{
  "schemaVersion": "1.0",
  "benchmarkVersion": "2026-07-31",
  "generatedAt": "2026-07-31T09:16:50.533Z",
  "dataset": {
    "id": "allenai/olmOCR-bench",
    "revision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
    "license": "odc-by"
  },
  "redistribution": "Source PDFs are not republished by PDFtoMDConverter. Each row links to the pinned dataset copy and the original source.",
  "selectionMethod": "Deterministic stratified sample followed by a rendered-page review for English language, legibility, and the declared layout group.",
  "corpus": [
    {
      "id": "BD-01",
      "group": "born-digital",
      "datasetPath": "headers_footers/008086eec0621732163bc07b8aca9fe02e6954af_page_2_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/008086eec0621732163bc07b8aca9fe02e6954af_page_2_processed.pdf",
      "sourceUrl": "https://apps.dtic.mil/dtic/tr/fulltext/u2/a362089.pdf",
      "sha256": "16caa737d2ca8ac4b5f89924b44e7bbcb45ebabcdb0fc4709d83071ae948e3b6",
      "fileBytes": 60779,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "table",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 2
      }
    },
    {
      "id": "BD-02",
      "group": "born-digital",
      "datasetPath": "headers_footers/0188595fce9aeaa5051eb00567ba195bb3ac6e1b_page_1_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/0188595fce9aeaa5051eb00567ba195bb3ac6e1b_page_1_processed.pdf",
      "sourceUrl": "https://www.nsf.gov/statistics/seind12/pdf/c01.pdf",
      "sha256": "95987674dbcdc031c47f5a4c5a706f002cbb848b4166fd350fb22c8c1d38f274",
      "fileBytes": 35828,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "headings",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 1
      }
    },
    {
      "id": "BD-03",
      "group": "born-digital",
      "datasetPath": "headers_footers/029b20b3eb58d1fbda4a16bfea632b29642998ae_page_6_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/029b20b3eb58d1fbda4a16bfea632b29642998ae_page_6_processed.pdf",
      "sourceUrl": "http://www.researchgate.net/profile/Charles_Pontonnier/publication/258552467_Assessing_the_Ability_of_a_VR-based_Assembly_Task_Simulation_to_Evaluate_Physical_Risk_Factors/links/00b7d529f39d5cada9000000.pdf",
      "sha256": "b937d347a248a4686cfeb10b00a793be03c7e413a26151392f7c371b10622125",
      "fileBytes": 277585,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "figure",
        "list",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 1
      }
    },
    {
      "id": "BD-04",
      "group": "born-digital",
      "datasetPath": "headers_footers/0383177b7342945f0657dea30a721222eaa22a81_page_1_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/0383177b7342945f0657dea30a721222eaa22a81_page_1_processed.pdf",
      "sourceUrl": "http://shodhganga.inflibnet.ac.in:8080/jspui/bitstream/10603/116694/2/02_certificate.pdf",
      "sha256": "4ba55055c097c450175ccff8a36b0888048b09789900df4d1eee0b23fee3a250",
      "fileBytes": 45250,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "certificate",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 5
      }
    },
    {
      "id": "BD-05",
      "group": "born-digital",
      "datasetPath": "headers_footers/04cea54b5e3d95140c36cfa315a41be27b2434f9_page_1_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/04cea54b5e3d95140c36cfa315a41be27b2434f9_page_1_processed.pdf",
      "sourceUrl": "http://pubs.ext.vt.edu/content/dam/pubs_ext_vt_edu/4-H/4H-224/4H-224-pdf.pdf",
      "sha256": "66d3c71f0b438eac7af358a633d20b1bbde1dec8302bf7f4e72b12970ced382a",
      "fileBytes": 151612,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "form",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 12
      }
    },
    {
      "id": "BD-06",
      "group": "born-digital",
      "datasetPath": "headers_footers/058e6f6769ff3be73d845a60c90053ee2900d10b_page_3_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/058e6f6769ff3be73d845a60c90053ee2900d10b_page_3_processed.pdf",
      "sourceUrl": "https://repository.ubn.ru.nl/bitstream/handle/2066/67282/67282.pdf",
      "sha256": "cd29589af9c73f2635c1cb6139894660355e9ab10108b147c1eb522c9e654090",
      "fileBytes": 35344,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "dense-text",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 2
      }
    },
