{"url":"/dataset/arch","name":"ARCH","full_name":null,"description_markdown":"**ARCH** is a computational pathology (CP) multiple instance captioning dataset to facilitate dense supervision of CP tasks. Existing CP datasets focus on narrow tasks; ARCH on the other hand contains dense diagnostic and morphological descriptions for a range of stains, tissue types and pathologies. \r\n\r\nSource: [Gamper et al.](https://arxiv.org/pdf/2103.05121v1.pdf)\r\n\r\nImage source: [Gamper et al.](https://arxiv.org/pdf/2103.05121v1.pdf)","description_withheld":null,"homepage":"https://arxiv.org/pdf/2103.05121v1.pdf","introduced_date":"2021-03-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/multiple-instance-captioning-learning","title":"Multiple Instance Captioning: Learning Representations from Histopathology Textbooks and Articles","first_author":"Jevgenij Gamper","url":null},"license":null,"modalities":[{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ARCH"],"data_loaders":[],"num_papers_in_archive":11,"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."}