{"url":"/dataset/scitsr","name":"SciTSR","full_name":null,"description_markdown":"**SciTSR** is a large-scale table structure recognition dataset, which contains 15,000 tables in PDF format and their corresponding structure labels obtained from LaTeX source files.\n\nSource: [https://github.com/Academic-Hammer/SciTSR](https://github.com/Academic-Hammer/SciTSR)","description_withheld":null,"homepage":"https://github.com/Academic-Hammer/SciTSR","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/complicated-table-structure-recognition","title":"Complicated Table Structure Recognition","first_author":"Zewen Chi","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Table Detection","url":"/task/table-detection","datasets_with_task":"/datasets/task/table-detection"}],"languages":[],"variants":["SciTSR"],"data_loaders":[{"repo":"https://github.com/Academic-Hammer/SciTSR","url":"https://github.com/Academic-Hammer/SciTSR","frameworks":[]}],"num_papers_in_archive":36,"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."}