{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KX3JBMJF7WCMD4E5WMSV2HJ22B","short_pith_number":"pith:KX3JBMJF","schema_version":"1.0","canonical_sha256":"55f690b125fd84c1f09db3255d1d3ad06666ab09f63d72e2a10c5b0bca9b1e4e","source":{"kind":"arxiv","id":"1806.00979","version":1},"attestation_state":"computed","paper":{"title":"Similarity encoding for learning with dirty categorical variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bal\\'azs K\\'egl (LAL, CNRS), Ga\\\"el Varoquaux (Parietal), Patricio Cerda (PARIETAL)","submitted_at":"2018-06-04T06:46:22Z","abstract_excerpt":"For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. \"Dirty\" non-curated data gives rise to categorical variables with a very high cardinality but redundancy: several categories reflect the same entity. In databases, this issue is typically solved with a deduplication step. We show that a simple approach that exposes the redundancy to the learning algorithm brings significant gains. We study a generalization of one-hot encoding, similarity encoding, that builds feature vect"},"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":"1806.00979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-04T06:46:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8fac2d789d2447b8133e38f1b948bf729b58d8a1d074df3d26811809ae9db0ec","abstract_canon_sha256":"231f60f8162f38fda2aaf34796c49bb9eed2ff27f05d53f0333749bf47981643"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:17.836572Z","signature_b64":"Vg2SBEos4Dx8jq0m7xzDv+CXO3i4+jOj5GsXc2rEDX4+JWbg4KFXvZVqRyEBGVYIbxpn9M49977S4HmP/OaMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55f690b125fd84c1f09db3255d1d3ad06666ab09f63d72e2a10c5b0bca9b1e4e","last_reissued_at":"2026-05-18T00:14:17.835994Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:17.835994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Similarity encoding for learning with dirty categorical variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bal\\'azs K\\'egl (LAL, CNRS), Ga\\\"el Varoquaux (Parietal), Patricio Cerda (PARIETAL)","submitted_at":"2018-06-04T06:46:22Z","abstract_excerpt":"For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. \"Dirty\" non-curated data gives rise to categorical variables with a very high cardinality but redundancy: several categories reflect the same entity. In databases, this issue is typically solved with a deduplication step. We show that a simple approach that exposes the redundancy to the learning algorithm brings significant gains. We study a generalization of one-hot encoding, similarity encoding, that builds feature vect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00979","kind":"arxiv","version":1},"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":"1806.00979","created_at":"2026-05-18T00:14:17.836057+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00979v1","created_at":"2026-05-18T00:14:17.836057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00979","created_at":"2026-05-18T00:14:17.836057+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX3JBMJF7WCM","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX3JBMJF7WCMD4E5","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX3JBMJF","created_at":"2026-05-18T12:32:33.847187+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/KX3JBMJF7WCMD4E5WMSV2HJ22B","json":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B.json","graph_json":"https://pith.science/api/pith-number/KX3JBMJF7WCMD4E5WMSV2HJ22B/graph.json","events_json":"https://pith.science/api/pith-number/KX3JBMJF7WCMD4E5WMSV2HJ22B/events.json","paper":"https://pith.science/paper/KX3JBMJF"},"agent_actions":{"view_html":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B","download_json":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B.json","view_paper":"https://pith.science/paper/KX3JBMJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00979&json=true","fetch_graph":"https://pith.science/api/pith-number/KX3JBMJF7WCMD4E5WMSV2HJ22B/graph.json","fetch_events":"https://pith.science/api/pith-number/KX3JBMJF7WCMD4E5WMSV2HJ22B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/action/storage_attestation","attest_author":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/action/author_attestation","sign_citation":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/action/citation_signature","submit_replication":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/action/replication_record"}},"created_at":"2026-05-18T00:14:17.836057+00:00","updated_at":"2026-05-18T00:14:17.836057+00:00"}