{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T01:46:47Z","timestamp":1791942407453,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T00:00:00Z","timestamp":1791849600000},"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":[[2026,10,13]]},"DOI":"10.1145\/3805696.3846504","type":"proceedings-article","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T07:02:51Z","timestamp":1791788571000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Accessibility Annotations as OCR Ground Truth: A Large-Scale Corpus of Long, Visually Complex Documents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3866-1206","authenticated-orcid":false,"given":"Gaozheng","family":"Liu","sequence":"first","affiliation":[{"name":"School of Information Sciences, University of Illinois at Urbana Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9397-6189","authenticated-orcid":false,"given":"Jill","family":"Naiman","sequence":"additional","affiliation":[{"name":"School of Information Sciences, University of Illinois at Urbana Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9784-5090","authenticated-orcid":false,"given":"J. Stephen","family":"Downie","sequence":"additional","affiliation":[{"name":"School of Information Sciences, University of Illinois at Urbana Champaign, Champaign, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,10,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.271"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Jeonghun Baek Geewook Kim Junyeop Lee Sungrae Park Dongyoon Han Sangdoo Yun Seong\u00a0Joon Oh and Hwalsuk Lee. 2019. What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis. arXiv:https:\/\/arXiv.org\/abs\/1904.01906 [cs]. 10.48550\/arXiv.1904.01906","DOI":"10.48550\/arXiv.1904.01906"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Henry\u00a0S Baird. 2003. Digital Libraries and Document Image Analysis. (2003).","DOI":"10.1142\/9789812775375_0014"},{"key":"e_1_3_3_2_5_2","unstructured":"Lukas Blecher Guillem Cucurull Thomas Scialom and Robert Stojnic. 2023. Nougat: Neural Optical Understanding for Academic Documents."},{"key":"e_1_3_3_2_6_2","unstructured":"Datalab. 2025. Chandra OCR. https:\/\/github.com\/datalab-to\/chandra"},{"key":"e_1_3_3_2_7_2","volume-title":"Special Education in Contemporary Society: An Introduction to Exceptionality (4th ed.)","author":"Gargiulo Richard\u00a0M.","year":"2012","unstructured":"Richard\u00a0M. Gargiulo. 2012. Special Education in Contemporary Society: An Introduction to Exceptionality (4th ed.). SAGE Publications, Thousand Oaks, CA. Page 76."},{"key":"e_1_3_3_2_8_2","volume-title":"The Contexts Reader (2nd ed.)","author":"Hartmann Douglas","year":"2011","unstructured":"Douglas Hartmann and Christopher Uggen (Eds.). 2011. The Contexts Reader (2nd ed.). W. W. Norton, New York. Page 165, \u201cThe Scarcity Fallacy\u201d."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Yupan Huang Tengchao Lv Lei Cui Yutong Lu and Furu Wei. 2022. LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking. arXiv:https:\/\/arXiv.org\/abs\/2204.08387 [cs]. 10.48550\/arXiv.2204.08387","DOI":"10.48550\/arXiv.2204.08387"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Guillaume Jaume Hazim\u00a0Kemal Ekenel and Jean-Philippe Thiran. 2019. FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents. arXiv:https:\/\/arXiv.org\/abs\/1905.13538 [cs]. 10.48550\/arXiv.1905.13538","DOI":"10.48550\/arXiv.1905.13538"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.41"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Zhang Li Yuliang Liu Qiang Liu Zhiyin Ma Ziyang Zhang Shuo Zhang Zidun Guo Jiarui Zhang Xinyu Wang and Xiang Bai. 2025. MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm. arXiv:https:\/\/arXiv.org\/abs\/2506.05218 [cs]. 10.48550\/arXiv.2506.05218","DOI":"10.48550\/arXiv.2506.05218"},{"key":"e_1_3_3_2_15_2","unstructured":"Chenglong Liu and others. 2024. Focus Anywhere for Fine-grained Multi-page Document Understanding."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Yuliang Liu Zhang Li Mingxin Huang Biao Yang Wenwen Yu Chunyuan Li Xucheng Yin Cheng-lin Liu Lianwen Jin and Xiang Bai. 2024. OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models. Science China Information Sciences 67 12 (Dec. 2024) 220102. arXiv:https:\/\/arXiv.org\/abs\/2305.07895 [cs]. 10.1007\/s11432-024-4235-6","DOI":"10.1007\/s11432-024-4235-6"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Urs-Viktor Marti and Horst Bunke. 