    {
      "id": "BD-07",
      "group": "born-digital",
      "datasetPath": "headers_footers/0678963a20825044fed5401fedb69bc7a3e54de6_page_2_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/0678963a20825044fed5401fedb69bc7a3e54de6_page_2_processed.pdf",
      "sourceUrl": "https://kclpure.kcl.ac.uk/portal/files/70102044/Corrigendum_to_Midwifery_continuity_HOMER_Publishedonline31May2017_GOLD_CP_CC_BY_NC_ND_.pdf",
      "sha256": "8e18fb75fa2e7c7a6300ac7ca267ddc231a6c972b5f6b8c5769e2abe592cf7bd",
      "fileBytes": 76431,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "article",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 6
      }
    },
    {
      "id": "BD-08",
      "group": "born-digital",
      "datasetPath": "headers_footers/06f8837dfd6ffb7b8b93427f047f0aa456af2e23_page_1_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/06f8837dfd6ffb7b8b93427f047f0aa456af2e23_page_1_processed.pdf",
      "sourceUrl": "https://embryo.asu.edu/printpdf/13893",
      "sha256": "77805e58be231059b4a34d30c0c3fe5b49f437597bbe6c7cfd13a566fe66cdb2",
      "fileBytes": 7282,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "record",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 2
      }
    },
    {
      "id": "BD-09",
      "group": "born-digital",
      "datasetPath": "headers_footers/0722235b45282fd9c4b9d92efc9dbf6e9704d798_page_2_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/0722235b45282fd9c4b9d92efc9dbf6e9704d798_page_2_processed.pdf",
      "sourceUrl": "https://nlj.gov.jm/wp-content/uploads/2016/10/bn_nettleford_rm_080.pdf",
      "sha256": "1a3502c232f290e8f3434584c53db90f3b1303ce3734d16f46b6ce0bf7722961",
      "fileBytes": 194998,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "schedule",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 2
      }
    },
    {
      "id": "BD-10",
      "group": "born-digital",
      "datasetPath": "headers_footers/0805b42e6e18b9c2f2f3d31d8ecf73e1a422f182_page_2_processed.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/headers_footers/0805b42e6e18b9c2f2f3d31d8ecf73e1a422f182_page_2_processed.pdf",
      "sourceUrl": "http://cellsignet.org.uk/holt/chemistry/holt_chemistry_study_guide_stoichiometry_answer.pdf",
      "sha256": "564f58e00e3bdd1da67d3abd807f2c769263c72ff1fdb1382ebc2b5584c1f84a",
      "fileBytes": 3197,
      "pages": 1,
      "language": "en",
      "features": [
        "single-column",
        "dense-text",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "absent": 3
      }
    },
    {
      "id": "MC-01",
      "group": "multi-column",
      "datasetPath": "multi_column/0a2b678b6c6825364a5a18154dd59064922e_page_8_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/0a2b678b6c6825364a5a18154dd59064922e_page_8_pg1.pdf",
      "sourceUrl": "http://koreanjpathol.org/upload/journal/4404346.pdf",
      "sha256": "d415be97ec5ed102fb66020e077d813c2c3410bedddc047ed6c29a73e5e8c908",
      "fileBytes": 31531,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "references",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 5
      }
    },
    {
      "id": "MC-02",
      "group": "multi-column",
      "datasetPath": "multi_column/0b045ab838c05c4ff1ac844caf826f8f368d_page_18_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/0b045ab838c05c4ff1ac844caf826f8f368d_page_18_pg1.pdf",
      "sourceUrl": "http://www.dod.mil.za/sasoldier/2015/SoldVol22%20no1%20net.pdf",
      "sha256": "431ff40bf79b3bd46ae65f9034d9fe8fbd7969232d3e79048e1c17bf505a3720",
      "fileBytes": 279096,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "article",
        "images",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 2
      }
    },
    {
      "id": "MC-03",
      "group": "multi-column",
      "datasetPath": "multi_column/0145bc47f7ca5f8c5ff1a10481207670bcd3_page_11_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/0145bc47f7ca5f8c5ff1a10481207670bcd3_page_11_pg1.pdf",
      "sourceUrl": "https://bulletin.sfsu.edu/colleges/health-social-sciences/kinesiology/kinesiology.pdf",
      "sha256": "f63d49cad83f3641a3e1b9a19f0972ed86216d358677832ed86d8f0627108aaf",
      "fileBytes": 45546,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "list",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 4
      }
    },
    {
