{"url":"/dataset/s2orc","name":"S2ORC","full_name":"S2ORC","description_markdown":"A large corpus of 81.1M English-language academic papers spanning many academic disciplines. Rich metadata, paper abstracts, resolved bibliographic references, as well as structured full text for 8.1M open access papers. Full text annotated with automatically-detected inline mentions of citations, figures, and tables, each linked to their corresponding paper objects. Aggregated papers from hundreds of academic publishers and digital archives into a unified source, and create the largest publicly-available collection of machine-readable academic text to date.\r\n\r\nSource: [Allen Institute for AI](https://allenai.org/data/s2orc)","description_withheld":null,"homepage":"https://allenai.org/data/s2orc","introduced_date":"2019-11-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/gorc-a-large-contextual-citation-graph-of","title":"S2ORC: The Semantic Scholar Open Research Corpus","first_author":"Kyle Lo","url":null},"license":{"name":"CC BY-NC 2.0","url":"https://creativecommons.org/licenses/by-nc/2.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Citation Recommendation","url":"/task/citation-recommendation","datasets_with_task":"/datasets/task/citation-recommendation"}],"languages":[],"variants":["S2ORC"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/s2orc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/s2orc","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":152,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-s2orc","task":"Text Summarization","dataset_variant":"S2ORC","rows":1,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"GenCompareSum","paper":"/paper/gencomparesum-a-hybrid-unsupervised","metrics":{"ROUGE-1":"43.39","ROUGE-2":"16.84","ROUGE-L":"39.82"},"code_links":[{"title":"jbshp/gencomparesum","url":"https://github.com/jbshp/gencomparesum"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/gencomparesum-a-hybrid-unsupervised","title":"GenCompareSum: a hybrid unsupervised summarization method using salience","date":"2022-05-01","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}