{"url":"/dataset/forms-dataset","name":"Forms Dataset","full_name":null,"description_markdown":"The **Forms Dataset** is a dataset for document structure extraction comprising of 5K forms.","description_withheld":null,"homepage":"https://github.com/forms-data-structures/forms-data","introduced_date":"2021-07-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/multi-modal-association-based-grouping-for","title":"Multi-Modal Association based Grouping for Form Structure Extraction","first_author":"Milan Aggarwal","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[],"languages":[],"variants":["Forms Dataset"],"data_loaders":[],"num_papers_in_archive":3,"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":"2026-09-24T18:15:14+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."}