{"url":"/dataset/pubmed-paper-reading-dataset","name":"PubMed Paper Reading Dataset","full_name":null,"description_markdown":"This dataset gathers 14,857 entities, 133 relations, and entities corresponding tokenized text from PubMed. It contains 875,698 training pairs, 109,462 development pairs, and 109,462 test pairs.","description_withheld":null,"homepage":"https://eaglew.github.io/dataset/paperrobot_reading","introduced_date":"2019-05-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/paperrobot-incremental-draft-generation-of","title":"PaperRobot: Incremental Draft Generation of Scientific Ideas","first_author":"Qingyun Wang","url":null},"license":{"name":"MIT License","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"},{"name":"Paper generation","url":"/task/paper-generation","datasets_with_task":"/datasets/task/paper-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PubMed Paper Reading Dataset"],"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."}