{"url":"/dataset/meshup","name":"MeSHup","full_name":"A Corpus for Full Text Biomedical Document Indexing","description_markdown":"Contains 1,342,667 full text articles in English, together with the associated MeSH labels and metadata, authors, and publication venues that are collected from the MEDLINE database.","description_withheld":null,"homepage":"https://github.com/xdwang0726/MeSHup","introduced_date":"2022-04-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/meshup-a-corpus-for-full-text-biomedical","title":"MeSHup: A Corpus for Full Text Biomedical Document Indexing","first_author":"Xindi Wang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Document Classification","url":"/task/document-classification","datasets_with_task":"/datasets/task/document-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MeSHup"],"data_loaders":[],"num_papers_in_archive":1,"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."}