{"artifacts":[{"compression":"none","distribution":"upstream-only","downloads":[{"kind":"upstream","url":"https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/w1a"}],"format":"libsvm","name":"train","sha256":"0ae2b1c40f6a99061d1c6f4a1f3b50eea58a2f3b8bf851a337c25c2a65a49d32","size":170263},{"compression":"none","distribution":"upstream-only","downloads":[{"kind":"upstream","url":"https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/w1a.t"}],"format":"libsvm","name":"test","sha256":"c5e489a499286d69c8c2035cb04bc48e2ea1f73e56153c72cc50b29732a9316a","size":3307975}],"description":"The w1a binary classification variant of the Web dataset, distributed by LIBSVM with predefined training and test artifacts and 300 sparse features.","license":{"evidence":"The LIBSVM dataset page identifies Platt's JP98a reference as the source but states no license terms for these artifacts: https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html#w1a. The LIBSVM software license does not establish a license for the distributed dataset.","status":"unknown"},"modality":"tabular","name":"w1a","preprocessing":{"datamonger":{"evidence":["spec/decoders/libsvm-v1.md"],"notes":"Datamonger decodes the provider artifacts without additional statistical preprocessing.","status":"none"},"upstream":{"evidence":["https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html#w1a","https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/ref.html#JP98a"],"notes":"LIBSVM documents the feature count and training and test sizes but does not describe feature construction, sample selection, or the split selection procedure for these artifacts.","status":"unknown"}},"provenance":{"authors":["John C. Platt"],"citations":[{"citation":"John C. Platt. Fast training of support vector machines using sequential minimal optimization. In Advances in Kernel Methods - Support Vector Learning. MIT Press, 1998.","note":"Reference JP98a associated with this variant by LIBSVM: https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/ref.html#JP98a.","role":"paper"}],"landing_page":"https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html#w1a","provider":"LIBSVM","retrieved_at":"2026-10-26","upstream_name":"w1a"},"representation":{"decoder":"libsvm-split","decoder_version":1,"expect":{"components":[{"columns":300,"kind":"sparse_matrix","name":"train_features","rows":2477,"type":"float64"},{"kind":"vector","length":2477,"name":"train_response","type":"int64"},{"columns":300,"kind":"sparse_matrix","name":"test_features","rows":47272,"type":"float64"},{"kind":"vector","length":47272,"name":"test_response","type":"int64"}],"verification":[{"algorithm":"sha256","canonical_form":1,"digest":"ea664a763c2dabb912cee5362ab0218c1c94c22c12389e6dc74a2bc9bfe11920"}]},"inputs":{"test":"test","train":"train"},"options":{"duplicate_features":"error","feature_count":300,"index_base":1,"label_type":"int64","row_order":"source","target_name":"response"}},"schema_version":4,"source":"libsvm","tasks":[{"name":"default","splits":{"test":{"features":"test_features","target":"test_response"},"train":{"features":"train_features","target":"train_response"}},"type":"classification"}],"title":"Web (w1a)","version":"1"}