{"artifacts":[{"compression":"none","distribution":"upstream-only","downloads":[{"kind":"upstream","url":"https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/w5a"}],"format":"libsvm","name":"train","sha256":"50599ff799c35726061b747912c106ee1b084280411c086f10e5adb3487c3993","size":690824},{"compression":"none","distribution":"upstream-only","downloads":[{"kind":"upstream","url":"https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary/w5a.t"}],"format":"libsvm","name":"test","sha256":"be5e85b5fd51e11c4446ab8dadaee5879c2fead6ca5f2c56c588216279f90ce7","size":2787414}],"description":"The w5a 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#w5a. The LIBSVM software license does not establish a license for the distributed dataset.","status":"unknown"},"modality":"tabular","name":"w5a","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#w5a","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#w5a","provider":"LIBSVM","retrieved_at":"2026-10-26","upstream_name":"w5a"},"representation":{"decoder":"libsvm-split","decoder_version":1,"expect":{"components":[{"columns":300,"kind":"sparse_matrix","name":"train_features","rows":9888,"type":"float64"},{"kind":"vector","length":9888,"name":"train_response","type":"int64"},{"columns":300,"kind":"sparse_matrix","name":"test_features","rows":39861,"type":"float64"},{"kind":"vector","length":39861,"name":"test_response","type":"int64"}],"verification":[{"algorithm":"sha256","canonical_form":1,"digest":"219cd12188bdd54f4e0c983bc4fba4bb59ddaf18f97d2dc8994a6083e88887d2"}]},"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 (w5a)","version":"1"}