2002. The IAM-Database: An English Sentence Database for Offline Handwriting Recognition. International Journal on Document Analysis and Recognition 5 (2002).","DOI":"10.1007\/s100320200071"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Minesh Mathew Dimosthenis Karatzas and C.\u00a0V. Jawahar. 2021. DocVQA: A Dataset for VQA on Document Images. arXiv:https:\/\/arXiv.org\/abs\/2007.00398 [cs]. 10.48550\/arXiv.2007.00398","DOI":"10.48550\/arXiv.2007.00398"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"e_1_3_3_2_21_2","unstructured":"OpenAI. 2023. GPT-4V(ision) System Card. https:\/\/openai.com\/research\/gpt-4v-system-card"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Linke Ouyang Yuan Qu Hongbin Zhou Jiawei Zhu Rui Zhang Qunshu Lin Bin Wang Zhiyuan Zhao Man Jiang Xiaomeng Zhao Jin Shi Fan Wu Pei Chu Minghao Liu Zhenxiang Li Chao Xu Bo Zhang Botian Shi Zhongying Tu and Conghui He. 2024. OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations. Version Number: 2. 10.48550\/ARXIV.2412.07626","DOI":"10.48550\/ARXIV.2412.07626"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Jake Poznanski Jon Borchardt Jason Dunkelberger Regan Huff Daniel Lin Aman Rangapur Christopher Wilhelm Kyle Lo and Luca Soldaini. 2025. olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models. arXiv:https:\/\/arXiv.org\/abs\/2502.18443 [cs]. 10.48550\/arXiv.2502.18443","DOI":"10.48550\/arXiv.2502.18443"},{"key":"e_1_3_3_2_25_2","unstructured":"Qwen Team. 2025. Qwen3-VL. https:\/\/github.com\/QwenLM\/Qwen3-VL"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Anhar Risnumawan Palaiahnakote Shivakumara Chee\u00a0Seng Chan and Chew\u00a0Lim Tan. 2014. A Robust Arbitrary Text Detection System for Natural Scene Images. Expert Systems with Applications 41 18 (2014).","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/icdar.2007.4376991"},{"key":"e_1_3_3_2_29_2","unstructured":"W3C. 2018. Web Content Accessibility Guidelines (WCAG) 2.1. W3C Recommendation. https:\/\/www.w3.org\/TR\/WCAG21\/"},{"key":"e_1_3_3_2_30_2","unstructured":"Bin Wang and others. 2024. UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Zilong Wang Yiheng Xu Lei Cui Jingbo Shang and Furu Wei. 2021. LayoutReader: Pre-training of Text and Layout for Reading Order Detection. arXiv:https:\/\/arXiv.org\/abs\/2108.11591 [cs]. 10.48550\/arXiv.2108.11591","DOI":"10.48550\/arXiv.2108.11591"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Haoran Wei Chenglong Liu Jinyue Chen Jia Wang Lingyu Kong Yanming Xu Zheng Ge Liang Zhao Jianjian Sun Yuang Peng Chunrui Han and Xiangyu Zhang. 2024. General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model. arXiv:https:\/\/arXiv.org\/abs\/2409.01704 [cs]. 10.48550\/arXiv.2409.01704","DOI":"10.48550\/arXiv.2409.01704"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Yang Xu Yiheng Xu Tengchao Lv Lei Cui Furu Wei Guoxin Wang Yijuan Lu Dinei Florencio Cha Zhang Wanxiang Che Min Zhang and Lidong Zhou. 2022. LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding. arXiv:https:\/\/arXiv.org\/abs\/2012.14740 [cs]. 10.48550\/arXiv.2012.14740","DOI":"10.48550\/arXiv.2012.14740"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Chong Zhang Yi Tu Yixi Zhao Chenshu Yuan Huan Chen Yue Zhang Mingxu Chai Ya Guo Huijia Zhu Qi Zhang and Tao Gui. 2024. Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding. arXiv:https:\/\/arXiv.org\/abs\/2409.19672 [cs]. 10.48550\/arXiv.2409.19672","DOI":"10.48550\/arXiv.2409.19672"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_34"}],"event":{"name":"JCDL '26: The 2026 ACM\/IEEE Joint Conference on Digital Libraries","location":"Frisco USA","acronym":"JCDL '26","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval","IEEE TCDL"]},"container-title":["Proceedings of the 26th ACM\/IEEE Joint Conference on Digital Libraries"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805696.3846504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T01:17:26Z","timestamp":1791940646000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805696.3846504"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,13]]},"references-count":36,"alternative-id":["10.1145\/3805696.3846504","10.1145\/3805696"],"URL":"https:\/\/doi.org\/10.1145\/3805696.3846504","relation":{},"subject":[],"published":{"date-parts":[[2026,10,13]]},"assertion":[{"value":"2026-10-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}