{"url":"/dataset/orcas-i","name":"ORCAS-I","full_name":"Queries Annotated with Intent using Weak Supervision","description_markdown":"A labelled version of the ORCAS click-based dataset of Web queries, which provides 18 million connections to 10 million distinct queries.\r\n\r\nDOI of the dataset: 10.48436/pp7xz-n9a06","description_withheld":null,"homepage":"https://researchdata.tuwien.ac.at/records/pp7xz-n9a06","introduced_date":"2022-05-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/orcas-i-queries-annotated-with-intent-using","title":"ORCAS-I: Queries Annotated with Intent using Weak Supervision","first_author":"Daria Alexander","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Intent Classification","url":"/task/intent-classification","datasets_with_task":"/datasets/task/intent-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ORCAS-I"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/intent-classification-on-orcas-i","task":"Intent Classification","dataset_variant":"ORCAS-I","rows":1,"metrics":["F1-score","Precision","Recall"],"first_row_in_archive_order":{"model":"BERT (query + URL)","paper":"/paper/orcas-i-queries-annotated-with-intent-using","metrics":{"F1-score":"0.774","Precision":"0.789","Recall":"0.764"},"code_links":[{"title":"projectdossier/intents_labelling","url":"https://github.com/projectdossier/intents_labelling"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/orcas-i-queries-annotated-with-intent-using","title":"ORCAS-I: Queries Annotated with Intent using Weak Supervision","date":"2022-05-02","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."}