{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UONHQXDTCB6LRSCDGRDMA7MZRB","short_pith_number":"pith:UONHQXDT","schema_version":"1.0","canonical_sha256":"a39a785c73107cb8c8433446c07d99885c46420f28bdc4929cd2bdedc03579ef","source":{"kind":"arxiv","id":"1906.00938","version":1},"attestation_state":"computed","paper":{"title":"Big-Data Clustering: K-Means or K-Indicators?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Feiyu Chen, Liwei Xu, Taiping Zhang, Yin Zhang, Yuchen Yang","submitted_at":"2019-06-03T17:30:24Z","abstract_excerpt":"The K-means algorithm is arguably the most popular data clustering method, commonly applied to processed datasets in some \"feature spaces\", as is in spectral clustering. Highly sensitive to initializations, however, K-means encounters a scalability bottleneck with respect to the number of clusters K as this number grows in big data applications. In this work, we promote a closely related model called K-indicators model and construct an efficient, semi-convex-relaxation algorithm that requires no randomized initializations. We present extensive empirical results to show advantages of the new al"},"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":"1906.00938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:30:24Z","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"title_canon_sha256":"55156ba82bd0e3cd9e2bd7753c7e746413ad10779495f895c86eb555b9937788","abstract_canon_sha256":"580b167a69ed3ee0805b93918e0513e5c497c87f5c19ab43bb66147a2d2d2c92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:23.447982Z","signature_b64":"6HtvHU+yP3mCiys2AhQf1OgptltpwhTUOME2xEBI2M62bw9Zm61vo0IXzKV7FZWqvbMVRKEl5VixGDGb69/KBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a39a785c73107cb8c8433446c07d99885c46420f28bdc4929cd2bdedc03579ef","last_reissued_at":"2026-05-17T23:44:23.447474Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:23.447474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Big-Data Clustering: K-Means or K-Indicators?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Feiyu Chen, Liwei Xu, Taiping Zhang, Yin Zhang, Yuchen Yang","submitted_at":"2019-06-03T17:30:24Z","abstract_excerpt":"The K-means algorithm is arguably the most popular data clustering method, commonly applied to processed datasets in some \"feature spaces\", as is in spectral clustering. Highly sensitive to initializations, however, K-means encounters a scalability bottleneck with respect to the number of clusters K as this number grows in big data applications. In this work, we promote a closely related model called K-indicators model and construct an efficient, semi-convex-relaxation algorithm that requires no randomized initializations. We present extensive empirical results to show advantages of the new al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00938","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":"1906.00938","created_at":"2026-05-17T23:44:23.447557+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00938v1","created_at":"2026-05-17T23:44:23.447557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00938","created_at":"2026-05-17T23:44:23.447557+00:00"},{"alias_kind":"pith_short_12","alias_value":"UONHQXDTCB6L","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UONHQXDTCB6LRSCD","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UONHQXDT","created_at":"2026-05-18T12:33:30.264802+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/UONHQXDTCB6LRSCDGRDMA7MZRB","json":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB.json","graph_json":"https://pith.science/api/pith-number/UONHQXDTCB6LRSCDGRDMA7MZRB/graph.json","events_json":"https://pith.science/api/pith-number/UONHQXDTCB6LRSCDGRDMA7MZRB/events.json","paper":"https://pith.science/paper/UONHQXDT"},"agent_actions":{"view_html":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB","download_json":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB.json","view_paper":"https://pith.science/paper/UONHQXDT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00938&json=true","fetch_graph":"https://pith.science/api/pith-number/UONHQXDTCB6LRSCDGRDMA7MZRB/graph.json","fetch_events":"https://pith.science/api/pith-number/UONHQXDTCB6LRSCDGRDMA7MZRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/action/storage_attestation","attest_author":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/action/author_attestation","sign_citation":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/action/citation_signature","submit_replication":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/action/replication_record"}},"created_at":"2026-05-17T23:44:23.447557+00:00","updated_at":"2026-05-17T23:44:23.447557+00:00"}