{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:44:38Z","timestamp":1782758678730,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3806442","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:52:08Z","timestamp":1782755528000},"page":"7675-7691","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2006-7580","authenticated-orcid":false,"given":"Fitsum Sileshi","family":"Beyene","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Pennsylvania State University, State college, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2119-496X","authenticated-orcid":false,"given":"Christopher L.","family":"Dancy","sequence":"additional","affiliation":[{"name":"Department of Industrial and Manufacturing Engineering & Computer Science and Engineering, Pennsylvania State University, State college, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"arXiv","author":"Bai Shuai","year":"2025","unstructured":"Shuai Bai, Kai Chen, Xiaohui Liu, Jianfeng Wang, Wenqi Ge, Shiqi Song, and Jingdong Lin. 2025. Qwen2.5-VL Technical Report. arXiv (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99739-7_31"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISTAS65609.2025.11269615"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533083"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533157"},{"key":"e_1_3_2_1_6_1","volume-title":"Nougat: Neural Optical Understanding for Academic Documents. arXiv","author":"Blecher Lukas","year":"2023","unstructured":"Lukas Blecher and Graham Neubig. 2023. Nougat: Neural Optical Understanding for Academic Documents. arXiv (2023). https:\/\/arxiv.org\/abs\/2308.13418"},{"key":"e_1_3_2_1_7_1","volume-title":"DUE: End-to-End Document Understanding Benchmark. In Proceedings of the NeurIPS Datasets and Benchmarks Track","author":"Borchmann \u0141ukasz","year":"2021","unstructured":"\u0141ukasz Borchmann, Micha\u0142 Pietruszka, Tomasz Stanis\u0142awek, Dawid Jurkiewicz, Micha\u0142 Turski, Karolina Szyndler, and Filip Grali\u0144ski. 2021. DUE: End-to-End Document Understanding Benchmark. In Proceedings of the NeurIPS Datasets and Benchmarks Track. Neural Information Processing Systems Foundation. https:\/\/datasetsbenchmarksproceedings.neurips.cc\/paper\/2021\/file\/069059b7ef840f0c74a814ec9237b6ec-Paper.pdf"},{"key":"e_1_3_2_1_8_1","volume-title":"Howard University Is Digitizing Thousands of Black Newspapers. https:\/\/www.nbcnews.com\/news\/nbcblk\/howard-university-digitize-archive-thousands-black-newspapers-rcna17185 Retrieved","author":"Bunn Curtis M.","year":"2026","unstructured":"Curtis M. Bunn. 2024. Howard University Is Digitizing Thousands of Black Newspapers. https:\/\/www.nbcnews.com\/news\/nbcblk\/howard-university-digitize-archive-thousands-black-newspapers-rcna17185 Retrieved January 14, 2026."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1515\/jbwg-2023-0003"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1353\/cwh.2022.0010"},{"key":"e_1_3_2_1_11_1","volume-title":"Conventions Project. [n. d.]. About the Colored Conventions Project. https:\/\/omeka.coloredconventions.org\/about Retrieved","author":"Colored","year":"2026","unstructured":"Colored Conventions Project. [n. d.]. About the Colored Conventions Project. https:\/\/omeka.coloredconventions.org\/about Retrieved January 14, 2026."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732058"},{"key":"e_1_3_2_1_13_1","volume-title":"PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model. arXiv","author":"Cui Cheng","year":"2025","unstructured":"Cheng Cui, Tianxiang Sun, Shiyao Liang, Tao Gao, Zhe Zhang, Jiajun Liu, and Yu Ma. 2025. PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model. arXiv (2025). https:\/\/arxiv.org\/abs\/2510.14528"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TTS.2021.3125998"},{"key":"e_1_3_2_1_15_1","volume-title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers. In Proceedings of the NeurIPS Datasets and Benchmarks Track","author":"Dell Melissa","year":"2023","unstructured":"Melissa Dell, Jacob Carlson, Tom Bryan, Emily Silcock, Abhishek Arora, Zejiang Shen, Luca D'Amico-Wong, Quan Le, Pablo Querubin, and Leander Heldring. 2023. American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers. In Proceedings of the NeurIPS Datasets and Benchmarks Track. Neural Information Processing Systems Foundation. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/ffeb860479ccae44d84c0de32acd693d-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_2_1_16_1","unstructured":"Kim Gallon. 2016. Making a Case for the Black Digital Humanities. https:\/\/dhdebates.gc.cuny.edu\/read\/untitled\/section\/fa10e2e1-0c3d-4519-a958-d823aac989eb In *Debates in the Digital Humanities*."},{"key":"e_1_3_2_1_17_1","volume-title":"The Black Press. https:\/\/oxfordre.com\/americanhistory\/view\/10.1093\/acrefore\/9780199329175.001.0001\/acrefore-9780199329175-e-851 Retrieved","author":"Gallon Kim","year":"2026","unstructured":"Kim Gallon. 2021. The Black Press. https:\/\/oxfordre.com\/americanhistory\/view\/10.1093\/acrefore\/9780199329175.001.0001\/acrefore-9780199329175-e-851 Retrieved January 14, 2026."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1135"},{"key":"e_1_3_2_1_19_1","volume-title":"How Good Can It Get? Analysing and Improving OCR Accuracy in Large Scale Historic Newspaper Digitisation Programs. D Lib Mag. 15","author":"Holley Rose","year":"2009","unstructured":"Rose Holley. 2009. How Good Can It Get? Analysing and Improving OCR Accuracy in Large Scale Historic Newspaper Digitisation Programs. D Lib Mag. 15 (2009). https:\/\/api.semanticscholar.org\/CorpusID:2568435"},{"key":"e_1_3_2_1_20_1","unstructured":"Howard University Moorland-Spingarn Research Center. 