{ "schemaVersion": "1.0", "benchmarkVersion": "2026-07-31", "status": "completed", "distributionReady": true, "distributionEvidence": { "status": "production_technical_acceptance_passed", "verifiedAt": "2026-07-31", "checks": [ "Production research page returned HTTP 200.", "Title, description, canonical, robots, schema, sitemap, and footer entry were verified.", "All eight versioned benchmark assets returned HTTP 200." ] }, "title": "Best PDF to Markdown Converter: Benchmarking OCR, Tables and Reading Order", "primaryKeyword": "best pdf to markdown converter", "publishedAt": "2026-07-31", "updatedAt": "2026-07-31", "disclosure": "PDFtoMDConverter publishes this benchmark and is one of the systems tested. Results use the same selected corpus and declared metric code for every system.", "corpusSource": { "id": "allenai/olmOCR-bench", "revision": "54a96a6fb6a2bd3b297e59869491db4d3625b711", "license": "odc-by" }, "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 } } ], "systems": [ { "id": "pdftomdconverter", "name": "PDFtoMDConverter", "version": "a840a9378871d378b1a0993444e73ed3cdf45595", "configuration": { "pipeline": "browser text layer with local OCR fallback", "browser": "Chromium 150.0.7871.187", "execution": "local", "nonReadRequests": 0 }, "machine": { "platform": "darwin 25.5.0", "machine": "arm64", "processor": "Apple M5", "logicalCpuCount": 10, "memoryBytes": 34359738368, "node": "v26.0.0" }, "warmup": { "documentId": "SC-02", "runtimeMs": 17647.77, "excludedFromResults": true }, "completedDocuments": 39, "metrics": { "digitalTextFidelity": { "meanF1": 0.9669544315395993, "documents": 33 }, "scannedTextRecall": { "passed": 3, "total": 13, "rate": 0.23076923076923078 }, "readingOrder": { "passed": 13, "total": 52, "rate": 0.25 }, "headingHierarchy": { "passed": 0, "total": 14, "rate": 0 }, "tableStructure": { "passed": 26, "total": 40, "rate": 0.65 }, "markdownParseSuccess": { "passed": 39, "total": 39, "rate": 1 }, "runtime": { "medianMs": 534.1, "meanMs": 2078.732307692308, "documents": 39 } } }, { "id": "docling", "name": "Docling", "version": "2.117.0", "configuration": { "pipeline": "standard", "ocr": "RapidOCR PyTorch English", "tables": "TableFormer accurate", "threads": 4, "accelerator": "MPS where supported; RapidOCR CPU", "execution": "local" }, "machine": { "platform": "macOS-26.5.1-arm64-arm-64bit", "machine": "arm64", "processor": "arm", "python": "3.11.15" }, "warmup": { "documentId": "BD-01", "runtimeMs": 14314.83, "excludedFromResults": true }, "completedDocuments": 40, "metrics": { "digitalTextFidelity": { "meanF1": 0.8851805052486258, "documents": 34 }, "scannedTextRecall": { "passed": 7, "total": 13, "rate": 0.5384615384615384 }, "readingOrder": { "passed": 32, "total": 54, "rate": 0.5925925925925926 }, "headingHierarchy": { "passed": 5, "total": 14, "rate": 0.35714285714285715 }, "tableStructure": { "passed": 38, "total": 40, "rate": 0.95 }, "markdownParseSuccess": { "passed": 40, "total": 40, "rate": 1 }, "runtime": { "medianMs": 1494.1750000000002, "meanMs": 4623.253250000001, "documents": 40 } } }, { "id": "marker", "name": "Marker", "version": "2.0.0", "configuration": { "mode": "fast", "output_format": "markdown", "disable_image_extraction": true, "disable_tqdm": true, "llmService": null, "inferenceBackend": "llamacpp", "llamaCpp": "b10199", "accelerator": "MPS", "execution": "local" }, "machine": { "platform": "macOS-26.5.1-arm64-arm-64bit", "machine": "arm64", "processor": "arm", "python": "3.11.15" }, "warmup": { "documentId": "BD-02", "runtimeMs": 46042.1, "excludedFromResults": true }, "completedDocuments": 40, "metrics": { "digitalTextFidelity": { "meanF1": 0.9023527706816508, "documents": 34 }, "scannedTextRecall": { "passed": 12, "total": 13, "rate": 0.9230769230769231 }, "readingOrder": { "passed": 44, "total": 54, "rate": 0.8148148148148148 }, "headingHierarchy": { "passed": 5, "total": 14, "rate": 0.35714285714285715 }, "tableStructure": { "passed": 31, "total": 40, "rate": 0.775 }, "markdownParseSuccess": { "passed": 40, "total": 40, "rate": 1 }, "runtime": { "medianMs": 1089.86, "meanMs": 12596.811999999996, "documents": 40 } } }, { "id": "markitdown", "name": "Microsoft MarkItDown", "version": "0.1.7", "configuration": { "plugins": false, "azureDocumentIntelligence": false, "execution": "local" }, "machine": { "platform": "macOS-26.5.1-arm64-arm-64bit", "machine": "arm64", "processor": "arm", "python": "3.11.15" }, "warmup": { "documentId": "BD-01", "runtimeMs": 49.31, "excludedFromResults": true }, "completedDocuments": 40, "metrics": { "digitalTextFidelity": { "meanF1": 0.9374471023995781, "documents": 34 }, "scannedTextRecall": { "passed": 0, "total": 13, "rate": 0 }, "readingOrder": { "passed": 18, "total": 54, "rate": 0.3333333333333333 }, "headingHierarchy": { "passed": 0, "total": 14, "rate": 0 }, "tableStructure": { "passed": 9, "total": 40, "rate": 0.225 }, "markdownParseSuccess": { "passed": 40, "total": 40, "rate": 1 }, "runtime": { "medianMs": 41.97, "meanMs": 44.88749999999999, "documents": 40 } } } ], "results": [ { "documentId": "BD-01", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 531.18, "outputBytes": 2080, "outputSha256": "802e6975c07ba079e026a5a9b3be06fc2a40f0d687ebb4797cffbbc6989ff477", "outputFile": "pdftomdconverter/markdown/BD-01.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 0.9939024390243902, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-02", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 424.1, "outputBytes": 4056, "outputSha256": "c123ccf5c6d27f17e49bef3419119597e19c9c9b3f6963e5d2cc0567cebafa27", "outputFile": "pdftomdconverter/markdown/BD-02.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-03", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 531.9, "outputBytes": 947, "outputSha256": "5d0b5b00edffbafc4213a35e63b057917de0c68f5caf383bbdea17656212f142", "outputFile": "pdftomdconverter/markdown/BD-03.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 0.9898989898989898, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-04", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 527.09, "outputBytes": 1152, "outputSha256": "b55f6287a669207fbcdf48ae457d669939fb554444a36738b53467871ac6acea", "outputFile": "pdftomdconverter/markdown/BD-04.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 0.9794721407624634, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-05", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 526.45, "outputBytes": 3233, "outputSha256": "388ee8a21e6a4aa469148a8869a1ffcaf9cbc413d4eaa8729712873d6fc56ad4", "outputFile": "pdftomdconverter/markdown/BD-05.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 0.9958041958041959, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-06", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 527.75, "outputBytes": 3870, "outputSha256": "b0080711117ee1e0aa4d7f3ded92a7ad1abc942c5bac1ebb2734bc5e8e7b3151", "outputFile": "pdftomdconverter/markdown/BD-06.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 0.9965156794425087, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-07", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 527.64, "outputBytes": 2044, "outputSha256": "96d175495cfdb988be3d229e24f13e8f71e1ba87654736b856a100427c487c0a", "outputFile": "pdftomdconverter/markdown/BD-07.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 0.974921630094044, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-08", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 529.36, "outputBytes": 741, "outputSha256": "4a63458f027675d214a00f52728b11b8f54830ce17340eb8c4146b8fdcbf133d", "outputFile": "pdftomdconverter/markdown/BD-08.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-09", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 526.61, "outputBytes": 2596, "outputSha256": "14a4717b5eceb2be79ebd0669e79f33996df90c0c0f480f1f1e5d13359b80369", "outputFile": "pdftomdconverter/markdown/BD-09.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 0.996168582375479, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-10", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 531.94, "outputBytes": 2694, "outputSha256": "a1eebf70a598aacfe1fe5c261a6cf2edce0bfaebd55d8fd2930c562a7d15b6b6", "outputFile": "pdftomdconverter/markdown/BD-10.md", "converterOutcome": "Markdown ready", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-01", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 527.72, "outputBytes": 1746, "outputSha256": "3d2de2aae81221e9d8db40a253119fe6f3f4feaef175413afbadbd333fcb97a3", "outputFile": "pdftomdconverter/markdown/MC-01.