{"artifacts":[{"compression":"none","distribution":"upstream-only","downloads":[{"kind":"upstream","url":"https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/w7a"}],"format":"libsvm","name":"train","sha256":"bd02f445a1a2f4aaefd27d7dcc31f1f6a8521f904157f2ee7c96d1294cd26e36","size":1729215},{"compression":"none","distribution":"upstream-only","downloads":[{"kind":"upstream","url":"https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/w7a.t"}],"format":"libsvm","name":"test","sha256":"a52edcfe9871e3b0db5d864959bf32230491ddfeca3334cfec93c1d932ea32b9","size":1749023}],"description":"The w7a 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#w7a. The LIBSVM software license does not establish a license for the distributed dataset.","status":"unknown"},"modality":"tabular","name":"w7a","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#w7a","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#w7a","provider":"LIBSVM","retrieved_at":"2026-10-26","upstream_name":"w7a"},"representation":{"decoder":"libsvm-split","decoder_version":1,"expect":{"components":[{"columns":300,"kind":"sparse_matrix","name":"train_features","rows":24692,"type":"float64"},{"kind":"vector","length":24692,"name":"train_response","type":"int64"},{"columns":300,"kind":"sparse_matrix","name":"test_features","rows":25057,"type":"float64"},{"kind":"vector","length":25057,"name":"test_response","type":"int64"}],"verification":[{"algorithm":"sha256","canonical_form":1,"digest":"ace844cb05ca4d82e56bd8fff446c25a3deb07c32aa7cefc50f5a91eed620601"}]},"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 (w7a)","version":"1"}