{"url":"/dataset/kpbiomed","name":"KPBiomed","full_name":null,"description_markdown":"A large scale dataset of scientific records from PubMed for scientific keyphrase generation.\r\nThe dataset has three sizes: 500k, 2million and 5.6million documents\r\n\r\nEach document contains a title, an abstract, author keyphrases and some documents also have Mesh terms assigned by professional indexors.","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-large-scale-dataset-for-biomedical","title":"A Large-Scale Dataset for Biomedical Keyphrase Generation","first_author":"Mael Houbre","url":null},"license":{"name":"CC-BY-NC v4.0","url":null},"modalities":[],"tasks":[],"languages":[],"variants":["KPBiomed"],"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."}