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 0.9963768115942029, "scannedTextRecall": null, "readingOrder": { "passed": 1, "total": 5, "rate": 0.2 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-02", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 526.14, "outputBytes": 1320, "outputSha256": "baeccf5e6cdb20143995497b7b00b6624446237b480e1474ad7faece52d1ed30", "outputFile": "pdftomdconverter/markdown/MC-02.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 1, "total": 2, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-03", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 532.46, "outputBytes": 3800, "outputSha256": "cef3b9d224c8c868f530218bef5c95d3e8a4ea31fd4a85faa98d6dd2643eaa0c", "outputFile": "pdftomdconverter/markdown/MC-03.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 3, "total": 4, "rate": 0.75 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-04", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 526.2, "outputBytes": 1988, "outputSha256": "0ee4f09178d71fed6b40fa3343b8ef6f29982a74a8f9e7b912fbb05f93c873c8", "outputFile": "pdftomdconverter/markdown/MC-04.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 1, "total": 4, "rate": 0.25 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-05", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 528.05, "outputBytes": 4682, "outputSha256": "fe6a274013d1782b060dc7add5a45f7855c6234a6bc881cb915d39ada10af8d6", "outputFile": "pdftomdconverter/markdown/MC-05.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 0.6159509202453988, "scannedTextRecall": null, "readingOrder": { "passed": 0, "total": 5, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-06", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 524.66, "outputBytes": 3367, "outputSha256": "8341e5e7e09095ed9c7b153bb414efa9e27fe72872c4029dcfbcb64c1f5f6769", "outputFile": "pdftomdconverter/markdown/MC-06.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 0.9969543147208122, "scannedTextRecall": null, "readingOrder": { "passed": 2, "total": 4, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-07", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 452.43, "outputBytes": 6768, "outputSha256": "571fb195c1fdf2f08ea95a4143dee0b0e13f2c06cc8a314d016230688d5e43e3", "outputFile": "pdftomdconverter/markdown/MC-07.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 1, "total": 4, "rate": 0.25 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-08", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 435.94, "outputBytes": 4560, "outputSha256": "5d98fbb8f06661857065930ba6f1f77e88749f6e963c14f8315c5e1e2bb296b7", "outputFile": "pdftomdconverter/markdown/MC-08.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 0.9977628635346756, "scannedTextRecall": null, "readingOrder": { "passed": 1, "total": 5, "rate": 0.2 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-09", "systemId": "pdftomdconverter", "status": "failed", "runtimeMs": 180468.34, "outputBytes": 0, "outputSha256": null, "outputFile": null, "error": "TimeoutError: locator.waitFor: Timeout 180000ms exceeded. Call log: - waiting for getByLabel('Editable Markdown result') to be visible", "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-10", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 539.47, "outputBytes": 5396, "outputSha256": "6eaadf8ed74a4e372940054f826516a55d9621231fc21b6e450a90fc3cef8159", "outputFile": "pdftomdconverter/markdown/MC-10.md", "converterOutcome": "Markdown ready", "error": null, "group": "multi-column", "textFidelity": 0.9962358845671268, "scannedTextRecall": null, "readingOrder": { "passed": 0, "total": 5, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "TB-01", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 535.32, "outputBytes": 5321, "outputSha256": "941315852f4126e107a123c5faf238bd1ffca1e6b227e95b781f1679c678bbd5", "outputFile": "pdftomdconverter/markdown/TB-01.md", "converterOutcome": "Markdown ready", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 7, "rate": 0.5714285714285714 }, "markdownParseSuccess": true }, { "documentId": "TB-02", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 534.1, "outputBytes": 1875, "outputSha256": "f1764b1f1f9c228bf001ad82ed841dec34bcf56090808342049a0b8180ea6413", "outputFile": "pdftomdconverter/markdown/TB-02.md", "converterOutcome": "Markdown ready", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 5, "total": 5, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-03", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 545.66, "outputBytes": 5720, "outputSha256": "e47cec7e4734417987e7b736fa2b21d0e6b61a2fd3fb1124d1d1b29a8da272f7", "outputFile": "pdftomdconverter/markdown/TB-03.md", "converterOutcome": "Markdown ready", "error": null, "group": "table-heavy", "textFidelity": 0.9313904068002428, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 3, "total": 5, "rate": 0.6 }, "markdownParseSuccess": true }, { "documentId": "TB-04", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 539.09, "outputBytes": 578, "outputSha256": "e9be348f9d4def9bc069c7df1b0ce1eee486a07c1e72604224134217d787054f", "outputFile": "pdftomdconverter/markdown/TB-04.md", "converterOutcome": "Markdown ready", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 3, "total": 5, "rate": 0.6 }, "markdownParseSuccess": true }, { "documentId": "TB-05", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 538.54, "outputBytes": 1925, "outputSha256": "e249da1d214fc72d08b118ec40314773eab33fb1bed7119c57277b11492c9e72", "outputFile": "pdftomdconverter/markdown/TB-05.md", "converterOutcome": "Markdown ready", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 3, "total": 4, "rate": 0.75 }, "markdownParseSuccess": true }, { "documentId": "TB-06", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 537.53, "outputBytes": 4875, "outputSha256": "dc1c114f74b66110147932d6fb947f727fe1609c7dea87293143a5c9f2d2c64b", "outputFile": "pdftomdconverter/markdown/TB-06.md", "converterOutcome": "Markdown ready", "error": null, "group": "table-heavy", "textFidelity": 0.9958100558659218, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 4, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-07", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 544.49, "outputBytes": 3255, "outputSha256": "0569e4483d7b59af5d4bec8bd35f21cdf1b157775b0bdf423e8d8d1839b8efc2", "outputFile": "pdftomdconverter/markdown/TB-07.md", "converterOutcome": "Markdown ready", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 5, "rate": 0.8 }, "markdownParseSuccess": true }, { "documentId": "TB-08", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 535.81, "outputBytes": 2271, "outputSha256": "e67cb10d158f12afaacebe7d52401e47451968a04b95537edb9aa0e625b674d2", "outputFile": "pdftomdconverter/markdown/TB-08.md", "converterOutcome": "Markdown ready", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 0, "total": 5, "rate": 0 }, "markdownParseSuccess": true }, { "documentId": "SC-01", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 18810.5, "outputBytes": 387, "outputSha256": "7f7eaa5a27509014bbe5f8ae4e7893368f40c3e1c5d6f2a7759b71c642864a80", "outputFile": "pdftomdconverter/markdown/SC-01.md", "converterOutcome": "Markdown ready", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-02", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 8181.99, "outputBytes": 752, "outputSha256": "d06884848ab9b4d6b277cc8ca3d535a468bc569e41c10a3b2a13627d694ac226", "outputFile": "pdftomdconverter/markdown/SC-02.md", "converterOutcome": "Markdown ready", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 2, "total": 2, "rate": 1 }, "readingOrder": { "passed": 2, "total": 3, "rate": 0.6666666666666666 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-03", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 11202.11, "outputBytes": 1382, "outputSha256": "c09b8c64aa35be361bacee27e4309e66290bff3f4cef97f14d772b020eefcfb9", "outputFile": "pdftomdconverter/markdown/SC-03.md", "converterOutcome": "Markdown ready", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 4, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-04", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 9171.95, "outputBytes": 743, "outputSha256": "78007c018326a89cd0d28f15112cb836b1e5c49b6b70ad162f998a96106166e5", "outputFile": "pdftomdconverter/markdown/SC-04.md", "converterOutcome": "Markdown ready", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 1, "total": 2, "rate": 0.5 }, "readingOrder": { "passed": 0, "total": 1, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-05", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 8195.36, "outputBytes": 1000, "outputSha256": "62f76f3b7fd03ba7f99cad4d27177a3c5aa4c1f5509a9f44abeee5544d9cdfeb", "outputFile": "pdftomdconverter/markdown/SC-05.md", "converterOutcome": "Markdown ready", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 3, "rate": 0 }, "readingOrder": { "passed": 1, "total": 2, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-06", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 