{"url":"/dataset/readingbank","name":"ReadingBank","full_name":null,"description_markdown":"ReadingBank is a benchmark dataset for reading order detection built with weak supervision from WORD documents, which contains 500K document images with a wide range of document types as well as the corresponding reading order information.","description_withheld":null,"homepage":"https://github.com/doc-analysis/ReadingBank","introduced_date":"2021-08-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/layoutreader-pre-training-of-text-and-layout","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","first_author":"Zilong Wang","url":null},"license":null,"modalities":[],"tasks":[{"name":"Reading Order Detection","url":"/task/reading-order-detection","datasets_with_task":"/datasets/task/reading-order-detection"}],"languages":[],"variants":["ReadingBank"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/reading-order-detection-on-readingbank","task":"Reading Order Detection","dataset_variant":"ReadingBank","rows":2,"metrics":["Average Relative Distance (ARD)","Average Page-level BLEU"],"first_row_in_archive_order":{"model":"TPP (LayoutMask)","paper":"/paper/reading-order-matters-information-extraction","metrics":{"Average Page-level BLEU":"98.16","Average Relative Distance (ARD)":"0.37"},"code_links":[{"title":"chongzhangfdu/tpp","url":"https://github.com/chongzhangfdu/tpp"},{"title":"WinterShiver/Token-Path-Prediction","url":"https://github.com/WinterShiver/Token-Path-Prediction"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/layoutreader-pre-training-of-text-and-layout","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","date":"2021-08-26","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}