{"url":"/dataset/mslr-web30k-1","name":"MSLR-WEB30K","full_name":null,"description_markdown":"The **MSLR-WEB30K** dataset consists of 30,000 search queries over the documents from search results. The data also contains the values of 136 features and a corresponding user-labeled relevance factor on a scale of one to five with respect to each query-document pair.","description_withheld":null,"homepage":"https://www.microsoft.com/en-us/research/project/mslr/","introduced_date":"2013-06-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/13062597","title":"Introducing LETOR 4.0 Datasets","first_author":"Tao Qin","url":null},"license":{"name":"Custom","url":"https://www.microsoft.com/en-us/research/project/mslr/"},"modalities":[],"tasks":[{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"}],"languages":[],"variants":["MSLR-WEB30K"],"data_loaders":[],"num_papers_in_archive":31,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/information-retrieval-on-mslr-web30k","task":"Information Retrieval","dataset_variant":"MSLR-WEB30K","rows":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Distilled Network","paper":"/paper/distilled-neural-networks-for-efficient","metrics":{"nDCG@10":"0.5259"},"code_links":[{"title":"hpclab/efficient_nn_for_ltr","url":"https://github.com/hpclab/efficient_nn_for_ltr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/distilled-neural-networks-for-efficient","title":"Distilled Neural Networks for Efficient Learning to Rank","date":"2022-02-22","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."}