8181.38, "outputBytes": 1295, "outputSha256": "3fed3718899d2ff5100fadc315cab0859827d005f89a7e2611f26e25a5482d12", "outputFile": "pdftomdconverter/markdown/SC-06.md", "converterOutcome": "Markdown ready", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-01", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 547.17, "outputBytes": 4095, "outputSha256": "791e2f04c0d1666bf89d1854e91a54617ba40d2ca468b0a283ffbe21c92d3bfc", "outputFile": "pdftomdconverter/markdown/SH-01.md", "converterOutcome": "Markdown ready", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9506172839506173, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 1, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-02", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 553.77, "outputBytes": 2924, "outputSha256": "ffe0351628f353ff5c275e764f6e38deb1b1f5cc86f01bb8050da9d83ffed4b2", "outputFile": "pdftomdconverter/markdown/SH-02.md", "converterOutcome": "Markdown ready", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9626253418413856, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 2, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-03", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 535.46, "outputBytes": 2282, "outputSha256": "bd6f3780f7c7b95edaa8f72ff6d0d49a2310269c08f89e89db741fca7056dbb7", "outputFile": "pdftomdconverter/markdown/SH-03.md", "converterOutcome": "Markdown ready", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8912751677852349, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 5, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-04", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 530.66, "outputBytes": 2416, "outputSha256": "7104a0b86c2291450864af89cc8c4b9a48ddd5ab3c88088bdd241e99daa07c2a", "outputFile": "pdftomdconverter/markdown/SH-04.md", "converterOutcome": "Markdown ready", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9112149532710281, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 1, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-05", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 537.18, "outputBytes": 3194, "outputSha256": "1e8257bc01e7b3159db64bf0b1f3fa1f242500ee1c6c11593e0384e9471809be", "outputFile": "pdftomdconverter/markdown/SH-05.md", "converterOutcome": "Markdown ready", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9561752988047809, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 1, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-06", "systemId": "pdftomdconverter", "status": "completed", "runtimeMs": 535.4, "outputBytes": 1839, "outputSha256": "76920838e22bf0b41df262f9b162abcd271c97f29c6148128d89759af406f8b5", "outputFile": "pdftomdconverter/markdown/SH-06.md", "converterOutcome": "Markdown ready", "error": null, "group": "figures-lists-headings", "textFidelity": 0.7804232804232804, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 4, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-01", "systemId": "docling", "status": "completed", "runtimeMs": 10553.09, "outputBytes": 2605, "outputSha256": "452aab23d5902e06790775db44029db06e1a8e795fe8da2baab4d6772a7f25f6", "outputFile": "docling/markdown/BD-01.md", "error": null, "group": "born-digital", "textFidelity": 0.9771689497716894, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-02", "systemId": "docling", "status": "completed", "runtimeMs": 1624.65, "outputBytes": 9840, "outputSha256": "3ca5b47605d6cd5194208c5e52705c6338848c2baf9bfd1dfd8d330b574ea983", "outputFile": "docling/markdown/BD-02.md", "error": null, "group": "born-digital", "textFidelity": 0.9955357142857144, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-03", "systemId": "docling", "status": "completed", "runtimeMs": 2292.48, "outputBytes": 1015, "outputSha256": "05d4a1e785de56c7465187b4b211aee1f82c2add0dbcfbb39903fd4e05bebb52", "outputFile": "docling/markdown/BD-03.md", "error": null, "group": "born-digital", "textFidelity": 0.9666666666666666, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-04", "systemId": "docling", "status": "completed", "runtimeMs": 7927.79, "outputBytes": 1106, "outputSha256": "e9f7723cbae9420afd8a44a8e10bfb688cf8cba8aa4172f453150cfd56b53c0f", "outputFile": "docling/markdown/BD-04.md", "error": null, "group": "born-digital", "textFidelity": 0.9151515151515152, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-05", "systemId": "docling", "status": "completed", "runtimeMs": 2819.28, "outputBytes": 3313, "outputSha256": "315b923be623c4682f24be0722d9d879f90860b6a5af9a2c597d69861a1cae1a", "outputFile": "docling/markdown/BD-05.md", "error": null, "group": "born-digital", "textFidelity": 0.8373590982286634, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-06", "systemId": "docling", "status": "completed", "runtimeMs": 175.37, "outputBytes": 3684, "outputSha256": "d801e512d41492613d26f5b7718c3f449420391274c3c8a3f45004bb7c538058", "outputFile": "docling/markdown/BD-06.md", "error": null, "group": "born-digital", "textFidelity": 0.9464285714285715, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-07", "systemId": "docling", "status": "completed", "runtimeMs": 2826.37, "outputBytes": 2098, "outputSha256": "bcde8cd918f52045885ebd7ee8e897a1c46d0fc95696629402cf70eb87d1477b", "outputFile": "docling/markdown/BD-07.md", "error": null, "group": "born-digital", "textFidelity": 0.9237804878048781, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-08", "systemId": "docling", "status": "completed", "runtimeMs": 1346.08, "outputBytes": 883, "outputSha256": "157c238101bc555c418d59579a0d66b7a2c74c427a3756f087a391920de34ebd", "outputFile": "docling/markdown/BD-08.md", "error": null, "group": "born-digital", "textFidelity": 0.884297520661157, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-09", "systemId": "docling", "status": "completed", "runtimeMs": 17930.24, "outputBytes": 4097, "outputSha256": "6a0c8842a42f6ecc5466d5bab842a97bc108e35633b2732228dcdd831b88fe50", "outputFile": "docling/markdown/BD-09.md", "error": null, "group": "born-digital", "textFidelity": 0.978343949044586, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-10", "systemId": "docling", "status": "completed", "runtimeMs": 182.89, "outputBytes": 2610, "outputSha256": "ca15208536fca768369cd13188e8e0ddbfcdd78b1fa6cf82d8697a641306667a", "outputFile": "docling/markdown/BD-10.md", "error": null, "group": "born-digital", "textFidelity": 0.9759797724399494, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-01", "systemId": "docling", "status": "completed", "runtimeMs": 140.66, "outputBytes": 1533, "outputSha256": "be48ee41715018db62712d10ed74f98930bc227936745394fba7c7e43e478de8", "outputFile": "docling/markdown/MC-01.md", "error": null, "group": "multi-column", "textFidelity": 0.9363295880149812, "scannedTextRecall": null, "readingOrder": { "passed": 5, "total": 5, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-02", "systemId": "docling", "status": "completed", "runtimeMs": 775.62, "outputBytes": 1155, "outputSha256": "f7271c75790e1481b7cab1f56e3e1c7a4f80cbdd73a5720f4111669b6c360bf7", "outputFile": "docling/markdown/MC-02.md", "error": null, "group": "multi-column", "textFidelity": 0.9305912596401029, "scannedTextRecall": null, "readingOrder": { "passed": 2, "total": 2, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-03", "systemId": "docling", "status": "completed", "runtimeMs": 233.69, "outputBytes": 3752, "outputSha256": "da3d1a2a343b9ac7c5ff30a7adffa3d82d293fbc7fa4b90f39cf301daab133da", "outputFile": "docling/markdown/MC-03.md", "error": null, "group": "multi-column", "textFidelity": 0.991236611489776, "scannedTextRecall": null, "readingOrder": { "passed": 3, "total": 4, "rate": 0.75 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-04", "systemId": "docling", "status": "completed", "runtimeMs": 3843.35, "outputBytes": 1779, "outputSha256": "38226e2f90032e4619873561a6ea8ba23db450e4adb15e101ba191f114f15634", "outputFile": "docling/markdown/MC-04.md", "error": null, "group": "multi-column", "textFidelity": 0.9556313993174061, "scannedTextRecall": null, "readingOrder": { "passed": 4, "total": 4, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-05", "systemId": "docling", "status": "completed", "runtimeMs": 260.69, "outputBytes": 8080, "outputSha256": "43d5d4a90e05cfd5c915ed1dde32ebb1686fa39abead5ddd36a5d0bd063619bb", "outputFile": "docling/markdown/MC-05.md", "error": null, "group": "multi-column", "textFidelity": 0.002917578409919766, "scannedTextRecall": null, "readingOrder": { "passed": 0, "total": 5, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-06", "systemId": "docling", "status": "completed", "runtimeMs": 18428.92, "outputBytes": 4632, "outputSha256": "d3e88bad19d1188a0a6d722913b9cbcd0de8cb6a36df899c0e9f4f4b4c724a1d", "outputFile": "docling/markdown/MC-06.md", "error": null, "group": "multi-column", "textFidelity": 