "url": "https://huggingface.co/datasets/mofengenden/PPTArena",
      "report": "https://corpus.betteroffice.dev/datasets/pptarena/import.json",
      "samples": 93
    },
    {
      "id": "sheetpedia",
      "url": "https://corpus.betteroffice.dev/datasets/sheetpedia/index.html",
      "report": "https://corpus.betteroffice.dev/datasets/sheetpedia/import.json",
      "license": "CC-BY-SA-4.0",
      "samples": 200
    }
  ],
  "updated_at_utc": "2026-09-20T17:50:21.220Z"
}
