{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7BOOI4BUVCXRCXQ3WYUNOE3QYL","short_pith_number":"pith:7BOOI4BU","schema_version":"1.0","canonical_sha256":"f85ce47034a8af115e1bb628d71370c2c1edf0eea515bd847ef638c2eea81429","source":{"kind":"arxiv","id":"2408.17244","version":3},"attestation_state":"computed","paper":{"title":"Categorical data clustering: 25 years beyond K-modes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniil Lisik, Hieu-Chi Dam, Minh-Quyet Ha, Philippe Fournier-Viger, Tai Dinh, Van-Nam Huynh, Wong Hauchi","submitted_at":"2024-08-30T12:36:00Z","abstract_excerpt":"The clustering of categorical data is a common and important task in computer science, offering profound implications across a spectrum of applications. Unlike purely numerical data, categorical data often lack inherent ordering as in nominal data, or have varying levels of order as in ordinal data, thus requiring specialized methodologies for efficient organization and analysis. This review provides a comprehensive synthesis of categorical data clustering in the past twenty-five years, starting from the introduction of K-modes. It elucidates the pivotal role of categorical data clustering in "},"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":"2408.17244","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-30T12:36:00Z","cross_cats_sorted":[],"title_canon_sha256":"dd76ca52bc82b9e6ea7d52144331541e15b9cd3ac42e0fa3ec5608e5f1235164","abstract_canon_sha256":"3752a2fd0fa57f7e202aab9d4cc7c29277545e42a3a5efc66d46b541e77467a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:12.621956Z","signature_b64":"MRloaQQOxa/csytd2wD8Pp+oBKG98oAnE0CeBhT1qpAZrzSCVhu9VJm4mAZnylGcsilIDGjqFe/J7t9Q0FBXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85ce47034a8af115e1bb628d71370c2c1edf0eea515bd847ef638c2eea81429","last_reissued_at":"2026-07-05T10:05:12.621459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:12.621459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Categorical data clustering: 25 years beyond K-modes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniil Lisik, Hieu-Chi Dam, Minh-Quyet Ha, Philippe Fournier-Viger, Tai Dinh, Van-Nam Huynh, Wong Hauchi","submitted_at":"2024-08-30T12:36:00Z","abstract_excerpt":"The clustering of categorical data is a common and important task in computer science, offering profound implications across a spectrum of applications. Unlike purely numerical data, categorical data often lack inherent ordering as in nominal data, or have varying levels of order as in ordinal data, thus requiring specialized methodologies for efficient organization and analysis. This review provides a comprehensive synthesis of categorical data clustering in the past twenty-five years, starting from the introduction of K-modes. It elucidates the pivotal role of categorical data clustering in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.17244","kind":"arxiv","version":3},"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/2408.17244/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":"2408.17244","created_at":"2026-07-05T10:05:12.621515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.17244v3","created_at":"2026-07-05T10:05:12.621515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.17244","created_at":"2026-07-05T10:05:12.621515+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BOOI4BUVCXR","created_at":"2026-07-05T10:05:12.621515+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BOOI4BUVCXRCXQ3","created_at":"2026-07-05T10:05:12.621515+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BOOI4BU","created_at":"2026-07-05T10:05:12.621515+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/7BOOI4BUVCXRCXQ3WYUNOE3QYL","json":"https://pith.science/pith/7BOOI4BUVCXRCXQ3WYUNOE3QYL.json","graph_json":"https://pith.science/api/pith-number/7BOOI4BUVCXRCXQ3WYUNOE3QYL/graph.json","events_json":"https://pith.science/api/pith-number/7BOOI4BUVCXRCXQ3WYUNOE3QYL/events.json","paper":"https://pith.science/paper/7BOOI4BU"},"agent_actions":{"view_html":"https://pith.science/pith/7BOOI4BUVCXRCXQ3WYUNOE3QYL","download_json":"https://pith.science/pith/7BOOI4BUVCXRCXQ3WYUNOE3QYL.json","view_paper":"https://pith.science/paper/7BOOI4BU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.17244&json=true","fetch_graph":"https://pith.science/api/pith-number/7BOOI4BUVCXRCXQ3WYUNOE3QYL/graph.json","fetch_events":"https://pith.science/api/pith-number/7BOOI4BUVCXRCXQ3WYUNOE3QYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BOOI4BUVCXRCXQ3WYUNOE3QYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BOOI4BUVCXRCXQ3WYUNOE3QYL/action/storage_attestation","attest_author":"https://pith.science/pith/7BOOI4BUVCXRCXQ3WYUNOE3QYL/action/author_attestation","sign_citation":"https://pith.science/pith/7BOOI4BUVCXRCXQ3WYUNOE3QYL/action/citation_signature","submit_replication":"https://pith.science/pith/7BOOI4BUVCXRCXQ3WYUNOE3QYL/action/replication_record"}},"created_at":"2026-07-05T10:05:12.621515+00:00","updated_at":"2026-07-05T10:05:12.621515+00:00"}