0.926470588235294, "scannedTextRecall": null, "readingOrder": { "passed": 2, "total": 4, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-07", "systemId": "docling", "status": "completed", "runtimeMs": 1252.19, "outputBytes": 6481, "outputSha256": "a1aff9e6ac2757db6b112a1dec1140d419aa654802cabfc9efba47b0b0c2afa7", "outputFile": "docling/markdown/MC-07.md", "error": null, "group": "multi-column", "textFidelity": 0.9699879951980792, "scannedTextRecall": null, "readingOrder": { "passed": 4, "total": 4, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-08", "systemId": "docling", "status": "completed", "runtimeMs": 313.63, "outputBytes": 4511, "outputSha256": "bfd86b23120f987139c76fc6942e18b8274501c5265d4d7fe2380ce211d74c50", "outputFile": "docling/markdown/MC-08.md", "error": null, "group": "multi-column", "textFidelity": 0.9347659247889487, "scannedTextRecall": null, "readingOrder": { "passed": 4, "total": 5, "rate": 0.8 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-09", "systemId": "docling", "status": "completed", "runtimeMs": 11676.74, "outputBytes": 1684, "outputSha256": "62d08edb6fe621c8b79dacce9f5cd00ad7808c5fce6467cb6fb912e9391e85d0", "outputFile": "docling/markdown/MC-09.md", "error": null, "group": "multi-column", "textFidelity": 0, "scannedTextRecall": null, "readingOrder": { "passed": 1, "total": 2, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-10", "systemId": "docling", "status": "completed", "runtimeMs": 261.77, "outputBytes": 5420, "outputSha256": "b2a3bd554a90c9a78d9dd5c83ab261bfb9c3b37fc60b9c99e289c46c060a0661", "outputFile": "docling/markdown/MC-10.md", "error": null, "group": "multi-column", "textFidelity": 0.9730077120822622, "scannedTextRecall": null, "readingOrder": { "passed": 5, "total": 5, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "TB-01", "systemId": "docling", "status": "completed", "runtimeMs": 1158.83, "outputBytes": 5717, "outputSha256": "09217a324dbd73d00b35b8f2f9640681a4e0bee5378efbe4394d2e115f0a88af", "outputFile": "docling/markdown/TB-01.md", "error": null, "group": "table-heavy", "textFidelity": 0.9936305732484078, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 7, "total": 7, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-02", "systemId": "docling", "status": "completed", "runtimeMs": 2392.98, "outputBytes": 3343, "outputSha256": "13e588fe45c431a99d1847cca76244d8932180f35650d6f5464f284c6c53e71b", "outputFile": "docling/markdown/TB-02.md", "error": null, "group": "table-heavy", "textFidelity": 0.9893129770992367, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 5, "total": 5, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-03", "systemId": "docling", "status": "completed", "runtimeMs": 575.97, "outputBytes": 4787, "outputSha256": "a34dd3677f95a17d7a8963ffcb9f1cf5792aad90760bc8e4052e7730bda26f80", "outputFile": "docling/markdown/TB-03.md", "error": null, "group": "table-heavy", "textFidelity": 0.9183540169823644, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 5, "total": 5, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-04", "systemId": "docling", "status": "completed", "runtimeMs": 381.53, "outputBytes": 824, "outputSha256": "48efffe41f96cf22fcb11b57137600aa6073364500559ffd402ebc28ef7c9e31", "outputFile": "docling/markdown/TB-04.md", "error": null, "group": "table-heavy", "textFidelity": 0.9015544041450777, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 3, "total": 5, "rate": 0.6 }, "markdownParseSuccess": true }, { "documentId": "TB-05", "systemId": "docling", "status": "completed", "runtimeMs": 1363.7, "outputBytes": 1913, "outputSha256": "7caa70956e9b35e8ce2c8d13f651cbc561ba0205adad84be423db02b4d48a13f", "outputFile": "docling/markdown/TB-05.md", "error": null, "group": "table-heavy", "textFidelity": 0.992, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 4, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-06", "systemId": "docling", "status": "completed", "runtimeMs": 568.53, "outputBytes": 5188, "outputSha256": "da3f5e51c7e6ae2a89b93429679733f49b658a923a3375b6191c8522f7dc3ab2", "outputFile": "docling/markdown/TB-06.md", "error": null, "group": "table-heavy", "textFidelity": 0.9901823281907433, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 4, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-07", "systemId": "docling", "status": "completed", "runtimeMs": 7530.63, "outputBytes": 3300, "outputSha256": "cd4a296a98ddc871e47c6ecf43ad80a48df2fd5d24dfe967b55ca3a51805b48b", "outputFile": "docling/markdown/TB-07.md", "error": null, "group": "table-heavy", "textFidelity": 0.9468926553672316, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 5, "total": 5, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-08", "systemId": "docling", "status": "completed", "runtimeMs": 1218.38, "outputBytes": 3284, "outputSha256": "4facd03089b5fa95f8734effa6e3c4afb591605c07244155942479a64825348b", "outputFile": "docling/markdown/TB-08.md", "error": null, "group": "table-heavy", "textFidelity": 0.9318181818181818, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 5, "total": 5, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "SC-01", "systemId": "docling", "status": "completed", "runtimeMs": 10447.03, "outputBytes": 25, "outputSha256": "4262ef44a1a996fbd6317f85af64b9aba9c4af62d4bf30c02a891f52d0e87547", "outputFile": "docling/markdown/SC-01.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-02", "systemId": "docling", "status": "completed", "runtimeMs": 14566.11, "outputBytes": 692, "outputSha256": "51c3981b97c7ae11dd2473e0afacd38c173ec084d9b64fca3f5f004aa2b45086", "outputFile": "docling/markdown/SC-02.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 1, "total": 2, "rate": 0.5 }, "readingOrder": { "passed": 1, "total": 3, "rate": 0.3333333333333333 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-03", "systemId": "docling", "status": "completed", "runtimeMs": 11035.06, "outputBytes": 116, "outputSha256": "01593d70813a0a20f248c34f0c1dd96e3560decbf1dca88b32c377cff5921204", "outputFile": "docling/markdown/SC-03.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 4, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-04", "systemId": "docling", "status": "completed", "runtimeMs": 13477.08, "outputBytes": 1182, "outputSha256": "be6103c6b5d168621eebc7bbe192dcf219a82aef4aefc035c272a7ee6942725f", "outputFile": "docling/markdown/SC-04.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 1, "total": 2, "rate": 0.5 }, "readingOrder": { "passed": 0, "total": 1, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-05", "systemId": "docling", "status": "completed", "runtimeMs": 9994.32, "outputBytes": 908, "outputSha256": "0261bcb6503934b6058b8b02670d17bb67b3ba4c922be77d47997da1eb688c18", "outputFile": "docling/markdown/SC-05.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 3, "total": 3, "rate": 1 }, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-06", "systemId": "docling", "status": "completed", "runtimeMs": 13981.76, "outputBytes": 1165, "outputSha256": "1b84ae1286228fcc82080f780a88a57207ca5b48da8696377990b80205ad5a0e", "outputFile": "docling/markdown/SC-06.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 2, "total": 2, "rate": 1 }, "readingOrder": { "passed": 1, "total": 2, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-01", "systemId": "docling", "status": "completed", "runtimeMs": 228.22, "outputBytes": 3950, "outputSha256": "ad3c3ed61a37f12fbba691febe8cbbea6e24d0611b64fe5b28e8e47d15a1a3c2", "outputFile": "docling/markdown/SH-01.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9423210562890897, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 1, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-02", "systemId": "docling", "status": "completed", "runtimeMs": 212.08, "outputBytes": 2824, "outputSha256": "26bdef65908f572aaaaef19d0d5eac2f41c877f4b003a881a9c6106cbc9100a9", "outputFile": "docling/markdown/SH-02.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9528214616096207, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 2, "rate": 0.5 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-03", "systemId": "docling", "status": "completed", "runtimeMs": 283.84, "outputBytes": 2088, "outputSha256": "f4034cc7edb2eb151fcbfed40650d0fd9a630c00906a83105636cdc6d79d3a01", "outputFile": "docling/markdown/SH-03.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8694362017804155, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 5, "rate": 0.2 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-04", "systemId": "docling", "status": "completed", "runtimeMs": 5026.32, "outputBytes": 2341, "outputSha256": "6cb18f02ee6eddd8e1d949cc9e4a18fefa54d57fe58e0a6aacaf625da2aff5c2", "outputFile": "docling/markdown/SH-04.