{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CPAYHQHBZZF3VZSVM2KDBOWFUI","short_pith_number":"pith:CPAYHQHB","schema_version":"1.0","canonical_sha256":"13c183c0e1ce4bbae655669430bac5a23d4dcbe6c0b16363f532828bb2230b6b","source":{"kind":"arxiv","id":"2501.05646","version":1},"attestation_state":"computed","paper":{"title":"Efficient Representations for High-Cardinality Categorical Variables in Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Zixuan Liang","submitted_at":"2025-01-10T01:25:01Z","abstract_excerpt":"High\\-cardinality categorical variables pose significant challenges in machine learning, particularly in terms of computational efficiency and model interpretability. Traditional one\\-hot encoding often results in high\\-dimensional sparse feature spaces, increasing the risk of overfitting and reducing scalability. This paper introduces novel encoding techniques, including means encoding, low\\-rank encoding, and multinomial logistic regression encoding, to address these challenges. These methods leverage sufficient representations to generate compact and informative embeddings of categorical da"},"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":"2501.05646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-10T01:25:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ce163a473fad9ded964dd1a461f8f4a0ad39c2d1b0216ed65ae1cbbcc43416f","abstract_canon_sha256":"21198e18323b3c98c6f9142ba5f1c5c83da7bbde7e7b6bc41e1b91fb0c78942a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:26.583675Z","signature_b64":"4yF8jEZlZDx5uLz/q2DuNd0GXCQOO8HNjEA4MImH2aaMZfrbs3yUE4tr0gHYSE55WHrSlu4iHcAozTX5bT41Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13c183c0e1ce4bbae655669430bac5a23d4dcbe6c0b16363f532828bb2230b6b","last_reissued_at":"2026-07-05T09:59:26.583300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:26.583300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Representations for High-Cardinality Categorical Variables in Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Zixuan Liang","submitted_at":"2025-01-10T01:25:01Z","abstract_excerpt":"High\\-cardinality categorical variables pose significant challenges in machine learning, particularly in terms of computational efficiency and model interpretability. Traditional one\\-hot encoding often results in high\\-dimensional sparse feature spaces, increasing the risk of overfitting and reducing scalability. This paper introduces novel encoding techniques, including means encoding, low\\-rank encoding, and multinomial logistic regression encoding, to address these challenges. These methods leverage sufficient representations to generate compact and informative embeddings of categorical da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05646","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.05646/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2501.05646","created_at":"2026-07-05T09:59:26.583368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05646v1","created_at":"2026-07-05T09:59:26.583368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05646","created_at":"2026-07-05T09:59:26.583368+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPAYHQHBZZF3","created_at":"2026-07-05T09:59:26.583368+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPAYHQHBZZF3VZSV","created_at":"2026-07-05T09:59:26.583368+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPAYHQHB","created_at":"2026-07-05T09:59:26.583368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02519","citing_title":"Evaluating Tabular Representation Learning for Network Intrusion Detection","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI","json":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI.json","graph_json":"https://pith.science/api/pith-number/CPAYHQHBZZF3VZSVM2KDBOWFUI/graph.json","events_json":"https://pith.science/api/pith-number/CPAYHQHBZZF3VZSVM2KDBOWFUI/events.json","paper":"https://pith.science/paper/CPAYHQHB"},"agent_actions":{"view_html":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI","download_json":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI.json","view_paper":"https://pith.science/paper/CPAYHQHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05646&json=true","fetch_graph":"https://pith.science/api/pith-number/CPAYHQHBZZF3VZSVM2KDBOWFUI/graph.json","fetch_events":"https://pith.science/api/pith-number/CPAYHQHBZZF3VZSVM2KDBOWFUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI/action/storage_attestation","attest_author":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI/action/author_attestation","sign_citation":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI/action/citation_signature","submit_replication":"https://pith.science/pith/CPAYHQHBZZF3VZSVM2KDBOWFUI/action/replication_record"}},"created_at":"2026-07-05T09:59:26.583368+00:00","updated_at":"2026-07-05T09:59:26.583368+00:00"}