{"url":"/dataset/cal10k","name":"CAL10K","full_name":"Computer Audition Lab 10000","description_markdown":"The **CAL10K** dataset (introduced as Swat10k) contains 10,870 songs that are weakly-labelled using a tag vocabulary of 475 acoustic tags and 153 genre tags. The tags have all been harvested from [Pandora’s](https://www.pandora.com/) website and result from song annotations performed by expert musicologists involved with the Music Genome Project.\n\nSource: [Exploring automatic music annotation with “acoustically-objectiv” tags](http://modelai.gettysburg.edu/2012/music/docs/Tingle_Autotag_MIR10.pdf)","description_withheld":null,"homepage":"http://calab1.ucsd.edu/~datasets/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"Exploring automatic music annotation with “acoustically-objectiv” tags","first_author":null,"url":"http://modelai.gettysburg.edu/2012/music/docs/Tingle_Autotag_MIR10.pdf"},"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Recommendation Systems","url":"/task/recommendation-systems","datasets_with_task":"/datasets/task/recommendation-systems"},{"name":"Quantization","url":"/task/quantization","datasets_with_task":"/datasets/task/quantization"},{"name":"Music Information Retrieval","url":"/task/music-information-retrieval","datasets_with_task":"/datasets/task/music-information-retrieval"}],"languages":[],"variants":["CAL10K"],"data_loaders":[],"num_papers_in_archive":1,"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."}