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8946745562130177, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 1, "rate": 1 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-05", "systemId": "docling", "status": "completed", "runtimeMs": 5439.32, "outputBytes": 3068, "outputSha256": "113b8cc4de011556fa9aa53b19880e741163c762a8aa113d3b35bf95770674a4", "outputFile": "docling/markdown/SH-05.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.949290060851927, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 1, "rate": 1 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-06", "systemId": "docling", "status": "completed", "runtimeMs": 182.94, "outputBytes": 1745, "outputSha256": "9351a612b71d782508c0e00f995d372685c08e507a81d559026e94927352914d", "outputFile": "docling/markdown/SH-06.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8021978021978021, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 4, "rate": 0.25 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-01", "systemId": "marker", "status": "completed", "runtimeMs": 1695.92, "outputBytes": 2265, "outputSha256": "be73e6fef12ecd87610e3e5c4c1cbd9083cde8a791919a9039107b122b8e8652", "outputFile": "marker/markdown/BD-01.md", "error": null, "group": "born-digital", "textFidelity": 0.9892141756548537, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-02", "systemId": "marker", "status": "completed", "runtimeMs": 65481.66, "outputBytes": 2912, "outputSha256": "e5abd893cfaa806cb4f44660493929a6e5ed5970d9c500de59e14fe8b7779bb0", "outputFile": "marker/markdown/BD-02.md", "error": null, "group": "born-digital", "textFidelity": 0.9866071428571429, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-03", "systemId": "marker", "status": "completed", "runtimeMs": 1130.86, "outputBytes": 940, "outputSha256": "76c2d9a32a85388a616e25f095a617d9e2e4d607ff80aba6268be2430122f855", "outputFile": "marker/markdown/BD-03.md", "error": null, "group": "born-digital", "textFidelity": 0.9731543624161074, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-04", "systemId": "marker", "status": "completed", "runtimeMs": 455.92, "outputBytes": 1017, "outputSha256": "01566eb679b7bdad5f4ed64c73ef23981a814a4b82e5ea10714774c206b7799a", "outputFile": "marker/markdown/BD-04.md", "error": null, "group": "born-digital", "textFidelity": 0.9470404984423676, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-05", "systemId": "marker", "status": "completed", "runtimeMs": 1371.61, "outputBytes": 3797, "outputSha256": "d713d603eb0e240c9b124a518d93deb01c4daf2afe302ccefae4088f9ea56f1d", "outputFile": "marker/markdown/BD-05.md", "error": null, "group": "born-digital", "textFidelity": 0.9430656934306569, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-06", "systemId": "marker", "status": "completed", "runtimeMs": 794.18, "outputBytes": 3677, "outputSha256": "780177d589f530c58d78d867258113042b4283a0a260aafedcd558665450affb", "outputFile": "marker/markdown/BD-06.md", "error": null, "group": "born-digital", "textFidelity": 0.9498207885304659, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-07", "systemId": "marker", "status": "completed", "runtimeMs": 742.88, "outputBytes": 1853, "outputSha256": "0fde2c8680c0f67a8bb5574b365d746a18036afa9740e6508642e633eb000e65", "outputFile": "marker/markdown/BD-07.md", "error": null, "group": "born-digital", "textFidelity": 0.752827140549273, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-08", "systemId": "marker", "status": "completed", "runtimeMs": 863.09, "outputBytes": 964, "outputSha256": "cc98f3baaefe2c699f064ef31182cd6752c49afea1da6569b25cd4f208f052a4", "outputFile": "marker/markdown/BD-08.md", "error": null, "group": "born-digital", "textFidelity": 0.8502024291497976, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-09", "systemId": "marker", "status": "completed", "runtimeMs": 16201.61, "outputBytes": 3579, "outputSha256": "9ade168b5e36762d0a9ce5b8553e4655892127b77a9e0121680d30c70fb36fe7", "outputFile": "marker/markdown/BD-09.md", "error": null, "group": "born-digital", "textFidelity": 0.9722222222222222, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-10", "systemId": "marker", "status": "completed", "runtimeMs": 299.35, "outputBytes": 2536, "outputSha256": "4b233656cdbd013bf03393dd41ad790db801ecfaea06746d5448b3547123b803", "outputFile": "marker/markdown/BD-10.md", "error": null, "group": "born-digital", "textFidelity": 0.9759797724399494, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-01", "systemId": "marker", "status": "completed", "runtimeMs": 138.76, "outputBytes": 1564, "outputSha256": "bb04ab7f23896ff10e68a341affd193d4e577d35bb24fabbf0bf4d0a286d22ef", "outputFile": "marker/markdown/MC-01.md", "error": null, "group": "multi-column", "textFidelity": 0.9363295880149812, "scannedTextRecall": null, "readingOrder": { "passed": 5, "total": 5, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-02", "systemId": "marker", "status": "completed", "runtimeMs": 25212.13, "outputBytes": 1024, "outputSha256": "cf352beaa6b62dc4067903d1580f4ae23bbf3620474be118df8792b0109957d5", "outputFile": "marker/markdown/MC-02.md", "error": null, "group": "multi-column", "textFidelity": 0.8978494623655914, "scannedTextRecall": null, "readingOrder": { "passed": 2, "total": 2, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-03", "systemId": "marker", "status": "completed", "runtimeMs": 270.32, "outputBytes": 3779, "outputSha256": "ada871508749f67d76a91ed00057d8000af728bde93f6f3a737a2cc82bb283a9", "outputFile": "marker/markdown/MC-03.md", "error": null, "group": "multi-column", "textFidelity": 0.991236611489776, "scannedTextRecall": null, "readingOrder": { "passed": 3, "total": 4, "rate": 0.75 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-04", "systemId": "marker", "status": "completed", "runtimeMs": 36354.28, "outputBytes": 1725, "outputSha256": "7eff65230d2ffc3f2ec74aea8d2875b4ce394781ab8bb83c040bb0e76305f249", "outputFile": "marker/markdown/MC-04.md", "error": null, "group": "multi-column", "textFidelity": 0.9605488850771869, "scannedTextRecall": null, "readingOrder": { "passed": 4, "total": 4, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-05", "systemId": "marker", "status": "completed", "runtimeMs": 267.23, "outputBytes": 4395, "outputSha256": "19eb56ba31a6ca055c7d740d477326995842afe177510bf6cfb0d64bdaeb1c29", "outputFile": "marker/markdown/MC-05.md", "error": null, "group": "multi-column", "textFidelity": 0.9310094408133623, "scannedTextRecall": null, "readingOrder": { "passed": 4, "total": 5, "rate": 0.8 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-06", "systemId": "marker", "status": "completed", "runtimeMs": 56323.75, "outputBytes": 4083, "outputSha256": "a7106478ce1f1e05fb6a334b0a4634193524cbcb5606c09ea702873007fcec73", "outputFile": "marker/markdown/MC-06.md", "error": null, "group": "multi-column", "textFidelity": 0.9129129129129129, "scannedTextRecall": null, "readingOrder": { "passed": 2, "total": 4, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-07", "systemId": "marker", "status": "completed", "runtimeMs": 231.99, "outputBytes": 6503, "outputSha256": "2304672e2da37ef4d18a57fbc89e756ad66cb57cb3445c4b97eb9e7a73b78527", "outputFile": "marker/markdown/MC-07.md", "error": null, "group": "multi-column", "textFidelity": 0.9717037928958459, "scannedTextRecall": null, "readingOrder": { "passed": 4, "total": 4, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-08", "systemId": "marker", "status": "completed", "runtimeMs": 228.18, "outputBytes": 4326, "outputSha256": "7d590f472dbe9e1090fe329d779bf4b5dbb4a4f6c11944a043289e897e034ae4", "outputFile": "marker/markdown/MC-08.md", "error": null, "group": "multi-column", "textFidelity": 0.9347659247889487, "scannedTextRecall": null, "readingOrder": { "passed": 4, "total": 5, "rate": 0.8 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-09", "systemId": "marker", "status": "completed", "runtimeMs": 42348.11, "outputBytes": 2182, "outputSha256": "4d1dfb6a9432f35d5f01f27e9072b831f03c59335007570b3dc87bcc85dc7059", "outputFile": "marker/markdown/MC-09.md", "error": null, "group": "multi-column", "textFidelity": 0, "scannedTextRecall": null, "readingOrder": { "passed": 2, "total": 2, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-10", "systemId": "marker", "status": "completed", "runtimeMs": 303.29, "outputBytes": 4996, "outputSha256": "188afe1d4f1130c2250412d525ff948cc24e712fddff705e7cead3ae56b6e37f", "outputFile": "marker/markdown/MC-10.md", "error": null, "group": "multi-column", "textFidelity": 0.9749196141479098, "scannedTextRecall": null, "readingOrder": { "passed": 5, "total": 5, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "TB-01", "systemId": "marker", "status": "completed", "runtimeMs": 