{"url":"/task/reading-order-detection","name":"Reading Order Detection","slug":"reading-order-detection","description_markdown":"Reading order detection aims to capture the word sequence which can be naturally comprehended by human readers from visually-rich documents. It is a fundamental task for visually-rich document understanding.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6,"papers_with_code":4,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/reading-order-detection-on-roor","slug":"reading-order-detection-on-roor","dataset":"ROOR","dataset_url":"/dataset/roor","rows_in_archive":4,"metrics":["Segment-level F1"],"first_row_in_archive_order":{"model":"LayoutLMv3-GlobalPointer (large)","paper_title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","paper_url":"/paper/modeling-layout-reading-order-as-ordering","paper_date":"2024-09-29","arxiv_id":"2409.19672","code_links":[{"title":"chongzhangFDU/ROOR","url":"https://github.com/chongzhangFDU/ROOR"}],"syntology":null}},{"leaderboard":"/sota/reading-order-detection-on-readingbank","slug":"reading-order-detection-on-readingbank","dataset":"ReadingBank","dataset_url":"/dataset/readingbank","rows_in_archive":2,"metrics":["Average Relative Distance (ARD)","Average Page-level BLEU"],"first_row_in_archive_order":{"model":"TPP (LayoutMask)","paper_title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","paper_url":"/paper/reading-order-matters-information-extraction","paper_date":"2023-10-17","arxiv_id":"2310.11016","code_links":[{"title":"chongzhangfdu/tpp","url":"https://github.com/chongzhangfdu/tpp"},{"title":"WinterShiver/Token-Path-Prediction","url":"https://github.com/WinterShiver/Token-Path-Prediction"}],"syntology":null}}],"datasets":[{"url":"/dataset/readingbank","name":"ReadingBank","full_name":"","num_papers_in_archive":6},{"url":"/dataset/roor","name":"ROOR","full_name":"","num_papers_in_archive":3},{"url":"/dataset/opendataset","name":"opendataset","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":6,"items":[{"url":"/paper/reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","repositories_listed":2,"syntology":null},{"url":"/paper/infinity-parser-layout-aware-reinforcement","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","date":"2025-06-01","arxiv_id":"2506.03197","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-layout-reading-order-as-ordering","title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","date":"2024-09-29","arxiv_id":"2409.19672","repositories_listed":1,"syntology":null},{"url":"/paper/layoutreader-pre-training-of-text-and-layout","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","date":"2021-08-26","arxiv_id":"2108.11591","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}