{"url":"/dataset/trec-covid","name":"TREC-COVID","full_name":null,"description_markdown":"TREC-COVID is a community evaluation designed to build a test collection that captures the information needs of biomedical researchers using the scientific literature during a pandemic. One of the key characteristics of pandemic search is the accelerated rate of change: the topics of interest evolve as the pandemic progresses and the scientific literature in the area explodes. The COVID-19 pandemic provides an opportunity to capture this progression as it happens. TREC-COVID, in creating a test collection around COVID-19 literature, is building infrastructure to support new research and technologies in pandemic search.","description_withheld":null,"homepage":"https://ir.nist.gov/trec-covid/","introduced_date":"2020-05-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/trec-covid-constructing-a-pandemic","title":"TREC-COVID: Constructing a Pandemic Information Retrieval Test Collection","first_author":"Ellen Voorhees","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Zero-shot Text Search","url":"/task/zero-shot-text-search","datasets_with_task":"/datasets/task/zero-shot-text-search"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TREC-COVID"],"data_loaders":[],"num_papers_in_archive":73,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-retrieval-on-trec-covid","task":"Text Retrieval","dataset_variant":"TREC-COVID","rows":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","metrics":{"nDCG@10":"58.9"},"code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":22,"samples_ran":10,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":22,"samples_ran":10,"samples_unverified":12,"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."}