      "id": "MC-04",
      "group": "multi-column",
      "datasetPath": "multi_column/0b045ab838c05c4ff1ac844caf826f8f368d_page_27_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/0b045ab838c05c4ff1ac844caf826f8f368d_page_27_pg1.pdf",
      "sourceUrl": "http://www.dod.mil.za/sasoldier/2015/SoldVol22%20no1%20net.pdf",
      "sha256": "8d85d3250121f0460de7d46b4b2434f3076963206ba9ca5712f9e7efd19936a7",
      "fileBytes": 245736,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "article",
        "images",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 4
      }
    },
    {
      "id": "MC-05",
      "group": "multi-column",
      "datasetPath": "multi_column/09f90a8fad0997f7cf454cbcbe79cab3bc0f_page_1_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/09f90a8fad0997f7cf454cbcbe79cab3bc0f_page_1_pg1.pdf",
      "sourceUrl": "http://aclweb.org/anthology/C00-1043",
      "sha256": "9ef1f05e6512ccfd8e17848a1a38904c5e05f077024b6233c0e1440815c70357",
      "fileBytes": 98855,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "academic",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 5
      }
    },
    {
      "id": "MC-06",
      "group": "multi-column",
      "datasetPath": "multi_column/0208fbb5d6b646f972f4702428ad2cede5c5_page_8_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/0208fbb5d6b646f972f4702428ad2cede5c5_page_8_pg1.pdf",
      "sourceUrl": "https://www.asmr.us/Portals/0/Documents/Conference-Proceedings/1991/0403-Moore.pdf",
      "sha256": "1c876a038e40ecc35081ad223355ad13fe01424bb6ea84aeecf3b15f5e705cd3",
      "fileBytes": 122762,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "table",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 4
      }
    },
    {
      "id": "MC-07",
      "group": "multi-column",
      "datasetPath": "multi_column/038650c9dfd95e7495d0c4d301d9dcca735a_page_1_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/038650c9dfd95e7495d0c4d301d9dcca735a_page_1_pg1.pdf",
      "sourceUrl": "https://catalog.georgiasouthern.edu/undergraduate/allen-paulson-engineering-computing/allen-paulson-engineering-computing.pdf",
      "sha256": "755b92fa3cfc5659c1dbec2d30af148db221732b005e95dcd615d4b9301fb75b",
      "fileBytes": 7849,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "brochure",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 4
      }
    },
    {
      "id": "MC-08",
      "group": "multi-column",
      "datasetPath": "multi_column/0925342e1efabb7957efa34203f65d3cbc4d_page_6_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/0925342e1efabb7957efa34203f65d3cbc4d_page_6_pg1.pdf",
      "sourceUrl": "http://www.nasbe.org/wp-content/uploads/Balek_article_StateLaws_Feb2012.pdf",
      "sha256": "d8bd74d4d250ebdff6e31e4e121c68e76a3a734ea5ed2bfea19b6cf1293366d0",
      "fileBytes": 76200,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "academic",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 5
      }
    },
    {
      "id": "MC-09",
      "group": "multi-column",
      "datasetPath": "multi_column/06125479b00df48e91fe2fb616292d14116d_page_4_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/06125479b00df48e91fe2fb616292d14116d_page_4_pg1.pdf",
      "sourceUrl": "https://www.buffalofieldcampaign.org/images/news-and-media/newsletters/buffalo-field-campaign-newsletter-2019-2020.pdf",
      "sha256": "713ac00e8c95ca3a4dc9881441a1c9ae8d4f98a2e8a9e514ae00c405424d498b",
      "fileBytes": 1506890,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "newsletter",
        "images",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 2
      }
    },
    {
      "id": "MC-10",
      "group": "multi-column",
      "datasetPath": "multi_column/013a3686ef75b4150c07d3ebc510ca2455d6_page_6_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/multi_column/013a3686ef75b4150c07d3ebc510ca2455d6_page_6_pg1.pdf",
      "sourceUrl": "http://oaji.net/articles/2017/1543-1514873987.pdf",
      "sha256": "5975b2bb1a6678df5ef3d05dd3620fef96c25e7dc52c0cfb41300648d0f60dc6",
      "fileBytes": 456418,
      "pages": 1,
      "language": "en",
      "features": [
        "multi-column",
        "academic",
        "reading-order"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "order": 5
      }
    },
    {
      "id": "TB-01",
