{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:ZUPVTTU5XNRWIU3WN553F5NYUS","short_pith_number":"pith:ZUPVTTU5","schema_version":"1.0","canonical_sha256":"cd1f59ce9dbb636453766f7bb2f5b8a4abb0594cb818f7253a3061d20846d9f8","source":{"kind":"arxiv","id":"1402.3849","version":1},"attestation_state":"computed","paper":{"title":"Scalable Kernel Clustering: Approximate Kernel k-means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anil K. Jain, Radha Chitta, Rong Jin, Timothy C. Havens","submitted_at":"2014-02-16T22:19:40Z","abstract_excerpt":"Kernel-based clustering algorithms have the ability to capture the non-linear structure in real world data. Among various kernel-based clustering algorithms, kernel k-means has gained popularity due to its simple iterative nature and ease of implementation. However, its run-time complexity and memory footprint increase quadratically in terms of the size of the data set, and hence, large data sets cannot be clustered efficiently. In this paper, we propose an approximation scheme based on randomization, called the Approximate Kernel k-means. We approximate the cluster centers using the kernel si"},"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":"1402.3849","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-02-16T22:19:40Z","cross_cats_sorted":["cs.DS","cs.LG"],"title_canon_sha256":"96ccf65cccd933548bc06f6bf4c2ccc2d38af67c85c9caf1128e4a855fa5217b","abstract_canon_sha256":"21af4d3edea3150f56ac45ecb3a1dd04d0f542295f77097fe26f08d527f7941e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:58:47.018952Z","signature_b64":"S2qdeBPVTM3J+u93jXJTpQkU/yXJ2Ybv2Lg4HsHKPF7xsptTp+QSFDtiUq8OFrC4OjPvA9bPHWbpv7fflhtGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd1f59ce9dbb636453766f7bb2f5b8a4abb0594cb818f7253a3061d20846d9f8","last_reissued_at":"2026-05-18T02:58:47.018128Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:58:47.018128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Kernel Clustering: Approximate Kernel k-means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anil K. Jain, Radha Chitta, Rong Jin, Timothy C. Havens","submitted_at":"2014-02-16T22:19:40Z","abstract_excerpt":"Kernel-based clustering algorithms have the ability to capture the non-linear structure in real world data. Among various kernel-based clustering algorithms, kernel k-means has gained popularity due to its simple iterative nature and ease of implementation. However, its run-time complexity and memory footprint increase quadratically in terms of the size of the data set, and hence, large data sets cannot be clustered efficiently. In this paper, we propose an approximation scheme based on randomization, called the Approximate Kernel k-means. We approximate the cluster centers using the kernel si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.3849","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":"1402.3849","created_at":"2026-05-18T02:58:47.018265+00:00"},{"alias_kind":"arxiv_version","alias_value":"1402.3849v1","created_at":"2026-05-18T02:58:47.018265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.3849","created_at":"2026-05-18T02:58:47.018265+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUPVTTU5XNRW","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUPVTTU5XNRWIU3W","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUPVTTU5","created_at":"2026-05-18T12:28:59.999130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.05226","citing_title":"Variance Matters: Improving Domain Adaptation via Stratified Sampling","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS","json":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS.json","graph_json":"https://pith.science/api/pith-number/ZUPVTTU5XNRWIU3WN553F5NYUS/graph.json","events_json":"https://pith.science/api/pith-number/ZUPVTTU5XNRWIU3WN553F5NYUS/events.json","paper":"https://pith.science/paper/ZUPVTTU5"},"agent_actions":{"view_html":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS","download_json":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS.json","view_paper":"https://pith.science/paper/ZUPVTTU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1402.3849&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUPVTTU5XNRWIU3WN553F5NYUS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUPVTTU5XNRWIU3WN553F5NYUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS/action/storage_attestation","attest_author":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS/action/author_attestation","sign_citation":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS/action/citation_signature","submit_replication":"https://pith.science/pith/ZUPVTTU5XNRWIU3WN553F5NYUS/action/replication_record"}},"created_at":"2026-05-18T02:58:47.018265+00:00","updated_at":"2026-05-18T02:58:47.018265+00:00"}