388.82, "outputBytes": 6160, "outputSha256": "647bf3302e17861151ceb52c3eaea644f2eccb5cd534a89e8749e3f7bccebb6b", "outputFile": "marker/markdown/TB-01.md", "error": null, "group": "table-heavy", "textFidelity": 0.9808673469387756, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 7, "rate": 0.5714285714285714 }, "markdownParseSuccess": true }, { "documentId": "TB-02", "systemId": "marker", "status": "completed", "runtimeMs": 210.56, "outputBytes": 4310, "outputSha256": "c880cf895689046c3ee1f3edce63742bb5e70230d869ccb767d3a9bb0bf32e62", "outputFile": "marker/markdown/TB-02.md", "error": null, "group": "table-heavy", "textFidelity": 0.9799691833590138, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 5, "total": 5, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-03", "systemId": "marker", "status": "completed", "runtimeMs": 12418.36, "outputBytes": 5359, "outputSha256": "adbe739e4f6730f6f11c960f146c0dc7e3eb20967a1f33ecf186dff20f8883df", "outputFile": "marker/markdown/TB-03.md", "error": null, "group": "table-heavy", "textFidelity": 0.8618075801749271, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 5, "total": 5, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-04", "systemId": "marker", "status": "completed", "runtimeMs": 6894.08, "outputBytes": 1273, "outputSha256": "bf9d779fd5e2d1ccf519804fb03786782f1473d1c8eac698494071f9185902f8", "outputFile": "marker/markdown/TB-04.md", "error": null, "group": "table-heavy", "textFidelity": 0.9174311926605505, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 3, "total": 5, "rate": 0.6 }, "markdownParseSuccess": true }, { "documentId": "TB-05", "systemId": "marker", "status": "completed", "runtimeMs": 370.73, "outputBytes": 1767, "outputSha256": "265ae87a37d90d03633d6c1428186bf8c1aa9d32c07eab6d361c8b2ed29408f9", "outputFile": "marker/markdown/TB-05.md", "error": null, "group": "table-heavy", "textFidelity": 0.9495798319327732, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 3, "total": 4, "rate": 0.75 }, "markdownParseSuccess": true }, { "documentId": "TB-06", "systemId": "marker", "status": "completed", "runtimeMs": 464.47, "outputBytes": 5074, "outputSha256": "adfd99b1aecdc50722a9d8bc17557fa01b3c923e4b33849e4db0e66851bcef70", "outputFile": "marker/markdown/TB-06.md", "error": null, "group": "table-heavy", "textFidelity": 0.9901823281907433, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 4, "rate": 1 }, "markdownParseSuccess": true }, { "documentId": "TB-07", "systemId": "marker", "status": "completed", "runtimeMs": 386.16, "outputBytes": 3239, "outputSha256": "5941472cee9bdccc69a3ba889ee1f81a9ac1ca1a06c2a9876829cc40b27b6945", "outputFile": "marker/markdown/TB-07.md", "error": null, "group": "table-heavy", "textFidelity": 0.983050847457627, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 5, "rate": 0.8 }, "markdownParseSuccess": true }, { "documentId": "TB-08", "systemId": "marker", "status": "completed", "runtimeMs": 5526.48, "outputBytes": 2226, "outputSha256": "bfa5637e21af132afec953cd24b25d8489d9291f1317417843c9d03ca1a05122", "outputFile": "marker/markdown/TB-08.md", "error": null, "group": "table-heavy", "textFidelity": 0.89760348583878, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 3, "total": 5, "rate": 0.6 }, "markdownParseSuccess": true }, { "documentId": "SC-01", "systemId": "marker", "status": "completed", "runtimeMs": 27262.49, "outputBytes": 758, "outputSha256": "a5718246975f81d4323a5bca80160cacb1a6486f169835e18194dd6e9eb40441", "outputFile": "marker/markdown/SC-01.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 2, "total": 2, "rate": 1 }, "readingOrder": { "passed": 1, "total": 2, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-02", "systemId": "marker", "status": "completed", "runtimeMs": 28824.82, "outputBytes": 709, "outputSha256": "4e7b9216034640e1957894984e6e6c8b2e2a0cc0aa68c03717625978cf6d6e53", "outputFile": "marker/markdown/SC-02.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 2, "total": 2, "rate": 1 }, "readingOrder": { "passed": 3, "total": 3, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-03", "systemId": "marker", "status": "completed", "runtimeMs": 37046.35, "outputBytes": 957, "outputSha256": "33b5f4e765adc13d78f2b9b81808deef770a9ece328bfa51d9b7db16501d98cd", "outputFile": "marker/markdown/SC-03.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 1, "total": 2, "rate": 0.5 }, "readingOrder": { "passed": 2, "total": 4, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-04", "systemId": "marker", "status": "completed", "runtimeMs": 49862.36, "outputBytes": 1799, "outputSha256": "b7b477336fa0b9f455dab7c3532c43986c5db0ed0337b84da6559cf5d4d33886", "outputFile": "marker/markdown/SC-04.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 2, "total": 2, "rate": 1 }, "readingOrder": { "passed": 1, "total": 1, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-05", "systemId": "marker", "status": "completed", "runtimeMs": 33677.65, "outputBytes": 921, "outputSha256": "42c16f74a9dacbc131ff204039cdf2a0dcda1b45ef3a8b16937a580c90ab9c37", "outputFile": "marker/markdown/SC-05.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 3, "total": 3, "rate": 1 }, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-06", "systemId": "marker", "status": "completed", "runtimeMs": 38254.39, "outputBytes": 1357, "outputSha256": "6d2dea8e411dcfe54c0e3d1609e8bb51845f79710ccc52c49a914d27e5d1d147", "outputFile": "marker/markdown/SC-06.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 2, "total": 2, "rate": 1 }, "readingOrder": { "passed": 2, "total": 2, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-01", "systemId": "marker", "status": "completed", "runtimeMs": 342.37, "outputBytes": 4102, "outputSha256": "94f7719b9f6b3e33eb93d9277a636566a3655bf9d21a923d1c1d73ad4b2bf9cf", "outputFile": "marker/markdown/SH-01.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9340584636301835, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 1, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-02", "systemId": "marker", "status": "completed", "runtimeMs": 214.73, "outputBytes": 3288, "outputSha256": "f9a09e5eeda48402018115acc4e3b896a865b6bb3d8976a843116a2d36a4c307", "outputFile": "marker/markdown/SH-02.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8983492615117288, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 2, "rate": 0.5 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-03", "systemId": "marker", "status": "completed", "runtimeMs": 5988.91, "outputBytes": 2601, "outputSha256": "41a139ad2d3bcc5c866088b966283556f5c14d698b44fe861f77ed889a8ff001", "outputFile": "marker/markdown/SH-03.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8508997429305911, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 5, "rate": 0.2 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-04", "systemId": "marker", "status": "completed", "runtimeMs": 1048.86, "outputBytes": 2534, "outputSha256": "a93d63cef42405cdffe0d17b0324457fb27463b6dbf3d99acb667f7567e7723c", "outputFile": "marker/markdown/SH-04.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8645598194130926, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 1, "rate": 1 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-05", "systemId": "marker", "status": "completed", "runtimeMs": 277.48, "outputBytes": 3369, "outputSha256": "165c971596edfca69348e785686fd5aec5964733eddebd7d807ccc90f2c2c3f0", "outputFile": "marker/markdown/SH-05.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8884615384615385, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 1, "rate": 1 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-06", "systemId": "marker", "status": "completed", "runtimeMs": 3697.29, "outputBytes": 2187, "outputSha256": "21393a8ff0e546aa1b28581e38caf3f1115bc045e7e09f42db6dc5544afb4842", "outputFile": "marker/markdown/SH-06.