{"url":"/dataset/docbank","name":"DocBank","full_name":null,"description_markdown":"A benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. DocBank is constructed using a simple yet effective way with weak supervision from the \\LaTeX{} documents available on the arXiv.com.\r\n\r\nSource: [DocBank: A Benchmark Dataset for Document Layout Analysis](/paper/docbank-a-benchmark-dataset-for-document)","description_withheld":null,"homepage":"https://github.com/doc-analysis/DocBank","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/docbank-a-benchmark-dataset-for-document","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","first_author":"Minghao Li","url":null},"license":null,"modalities":[],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Document Layout Analysis","url":"/task/document-layout-analysis","datasets_with_task":"/datasets/task/document-layout-analysis"}],"languages":[],"variants":["DocBank"],"data_loaders":[{"repo":"https://github.com/doc-analysis/DocBank","url":"https://github.com/doc-analysis/DocBank","frameworks":[]}],"num_papers_in_archive":34,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}