2025. Black Press Archives. https:\/\/msrc.howard.edu\/black-press-archive. Collection includes over 2 000 newspaper titles 100 000 issues and 2 847 microfilm reels."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_22_1","unstructured":"Jackson Ketanji Brown. 2024. Dissenting Opinion in Case No. 23-1275. Supreme Court of the United States. https:\/\/www.supremecourt.gov\/opinions\/24pdf\/23-1275_e2pg.pdf Dissenting opinion."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412767"},{"key":"e_1_3_2_1_25_1","volume-title":"CHR 2021: Computational Humanities Research Conference.","author":"Lee B. C. G.","unstructured":"B. C. G. Lee, S. H. Ortiz Baco, J.Salter, and J. Casey. 2021. Navigating the Mise-en-Page: Interpretive Machine Learning Approaches to the Visual Layouts of Multi-Ethnic Periodicals. In CHR 2021: Computational Humanities Research Conference."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.63744\/SKoZVUHQbtE7\/"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148307"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"e_1_3_2_1_30_1","volume-title":"Congress.","author":"Library","year":"2025","unstructured":"Library of Congress. 2025. Chronicling America: African American Newspapers. https:\/\/www.loc.gov\/collections\/chronicling-america\/titles\/. Filtered by subject ethnicity: African American; publications dated 1777\u20131963."},{"key":"e_1_3_2_1_31_1","volume-title":"Congress. 2025","author":"Library","year":"2025","unstructured":"Library of Congress. 2025. Improving Search through OCR Reprocessing in Chronicling America. https:\/\/blogs.loc.gov\/headlinesandheroes\/2025\/04\/ocr-reprocessing\/."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Yuhang Liu Zhe Li Minghao Huang et al. 2024. OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models. Science China Information Sciences 67 Article 220102 (2024). doi:10.1007\/s11432-024-4235-6","DOI":"10.1007\/s11432-024-4235-6"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_34_1","volume-title":"Voluptuous Disintegration: A Future History of Black Computational Thought. DHQ: Digital Humanities Quarterly 16, 3","author":"Morrison R.","year":"2022","unstructured":"R. Morrison. 2022. Voluptuous Disintegration: A Future History of Black Computational Thought. DHQ: Digital Humanities Quarterly 16, 3 (2022)."},{"key":"e_1_3_2_1_35_1","unstructured":"NBC News via BET Staff. 2022. Howard University Receives Grant To Archive Black Newspapers. https:\/\/www.bet.com\/article\/u49dcv\/howard-university-receives-grant-to-archive-black-newspapers. Report on Howard University's $2M grant to digitize 60% Black Press Archives based on NBC News coverage."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476887.3476888"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453476"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18574\/nyu\/9781479833641.001.0001"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02313"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539043"},{"key":"e_1_3_2_1_42_1","unstructured":"Adam Poznanski et al. 2025. olmOCR: Scaling PDF Understanding with Internet Archive Data. arXiv (2025). https:\/\/arxiv.org\/abs\/2502.18443"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/app9224853"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.478"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2013.6691675"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"e_1_3_2_1_47_1","volume-title":"Ground Truth for Training OCR Engines on Historical Documents in German Fraktur and Early Modern Latin. arXiv","author":"Springmann Uwe","year":"2018","unstructured":"Uwe Springmann, Christian Reul, Stefanie Dipper, and Johannes Baiter. 2018. Ground Truth for Training OCR Engines on Historical Documents in German Fraktur and Early Modern Latin. arXiv (2018). https:\/\/arxiv.org\/abs\/1809.05501"},{"key":"e_1_3_2_1_48_1","volume-title":"NeurIPS Workshop on AI Cultures. https:\/\/ai-cultures.github.io\/papers\/machine_learning_as_an_archiva.pdf","author":"Taurino Giulia","unstructured":"Giulia Taurino and David A. Smith. 2022. Machine Learning as an Archival Science: Narratives behind Artificial Intelligence, Cultural Data, and Archival Remediation. In NeurIPS Workshop on AI Cultures. https:\/\/ai-cultures.github.io\/papers\/machine_learning_as_an_archiva.pdf"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5149\/northcarolina\/9781469653662.001.0001"},{"key":"e_1_3_2_1_50_1","unstructured":"The Crowley Company. 2024. Preserving Voices: Digitizing Howard University's Black Newspaper Collection. https:\/\/thecrowleycompany.com\/preserving-voices-digitizing-howard-universitys-black-newspaper-collection\/. Describes multi-year digitization efforts for the Black Press Archives."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"e_1_3_2_1_52_1","volume-title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-End Model. arXiv","author":"Wei Hao","year":"2024","unstructured":"Hao Wei, Chao Liu, Jingye Chen, Jianfeng Wang, Lingpeng Kong, Yiheng Xu, and Xiaohui Zhang. 2024. General OCR Theory: Towards OCR-2.0 via a Unified End-to-End Model. arXiv (2024). https:\/\/arxiv.org\/abs\/2409.01704"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3584931.3606981"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3806442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:53:26Z","timestamp":1782755606000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3806442"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":56,"alternative-id":["10.1145\/3805689.3806442","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3806442","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}