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8317631224764469, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 1, "total": 4, "rate": 0.25 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-01", "systemId": "markitdown", "status": "completed", "runtimeMs": 41.88, "outputBytes": 2058, "outputSha256": "ce25458f64d6c81c29cb7049e204ce20c6e5e5dd3ad68af1908bc2eee797f870", "outputFile": "markitdown/markdown/BD-01.md", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-02", "systemId": "markitdown", "status": "completed", "runtimeMs": 52.67, "outputBytes": 4029, "outputSha256": "81342944f6548b62bdbb921bffba86f5100af332b11aaa47543b686a11802661", "outputFile": "markitdown/markdown/BD-02.md", "error": null, "group": "born-digital", "textFidelity": 0.9955752212389382, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-03", "systemId": "markitdown", "status": "completed", "runtimeMs": 23.76, "outputBytes": 987, "outputSha256": "f88afe797b4c5937b15b203b87bfded48a647c75475f62c74156d445cd40eb2a", "outputFile": "markitdown/markdown/BD-03.md", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-04", "systemId": "markitdown", "status": "completed", "runtimeMs": 19.01, "outputBytes": 2066, "outputSha256": "fcfdb0dd35fd9774826d6b60f023e79a700a81438ed9807f45aec9e73f3be758", "outputFile": "markitdown/markdown/BD-04.md", "error": null, "group": "born-digital", "textFidelity": 0.9910979228486648, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-05", "systemId": "markitdown", "status": "completed", "runtimeMs": 84.36, "outputBytes": 3316, "outputSha256": "7253338b9809e00857d827c00072460e84048afd3cc021de8eea2dc9c0b9ef5d", "outputFile": "markitdown/markdown/BD-05.md", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-06", "systemId": "markitdown", "status": "completed", "runtimeMs": 52.93, "outputBytes": 3820, "outputSha256": "8ea236e735ba082476de95dcf85cff72d375e040f025da738aa85429a3868cca", "outputFile": "markitdown/markdown/BD-06.md", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-07", "systemId": "markitdown", "status": "completed", "runtimeMs": 22.67, "outputBytes": 2734, "outputSha256": "e0b7fe2bb827ab1ac165cc1daa2778ac6d7148d9cdaf517f9ad80518b832cb4e", "outputFile": "markitdown/markdown/BD-07.md", "error": null, "group": "born-digital", "textFidelity": 0.6806883365200764, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-08", "systemId": "markitdown", "status": "completed", "runtimeMs": 15.01, "outputBytes": 738, "outputSha256": "29151144cffc9f3309c0f6c61e11ca3b6a2635708eedf475684b409ef5f85c8c", "outputFile": "markitdown/markdown/BD-08.md", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-09", "systemId": "markitdown", "status": "completed", "runtimeMs": 35.79, "outputBytes": 4007, "outputSha256": "6b1df187a88864feb56b8c045290c691cbb7800605ee93ae6ebfa06415840e3f", "outputFile": "markitdown/markdown/BD-09.md", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "BD-10", "systemId": "markitdown", "status": "completed", "runtimeMs": 48.41, "outputBytes": 2770, "outputSha256": "d17d2e41273a061fe9b56c9351e91d1eeea643270d54bdca3cc52744edf23ed2", "outputFile": "markitdown/markdown/BD-10.md", "error": null, "group": "born-digital", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-01", "systemId": "markitdown", "status": "completed", "runtimeMs": 27.69, "outputBytes": 1612, "outputSha256": "0cd27dd95c8a8a0f59a75cfeed2323a6ecd7c2424e6b7f9ddd6d4af0ce25dc12", "outputFile": "markitdown/markdown/MC-01.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 1, "total": 5, "rate": 0.2 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-02", "systemId": "markitdown", "status": "completed", "runtimeMs": 35.75, "outputBytes": 1222, "outputSha256": "1a912cf34c025c217faf203c2038191ff0a4e6801327df416527b4eee3cafb7a", "outputFile": "markitdown/markdown/MC-02.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 1, "total": 2, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-03", "systemId": "markitdown", "status": "completed", "runtimeMs": 131, "outputBytes": 3782, "outputSha256": "3918ed3d6f9d4e6ffa3f55c18662840d7df6174aba242254830daf10326985ef", "outputFile": "markitdown/markdown/MC-03.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 2, "total": 4, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-04", "systemId": "markitdown", "status": "completed", "runtimeMs": 47.5, "outputBytes": 1820, "outputSha256": "9d2aae2b9d3a352e6417be114fa9f87a053d2eb1e780a4ed7512126f9a83b5e0", "outputFile": "markitdown/markdown/MC-04.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 3, "total": 4, "rate": 0.75 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-05", "systemId": "markitdown", "status": "completed", "runtimeMs": 54.93, "outputBytes": 15180, "outputSha256": "5a20ab730d1d0bdec198eeb229c1550ff870206217cc9ec4038306adfeb3157c", "outputFile": "markitdown/markdown/MC-05.md", "error": null, "group": "multi-column", "textFidelity": 0.04068141367912536, "scannedTextRecall": null, "readingOrder": { "passed": 0, "total": 5, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-06", "systemId": "markitdown", "status": "completed", "runtimeMs": 47.98, "outputBytes": 7492, "outputSha256": "1396272d44dc11e3b21884952c344bf4319259569b5f4a458eff5f6e3d34155f", "outputFile": "markitdown/markdown/MC-06.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 2, "total": 4, "rate": 0.5 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-07", "systemId": "markitdown", "status": "completed", "runtimeMs": 101.34, "outputBytes": 6578, "outputSha256": "e58a207f6e6e37f3e6c5627f0bc69fc9fdc30b714dc1f154784990735ce12852", "outputFile": "markitdown/markdown/MC-07.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 4, "total": 4, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-08", "systemId": "markitdown", "status": "completed", "runtimeMs": 58.41, "outputBytes": 7884, "outputSha256": "2e993b1455f0e133ce4a95fc2ea75967c4b7703e9c87801d5eb21313348d94ae", "outputFile": "markitdown/markdown/MC-08.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 0, "total": 5, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-09", "systemId": "markitdown", "status": "completed", "runtimeMs": 4.96, "outputBytes": 0, "outputSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "outputFile": "markitdown/markdown/MC-09.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "MC-10", "systemId": "markitdown", "status": "completed", "runtimeMs": 118.92, "outputBytes": 5724, "outputSha256": "7a726a51d5216ec664c0489b92e2080bb0fde5bc15b7ea0fe135d0058f539faa", "outputFile": "markitdown/markdown/MC-10.md", "error": null, "group": "multi-column", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": { "passed": 5, "total": 5, "rate": 1 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "TB-01", "systemId": "markitdown", "status": "completed", "runtimeMs": 122.11, "outputBytes": 5303, "outputSha256": "3cddeb04c45abc2293c2d2916445246ccf2ac477575401fe595e2c4ad0af7b3d", "outputFile": "markitdown/markdown/TB-01.md", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 0, "total": 7, "rate": 0 }, "markdownParseSuccess": true }, { "documentId": "TB-02", "systemId": "markitdown", "status": "completed", "runtimeMs": 24.36, "outputBytes": 2441, "outputSha256": "d3b33557d26bf0ee872e0683dca49de1067a2c4148cf8259657ee53907e26e37", "outputFile": "markitdown/markdown/TB-02.md", "error": null, "group": "table-heavy", "textFidelity": 0.9723076923076923, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 4, "total": 5, "rate": 0.8 }, "markdownParseSuccess": true }, { "documentId": "TB-03", "systemId": "markitdown", "status": "completed", "runtimeMs": 80.53, "outputBytes": 13940, "outputSha256": "c6ec9bffae74a3be0bc75f008a540d475c9f561d89a007c42ade3bb89209b826", "outputFile": "markitdown/markdown/TB-03.md", "error": null, "group": "table-heavy", "textFidelity": 0.7137055837563452, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 1, "total": 5, "rate": 0.2 }, "markdownParseSuccess": true }, { "documentId": "TB-04", "systemId": "markitdown", "status": "completed", "runtimeMs": 34.2, "outputBytes": 546, "outputSha256": "16375d2780c7dcbff51184a3da492ac898acda5fb3539f2fdda0d0da434ce1bd", "outputFile": "markitdown/markdown/TB-04.md", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 0, "total": 5, "rate": 0 }, "markdownParseSuccess": true }, { "documentId": "TB-05", "systemId": "markitdown", "status": "completed", "runtimeMs": 21.88, "outputBytes": 2356, "outputSha256": "10eb4de88b8a30e8f5ce3820af017742af72897295a0210946fdb6e125b2d856", "outputFile": "markitdown/markdown/TB-05.md", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 3, "total": 4, "rate": 0.75 }, "markdownParseSuccess": true }, { "documentId": "TB-06", "systemId": "markitdown", "status": "completed", "runtimeMs": 54.87, "outputBytes": 6715, "outputSha256": "a00b9172709a097df9182726e7182b737dca70be6087eaf735719f5c7af78773", "outputFile": "markitdown/markdown/TB-06.md", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 1, "total": 4, "rate": 0.25 }, "markdownParseSuccess": true }, { "documentId": "TB-07", "systemId": "markitdown", "status": "completed", "runtimeMs": 71.96, "outputBytes": 3070, "outputSha256": "00565f13ebf4e50afb8f9bddedfa2099d2598b4c1bca411e0ee2789c167b9081", "outputFile": "markitdown/markdown/TB-07.md", "error": null, "group": "table-heavy", "textFidelity": 0.9933481152993349, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 0, "total": 5, "rate": 0 }, "markdownParseSuccess": true }, { "documentId": "TB-08", "systemId": "markitdown", "status": "completed", "runtimeMs": 42.06, "outputBytes": 3332, "outputSha256": "11600a4d8be223664953363543d8205e887c94a08f5e50c030cdcb360565d466", "outputFile": "markitdown/markdown/TB-08.md", "error": null, "group": "table-heavy", "textFidelity": 1, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": null, "tableStructure": { "passed": 0, "total": 5, "rate": 0 }, "markdownParseSuccess": true }, { "documentId": "SC-01", "systemId": "markitdown", "status": "completed", "runtimeMs": 3.81, "outputBytes": 0, "outputSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "outputFile": "markitdown/markdown/SC-01.