{"url":"/dataset/d3","name":"D3","full_name":"DBLP Discovery Dataset","description_markdown":"DBLP is the largest open-access repository of scientific articles on computer science and provides metadata associated with publications, authors, and venues. We retrieved more than 6 million publications from DBLP and extracted pertinent metadata (e.g., abstracts, author affiliations, citations) from the publication texts to create the D3 Discovery Dataset (D3). D3 can be used to identify trends in research activity, productivity, focus, bias, accessibility, and impact of computer science research.","description_withheld":null,"homepage":"https://dblp.org/","introduced_date":"2022-04-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/d3-a-massive-dataset-of-scholarly-metadata","title":"D3: A Massive Dataset of Scholarly Metadata for Analyzing the State of Computer Science Research","first_author":"Jan Philip Wahle","url":null},"license":{"name":"CC0-1.0","url":"https://creativecommons.org/publicdomain/zero/1.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["D3"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jpwahle/dblp-discovery-dataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/gipplab/d3-dataset","url":"https://github.com/gipplab/d3-dataset","frameworks":[]}],"num_papers_in_archive":4,"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":"2026-09-25T09:33:49+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."}