      "group": "table-heavy",
      "datasetPath": "tables/b5c5b8661b5a272e7a175cdb20d49e67ba0d_pg4.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/tables/b5c5b8661b5a272e7a175cdb20d49e67ba0d_pg4.pdf",
      "sourceUrl": "http://www.aensiweb.com/old/jasa/rjfh/2014/995-1001.pdf",
      "sha256": "7a509c59f5fabf77b4e1f45b87619dfb76773836b0e0d521d9e495cca1cd4084",
      "fileBytes": 134356,
      "pages": 1,
      "language": "en",
      "features": [
        "table",
        "academic",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "table": 7
      }
    },
    {
      "id": "TB-02",
      "group": "table-heavy",
      "datasetPath": "tables/d46c578922389c13e1766994f3fb393a17da_pg15.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/tables/d46c578922389c13e1766994f3fb393a17da_pg15.pdf",
      "sourceUrl": "https://rptsvr1.tea.texas.gov/cgi/sas/broker?_debug=0&_program=perfrept.perfmast.sas&_service=marykay&level=campus&namenum=015910133&prgopt=2017%2Ftapr%2Ftapr.sas&ptype=P&search=campnum&single=N&title=2017+Texas+Academic+Performance+Reports&year2=17&year4=2017",
      "sha256": "47f505cedad656c8347f58496cdeac1d498ae195c530c67ecbb14fccdd4aba3b",
      "fileBytes": 130370,
      "pages": 1,
      "language": "en",
      "features": [
        "table",
        "sparse-page",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "table": 5
      }
    },
    {
      "id": "TB-03",
      "group": "table-heavy",
      "datasetPath": "tables/1651cbb49c05c51fb5a2687130144f94865e_pg2.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/tables/1651cbb49c05c51fb5a2687130144f94865e_pg2.pdf",
      "sourceUrl": "https://cinc.org/archives/2023/pdf/CinC2023-132.pdf",
      "sha256": "6b87ae2adf76b12a615f455c32fe3a486c301d4db18cb49eec6906c97e086b8e",
      "fileBytes": 464801,
      "pages": 1,
      "language": "en",
      "features": [
        "table",
        "academic",
        "equations",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "table": 5
      }
    },
    {
      "id": "TB-04",
      "group": "table-heavy",
      "datasetPath": "tables/9c38972000c33231df815ece46cba559b5b4_pg17.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/tables/9c38972000c33231df815ece46cba559b5b4_pg17.pdf",
      "sourceUrl": "https://misinforeview.hks.harvard.edu/wp-content/uploads/2024/04/traberg_gamified_inoculation_political_ingroups_20240430.pdf",
      "sha256": "0e749613eb1d2ec1c9363580bbe1dc5c33109166eef35630da7cb7aa58a7c930",
      "fileBytes": 130942,
      "pages": 1,
      "language": "en",
      "features": [
        "table",
        "demographics",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "table": 5
      }
    },
    {
      "id": "TB-05",
      "group": "table-heavy",
      "datasetPath": "tables/f828606a3bb8b458fe49a4b6d79b3554961b_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/tables/f828606a3bb8b458fe49a4b6d79b3554961b_pg1.pdf",
      "sourceUrl": "http://www.docum-enter.com/get/K8P1pKVC9ObQifbxSiJGST0hU19Olu7ZItGXiwuH2RY,/AJAX-CLEANER-POWER-OXYGEN-BLEACH-Colgate-Site.pdf",
      "sha256": "32d905b46dd18b813a0c332fe2a5256c183c072860150a7b6f41c74e0c621e49",
      "fileBytes": 29571,
      "pages": 1,
      "language": "en",
      "features": [
        "table",
        "technical-sheet",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "table": 4
      }
    },
    {
      "id": "TB-06",
      "group": "table-heavy",
      "datasetPath": "tables/6046455b109ea0774ecc1d7a86fe30f12863_pg5.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/tables/6046455b109ea0774ecc1d7a86fe30f12863_pg5.pdf",
      "sourceUrl": "https://uhra.herts.ac.uk/bitstream/handle/2299/17838/Using_supermarket_Loyalty_card_data_to_explore_exported_yam_marketing_performance_and_prospects_in_the_UK.pdf?isAllowed=y&sequence=2",
      "sha256": "6ce6e0091ec72dc67e11bd921d90cada687363da802f5dee7d622dcc79141fab",
      "fileBytes": 12209,
      "pages": 1,
      "language": "en",
      "features": [
        "table",
        "academic",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "table": 4
      }
    },
    {
      "id": "TB-07",
      "group": "table-heavy",
      "datasetPath": "tables/1529b213d5db3acb5254d34f81d18e060f28_pg1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/tables/1529b213d5db3acb5254d34f81d18e060f28_pg1.pdf",
