{"url":"/dataset/musk-v2","name":"Musk v2","full_name":"Musk v2","description_markdown":"The Musk2 dataset is a set of 102 molecules of which 39 are judged by human experts to be musks and the remaining 63 molecules are judged to be non-musks. Each instance corresponds to a possible configuration of a molecule. The 166 features that describe these molecules depend upon the exact shape, or conformation, of the molecule.\n\nSource: [Confidence-Constrained Maximum Entropy Framework for Learning from Multi-Instance Data](https://arxiv.org/abs/1603.01901)","description_withheld":null,"homepage":"https://archive.ics.uci.edu/ml/datasets/Musk+(Version+2)","introduced_date":"1997-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/solving-the-multiple-instance-problem-with","title":"Solving the multiple instance problem with axis-parallel rectangles","first_author":"Thomas G. Dietteric","url":null},"license":null,"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Multiple Instance Learning","url":"/task/multiple-instance-learning","datasets_with_task":"/datasets/task/multiple-instance-learning"}],"languages":[],"variants":["Musk v2"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multiple-instance-learning-on-musk-v2","task":"Multiple Instance Learning","dataset_variant":"Musk v2","rows":2,"metrics":["ACC","AUC"],"first_row_in_archive_order":{"model":"DSMIL","paper":"/paper/dual-stream-multiple-instance-learning","metrics":{"ACC":"0.934"},"code_links":[{"title":"binli123/dsmil-wsi","url":"https://github.com/binli123/dsmil-wsi"},{"title":"Xiyue-Wang/RetCCL","url":"https://github.com/Xiyue-Wang/RetCCL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/snuffy-efficient-whole-slide-image-classifier","title":"Snuffy: Efficient Whole Slide Image Classifier","date":"2024-08-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dual-stream-multiple-instance-learning","title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","date":"2020-11-17","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"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":6,"samples_ran":4,"samples_unverified":2,"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."}