{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OPH7XLKKHMXUMPZKXVWVHMLMUZ","short_pith_number":"pith:OPH7XLKK","schema_version":"1.0","canonical_sha256":"73cffbad4a3b2f463f2abd6d53b16ca64428469c6f34ec2ac157668391563ecc","source":{"kind":"arxiv","id":"1703.08619","version":4},"attestation_state":"computed","paper":{"title":"Binarsity: a penalization for one-hot encoded features in linear supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Agathe Guilloux, Mokhtar Z. Alaya, Simon Bussy, St\\'ephane Ga\\\"iffas","submitted_at":"2017-03-24T22:54:17Z","abstract_excerpt":"This paper deals with the problem of large-scale linear supervised learning in settings where a large number of continuous features are available. We propose to combine the well-known trick of one-hot encoding of continuous features with a new penalization called \\emph{binarsity}. In each group of binary features coming from the one-hot encoding of a single raw continuous feature, this penalization uses total-variation regularization together with an extra linear constraint. This induces two interesting properties on the model weights of the one-hot encoded features: they are piecewise constan"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1703.08619","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-24T22:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"e3f77d4eb341d5c0d5ec73724fcc2985dd3deb453f695974d6ce608522510ade","abstract_canon_sha256":"b5641f93694c6ac2a7b89a96bb6b381c70248379dcdc20d3c2ca735987047a6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:43.200597Z","signature_b64":"6n7dYpyhe6WrEmm5+DRF4j24wGMTsLquIUDHeR6sqPcxNrJ6qvk+UsjKr7mDxG3/7N5OevsTpgp8QQOZaC3mAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73cffbad4a3b2f463f2abd6d53b16ca64428469c6f34ec2ac157668391563ecc","last_reissued_at":"2026-05-17T23:56:43.200211Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:43.200211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Binarsity: a penalization for one-hot encoded features in linear supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Agathe Guilloux, Mokhtar Z. Alaya, Simon Bussy, St\\'ephane Ga\\\"iffas","submitted_at":"2017-03-24T22:54:17Z","abstract_excerpt":"This paper deals with the problem of large-scale linear supervised learning in settings where a large number of continuous features are available. We propose to combine the well-known trick of one-hot encoding of continuous features with a new penalization called \\emph{binarsity}. In each group of binary features coming from the one-hot encoding of a single raw continuous feature, this penalization uses total-variation regularization together with an extra linear constraint. This induces two interesting properties on the model weights of the one-hot encoded features: they are piecewise constan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08619","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.08619","created_at":"2026-05-17T23:56:43.200271+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.08619v4","created_at":"2026-05-17T23:56:43.200271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08619","created_at":"2026-05-17T23:56:43.200271+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPH7XLKKHMXU","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPH7XLKKHMXUMPZK","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPH7XLKK","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ","json":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ.json","graph_json":"https://pith.science/api/pith-number/OPH7XLKKHMXUMPZKXVWVHMLMUZ/graph.json","events_json":"https://pith.science/api/pith-number/OPH7XLKKHMXUMPZKXVWVHMLMUZ/events.json","paper":"https://pith.science/paper/OPH7XLKK"},"agent_actions":{"view_html":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ","download_json":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ.json","view_paper":"https://pith.science/paper/OPH7XLKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.08619&json=true","fetch_graph":"https://pith.science/api/pith-number/OPH7XLKKHMXUMPZKXVWVHMLMUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OPH7XLKKHMXUMPZKXVWVHMLMUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/action/storage_attestation","attest_author":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/action/author_attestation","sign_citation":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/action/citation_signature","submit_replication":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/action/replication_record"}},"created_at":"2026-05-17T23:56:43.200271+00:00","updated_at":"2026-05-17T23:56:43.200271+00:00"}