      "sourceUrl": "http://www.sanjoseca.gov/DocumentCenter/View/823",
      "sha256": "14467d241201fa6a5db2b323543ee63faab6b385da374a88c318102187f3cc63",
      "fileBytes": 344500,
      "pages": 1,
      "language": "en",
      "features": [
        "table",
        "fact-sheet",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "table": 5
      }
    },
    {
      "id": "TB-08",
      "group": "table-heavy",
      "datasetPath": "tables/8b02fcbf9bc4d7bb680e85c1a3c40f7ef60f_pg3.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/tables/8b02fcbf9bc4d7bb680e85c1a3c40f7ef60f_pg3.pdf",
      "sourceUrl": "http://www.unisim.edu.sg/admissions/Continuing-Education-Admissions/Documents/CCLSDApplicationForm.pdf",
      "sha256": "b5dc153ef20be4797dfa4060619cf56133f76a47c3576e7afeac14d313132597",
      "fileBytes": 40135,
      "pages": 1,
      "language": "en",
      "features": [
        "table",
        "form",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "table": 5
      }
    },
    {
      "id": "SC-01",
      "group": "clear-scanned",
      "datasetPath": "old_scans/1.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/old_scans/1.pdf",
      "sourceUrl": "https://crowd.loc.gov/campaigns/rough-rider-bull-moose-theodore-roosevelt/guns-august/mss382990184/mss382990184-2/",
      "sha256": "c4f7da14c6d0f97576d6346996ede92d7a190f7c6cf5cd191ab4388fbd8d55f5",
      "fileBytes": 547209,
      "pages": 1,
      "language": "en",
      "features": [
        "scan",
        "handwriting",
        "letter"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "present": 2,
        "absent": 1,
        "order": 2
      }
    },
    {
      "id": "SC-02",
      "group": "clear-scanned",
      "datasetPath": "old_scans/2.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/old_scans/2.pdf",
      "sourceUrl": "https://crowd.loc.gov/campaigns/rough-rider-bull-moose-theodore-roosevelt/guns-august/mss382990184/mss382990184-7/",
      "sha256": "b3f48f1a5e265333bcb90aed251af6bc0c3a7b9730eb36365e6322fc0ed121b7",
      "fileBytes": 394811,
      "pages": 1,
      "language": "en",
      "features": [
        "scan",
        "typewritten",
        "letter"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "present": 2,
        "order": 3,
        "absent": 1
      }
    },
    {
      "id": "SC-03",
      "group": "clear-scanned",
      "datasetPath": "old_scans/4.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/old_scans/4.pdf",
      "sourceUrl": "https://crowd.loc.gov/campaigns/rough-rider-bull-moose-theodore-roosevelt/guns-august/mss382990184/mss382990184-9/",
      "sha256": "e2764f0dfcb91095ae4a36a000edf7e7a7d3409a26db6a49f0d290572d440bd1",
      "fileBytes": 420016,
      "pages": 1,
      "language": "en",
      "features": [
        "scan",
        "handwriting",
        "letter"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "present": 2,
        "order": 4,
        "absent": 2
      }
    },
    {
      "id": "SC-04",
      "group": "clear-scanned",
      "datasetPath": "old_scans/6.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/old_scans/6.pdf",
      "sourceUrl": "https://crowd.loc.gov/campaigns/rough-rider-bull-moose-theodore-roosevelt/guns-august/mss382990184/mss382990184-13/",
      "sha256": "a37f7c0a25f9343695dcf1ede30b59b5db6e09c23ac201f7eb3414f76f1b57a4",
      "fileBytes": 432684,
      "pages": 1,
      "language": "en",
      "features": [
        "scan",
        "typewritten",
        "letter"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "present": 2,
        "order": 1,
        "absent": 2
      }
    },
    {
      "id": "SC-05",
      "group": "clear-scanned",
      "datasetPath": "old_scans/10.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/old_scans/10.pdf",
      "sourceUrl": "https://crowd.loc.gov/campaigns/rough-rider-bull-moose-theodore-roosevelt/guns-august/mss382990184/mss382990184-17/",
      "sha256": "242ef89e604531048eead50adbe2d7dd686576192982b4976b54fa2cc45e966d",
      "fileBytes": 401812,
      "pages": 1,
      "language": "en",
      "features": [
        "scan",
        "typewritten",
        "letter"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "present": 3,
        "order": 2,
        "absent": 2
      }
    },
    {
