{"url":"/dataset/orcas","name":"ORCAS","full_name":null,"description_markdown":"ORCAS is a click-based dataset. It covers 1.4 million of the TREC DL documents, providing 18 million connections to 10 million distinct queries.","description_withheld":null,"homepage":"https://microsoft.github.io/msmarco/ORCAS","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/orcas-18-million-clicked-query-document-pairs","title":"ORCAS: 18 Million Clicked Query-Document Pairs for Analyzing Search","first_author":"Nick Craswell","url":null},"license":null,"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"}],"languages":[],"variants":["ORCAS"],"data_loaders":[],"num_papers_in_archive":18,"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."}