{"url":"/dataset/toollens","name":"ToolLens","full_name":null,"description_markdown":"The ToolLens dataset consists of 18,770 concise yet intentionally multifaceted queries, each associated with 1 to 3 verified tools out of a total of 464, designed to better mimic real-world user interactions.","description_withheld":null,"homepage":"https://huggingface.co/datasets/stuedu/ToolLens/tree/main","introduced_date":"2024-05-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/colt-towards-completeness-oriented-tool","title":"Towards Completeness-Oriented Tool Retrieval for Large Language Models","first_author":"Changle Qu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Retrieval","url":"/task/retrieval","datasets_with_task":"/datasets/task/retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ToolLens"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/retrieval-on-toollens","task":"Retrieval","dataset_variant":"ToolLens","rows":1,"metrics":["COMP@"],"first_row_in_archive_order":{"model":"COLT","paper":"/paper/colt-towards-completeness-oriented-tool","metrics":{"COMP@":"84.55"},"code_links":[{"title":"quchangle1/colt","url":"https://github.com/quchangle1/colt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/colt-towards-completeness-oriented-tool","title":"Towards Completeness-Oriented Tool Retrieval for Large Language Models","date":"2024-05-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"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."}