      "id": "SC-06",
      "group": "clear-scanned",
      "datasetPath": "old_scans/11.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/old_scans/11.pdf",
      "sourceUrl": "https://crowd.loc.gov/campaigns/rough-rider-bull-moose-theodore-roosevelt/guns-august/mss382990184/mss382990184-18/",
      "sha256": "42655b09a4b053665df7401a857ecf9538791524c71db79cc431c646848dc4aa",
      "fileBytes": 308805,
      "pages": 1,
      "language": "en",
      "features": [
        "scan",
        "typewritten",
        "letter"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "present": 2,
        "order": 2,
        "absent": 2
      }
    },
    {
      "id": "SH-01",
      "group": "figures-lists-headings",
      "datasetPath": "arxiv_math/2503.07228_pg12.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/arxiv_math/2503.07228_pg12.pdf",
      "sourceUrl": "https://arxiv.org/pdf/2503.07228",
      "sha256": "f6458e5ade7f79e1bcc37246f88c1209e9c842cff54cc5c0d6269c4ba863e216",
      "fileBytes": 206556,
      "pages": 1,
      "language": "en",
      "features": [
        "figure",
        "caption",
        "theorem",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "math": 1
      }
    },
    {
      "id": "SH-02",
      "group": "figures-lists-headings",
      "datasetPath": "arxiv_math/2503.08077_pg42.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/arxiv_math/2503.08077_pg42.pdf",
      "sourceUrl": "https://arxiv.org/pdf/2503.08077",
      "sha256": "6128b34b1edeeaca31a0d9ed12550847b9a17fb2e50a94c7741b766058063dd1",
      "fileBytes": 40717,
      "pages": 1,
      "language": "en",
      "features": [
        "heading",
        "ordered-list",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "math": 1
      }
    },
    {
      "id": "SH-03",
      "group": "figures-lists-headings",
      "datasetPath": "arxiv_math/2503.05614_pg12.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/arxiv_math/2503.05614_pg12.pdf",
      "sourceUrl": "https://arxiv.org/pdf/2503.05614",
      "sha256": "2d88be39e77a9197e1cdf2c493330a455ad1b935e7f823ce1dc7d795882cedd4",
      "fileBytes": 215103,
      "pages": 1,
      "language": "en",
      "features": [
        "heading",
        "steps",
        "theorem",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "math": 6
      }
    },
    {
      "id": "SH-04",
      "group": "figures-lists-headings",
      "datasetPath": "arxiv_math/2503.05717_pg14.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/arxiv_math/2503.05717_pg14.pdf",
      "sourceUrl": "https://arxiv.org/pdf/2503.05717",
      "sha256": "2fe4f578613c06814c7865deabcb9e8aee6f1af1638b06a29e57b56bf8db3f6e",
      "fileBytes": 428888,
      "pages": 1,
      "language": "en",
      "features": [
        "heading",
        "figure",
        "caption",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "math": 3
      }
    },
    {
      "id": "SH-05",
      "group": "figures-lists-headings",
      "datasetPath": "arxiv_math/2503.07251_pg28.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/arxiv_math/2503.07251_pg28.pdf",
      "sourceUrl": "https://arxiv.org/pdf/2503.07251",
      "sha256": "25553b9db091c0ac33547519b2ed1264ed53fd4d33c341f7a8a2a61675dcbd5c",
      "fileBytes": 229175,
      "pages": 1,
      "language": "en",
      "features": [
        "heading",
        "figure",
        "caption",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "math": 3
      }
    },
    {
      "id": "SH-06",
      "group": "figures-lists-headings",
      "datasetPath": "arxiv_math/2503.08646_pg17.pdf",
      "datasetUrl": "https://huggingface.co/datasets/allenai/olmOCR-bench/blob/54a96a6fb6a2bd3b297e59869491db4d3625b711/bench_data/pdfs/arxiv_math/2503.08646_pg17.pdf",
      "sourceUrl": "https://arxiv.org/pdf/2503.08646",
      "sha256": "5677caa8b6c011ad1d86c8168688d8ca8e79594831f45bf54ebb23165d21e5b3",
      "fileBytes": 188950,
      "pages": 1,
      "language": "en",
      "features": [
        "heading-hierarchy",
        "lemma",
        "proof",
        "text-layer"
      ],
      "sourceDataset": "allenai/olmOCR-bench",
      "sourceDatasetRevision": "54a96a6fb6a2bd3b297e59869491db4d3625b711",
      "sourceDatasetLicense": "odc-by",
      "assertionCounts": {
        "math": 9
      }
    }
  ]
}