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-02", "systemId": "markitdown", "status": "completed", "runtimeMs": 4.12, "outputBytes": 0, "outputSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "outputFile": "markitdown/markdown/SC-02.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 3, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-03", "systemId": "markitdown", "status": "completed", "runtimeMs": 3.29, "outputBytes": 0, "outputSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "outputFile": "markitdown/markdown/SC-03.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 4, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-04", "systemId": "markitdown", "status": "completed", "runtimeMs": 4.32, "outputBytes": 0, "outputSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "outputFile": "markitdown/markdown/SC-04.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 1, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-05", "systemId": "markitdown", "status": "completed", "runtimeMs": 2.97, "outputBytes": 0, "outputSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "outputFile": "markitdown/markdown/SC-05.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 3, "rate": 0 }, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SC-06", "systemId": "markitdown", "status": "completed", "runtimeMs": 2.56, "outputBytes": 0, "outputSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "outputFile": "markitdown/markdown/SC-06.md", "error": null, "group": "clear-scanned", "textFidelity": null, "scannedTextRecall": { "passed": 0, "total": 2, "rate": 0 }, "readingOrder": { "passed": 0, "total": 2, "rate": 0 }, "headingHierarchy": null, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-01", "systemId": "markitdown", "status": "completed", "runtimeMs": 55.76, "outputBytes": 6453, "outputSha256": "8b8daec5d506829921ed5493fff6342f6a902337083c3f6cfb29c38dd880296b", "outputFile": "markitdown/markdown/SH-01.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.7839506172839505, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 1, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-02", "systemId": "markitdown", "status": "completed", "runtimeMs": 51.74, "outputBytes": 2868, "outputSha256": "01114e6a8d27e08a927204faac2939311f901fb2875768ed1b8d940494e92a50", "outputFile": "markitdown/markdown/SH-02.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9935483870967742, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 2, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-03", "systemId": "markitdown", "status": "completed", "runtimeMs": 60.26, "outputBytes": 2156, "outputSha256": "19024c00b0af79b706a7699367c8ab8e9237c1696d83bc84fd46807ffe95ba91", "outputFile": "markitdown/markdown/SH-03.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9972067039106145, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 5, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-04", "systemId": "markitdown", "status": "completed", "runtimeMs": 39.73, "outputBytes": 3277, "outputSha256": "f8ea84e5c14111e0426cd4d5580ae742be2ab617f294410027b88167b8e71987", "outputFile": "markitdown/markdown/SH-04.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8934624697336562, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 1, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-05", "systemId": "markitdown", "status": "completed", "runtimeMs": 56.7, "outputBytes": 3099, "outputSha256": "b3853c7a14693d685ae2051655ab038248454ea829ea6b7cca6d214254ab8edc", "outputFile": "markitdown/markdown/SH-05.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.9724770642201834, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 1, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true }, { "documentId": "SH-06", "systemId": "markitdown", "status": "completed", "runtimeMs": 33.3, "outputBytes": 4609, "outputSha256": "b63cf9ee056dbba68b02d440a1a4b4f8ecc291c29ca21b7c01ca6d6d39f9cd96", "outputFile": "markitdown/markdown/SH-06.md", "error": null, "group": "figures-lists-headings", "textFidelity": 0.8451519536903038, "scannedTextRecall": null, "readingOrder": null, "headingHierarchy": { "passed": 0, "total": 4, "rate": 0 }, "tableStructure": null, "markdownParseSuccess": true } ], "failures": [ { "documentId": "MC-09", "systemId": "pdftomdconverter", "group": "multi-column", "failedMetrics": [ "conversion", "reading-order" ], "observedError": "TimeoutError: locator.waitFor: Timeout 180000ms exceeded. Call log: - waiting for getByLabel('Editable Markdown result') to be visible", "observedExcerpt": "" }, { "documentId": "MC-03", "systemId": "docling", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "## KIN 755 Exercise Electrocardiography, Testing, and Prescription (Units: 3) Prerequisite: Restricted to graduate Kinesiology students or permission" }, { "documentId": "MC-03", "systemId": "marker", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "### **KIN 755 Exercise Electrocardiography, Testing, and Prescription (Units: 3)** Prerequisite: Restricted to graduate Kinesiology students or permission" }, { "documentId": "MC-01", "systemId": "markitdown", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "MCM 7 and Smad 4 in Esophageal Cancer 353 of Smad4, a TGF-beta signaling molecule, in oral squamous" }, { "documentId": "MC-01", "systemId": "pdftomdconverter", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "MCM 7 and Smad 4 in Esophageal Cancer 306. 353 forming growth factor beta1 expression in patients with" }, { "documentId": "MC-05", "systemId": "docling", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "## BXDCD4CTD6CXD1CTD2D8D7 DBCXD8CW D4CTD2B9BWD3D1CPCXD2 CCCTDCD8D9CPD0 D9CTD7D8CXD3D2 BTD2D7DBCTD6CXD2CV CBCPD2CSCP BA CPD6CPCQCPCVCXD9 CPD2CS CPD6CXD9D7 BTBA CPAO D7CRCP CPD2CS CBD8CTDACTD2 -BA" }, { "documentId": "MC-05", "systemId": "marker", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "## Experiments with Open-Domain Textual Question Answering Sanda M. Harabagiu and Marius A. Pasca and Steven J. Maiorano" }, { "documentId": "MC-02", "systemId": "markitdown", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "events The National Civic Remembrance Sunday and Wreath-laying ceremony By Cpl Ally Rakoma Photos by Sgt Elias Mahuma" }, { "documentId": "MC-02", "systemId": "pdftomdconverter", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "## events By Cpl Ally Rakoma Photos by Sgt Elias Mahuma National Civic Remembrance Service and a wreath-" }, { "documentId": "MC-06", "systemId": "docling", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "Table 4. Interactive canopy cover responses of dominant individual herbaceous species to wood residue and gypsum ~mendment treatments" }, { "documentId": "MC-06", "systemId": "marker", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "Table 4. Interactive canopy cover responses of dominant individual herbaceous species to wood residue and gypsum amendment treatments" }, { "documentId": "MC-03", "systemId": "markitdown", "group": "multi-column", "failedMetrics": [ "reading-order" ], "observedError": null, "observedExcerpt": "Kinesiology San Francisco State University Bulletin 2023-2024 KIN 898 Master's Thesis (Units: 3) Prerequisites: Graduate Kinesiology students; KIN" } ], "limitations": [ "The corpus contains 40 English, single-page PDFs. It does not measure long-document consistency or non-English extraction.", "Digital text fidelity uses the embedded text layer as a reference. A flawed text layer can lower the usefulness of that reference.", "Runtime reflects this Apple silicon machine and the declared local configurations. It is not a cross-hardware speed guarantee.", "Heading checks cover six manually annotated pages. Table and reading-order checks reuse the source dataset assertions.", "PDFtoMDConverter timed out on MC-09 after 180 seconds. That terminal conversion failure remains in the row data and reduces its applicable metric denominators to 39 completed pages.", "Full generated Markdown stays in the local research workspace to avoid republishing source-document text." ], "correctionContact": "jaden@pdftomdconverter.app", "changelog": [ { "date": "2026-07-31", "note": "Initial 40-document local benchmark run, including the recorded PDFtoMDConverter timeout on MC-09." } ] }