{"url":"/dataset/cord-19","name":"CORD-19","full_name":"CORD-19","description_markdown":"CORD-19 is a free resource of tens of thousands of scholarly articles about COVID-19, SARS-CoV-2, and related coronaviruses for use by the global research community.\r\n\r\nSource: [Allen Institute for AI](https://allenai.org/data/cord-19)","description_withheld":null,"homepage":"https://allenai.org/data/cord-19","introduced_date":"2020-04-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/cord-19-the-covid-19-open-research-dataset","title":"CORD-19: The COVID-19 Open Research Dataset","first_author":"Lucy Lu Wang","url":null},"license":{"name":"Semantic Scholar Dataset License","url":"http://s2-public-api-prod.us-west-2.elasticbeanstalk.com/corpus/legal/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Knowledge Graphs","url":"/task/knowledge-graphs","datasets_with_task":"/datasets/task/knowledge-graphs"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Unsupervised Text Summarization","url":"/task/unsupervised-text-summarization","datasets_with_task":"/datasets/task/unsupervised-text-summarization"}],"languages":[],"variants":["CORD-19","pritamdeka/cord-19-fulltext"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/cord19","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cord19","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/covid19sum","frameworks":["tf","jax"]}],"num_papers_in_archive":163,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-cord-19","task":"Text Summarization","dataset_variant":"CORD-19","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":"41.02","ROUGE-2":"13.79","ROUGE-L":"37.25"},"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":"2026-09-24T18:15:14+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."}