{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EHXEOSDRVXBP4K6S3B2LWBUTMD","short_pith_number":"pith:EHXEOSDR","schema_version":"1.0","canonical_sha256":"21ee474871adc2fe2bd2d874bb069360c0c80534093ff93e41a98cb6349901a2","source":{"kind":"arxiv","id":"2502.06163","version":1},"attestation_state":"computed","paper":{"title":"Scalable k-Means Clustering for Large k via Seeded Approximate Nearest-Neighbor Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG","stat.ML"],"primary_cat":"cs.LG","authors_text":"Da Wei Zheng, Eliot Wong Robson, Jack Spalding-Jamieson","submitted_at":"2025-02-10T05:22:08Z","abstract_excerpt":"For very large values of $k$, we consider methods for fast $k$-means clustering of massive datasets with $10^7\\sim10^9$ points in high-dimensions ($d\\geq100$). All current practical methods for this problem have runtimes at least $\\Omega(k^2)$. We find that initialization routines are not a bottleneck for this case. Instead, it is critical to improve the speed of Lloyd's local-search algorithm, particularly the step that reassigns points to their closest center. Attempting to improve this step naturally leads us to leverage approximate nearest-neighbor search methods, although this alone is no"},"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":"2502.06163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T05:22:08Z","cross_cats_sorted":["cs.CG","stat.ML"],"title_canon_sha256":"5894889e1e93c27258c6e6c3c797bdc51f092496348e02f8f1d4a1739dfa2639","abstract_canon_sha256":"a050c1af9659ba8bf919f4a18101c5610670934c89d360f7b0c85c5682bd28b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:48.455727Z","signature_b64":"pqDLokUjepkuIceRUnKhKeaw9vA59TO46IzZS0cGeNLWcdmnsNInjjrlePrjIXzWec3vIbghmnTSzh2NCP8aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21ee474871adc2fe2bd2d874bb069360c0c80534093ff93e41a98cb6349901a2","last_reissued_at":"2026-07-05T10:11:48.455242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:48.455242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable k-Means Clustering for Large k via Seeded Approximate Nearest-Neighbor Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG","stat.ML"],"primary_cat":"cs.LG","authors_text":"Da Wei Zheng, Eliot Wong Robson, Jack Spalding-Jamieson","submitted_at":"2025-02-10T05:22:08Z","abstract_excerpt":"For very large values of $k$, we consider methods for fast $k$-means clustering of massive datasets with $10^7\\sim10^9$ points in high-dimensions ($d\\geq100$). All current practical methods for this problem have runtimes at least $\\Omega(k^2)$. We find that initialization routines are not a bottleneck for this case. Instead, it is critical to improve the speed of Lloyd's local-search algorithm, particularly the step that reassigns points to their closest center. Attempting to improve this step naturally leads us to leverage approximate nearest-neighbor search methods, although this alone is no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06163","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/2502.06163/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":"2502.06163","created_at":"2026-07-05T10:11:48.455325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06163v1","created_at":"2026-07-05T10:11:48.455325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06163","created_at":"2026-07-05T10:11:48.455325+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHXEOSDRVXBP","created_at":"2026-07-05T10:11:48.455325+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHXEOSDRVXBP4K6S","created_at":"2026-07-05T10:11:48.455325+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHXEOSDR","created_at":"2026-07-05T10:11:48.455325+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/EHXEOSDRVXBP4K6S3B2LWBUTMD","json":"https://pith.science/pith/EHXEOSDRVXBP4K6S3B2LWBUTMD.json","graph_json":"https://pith.science/api/pith-number/EHXEOSDRVXBP4K6S3B2LWBUTMD/graph.json","events_json":"https://pith.science/api/pith-number/EHXEOSDRVXBP4K6S3B2LWBUTMD/events.json","paper":"https://pith.science/paper/EHXEOSDR"},"agent_actions":{"view_html":"https://pith.science/pith/EHXEOSDRVXBP4K6S3B2LWBUTMD","download_json":"https://pith.science/pith/EHXEOSDRVXBP4K6S3B2LWBUTMD.json","view_paper":"https://pith.science/paper/EHXEOSDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06163&json=true","fetch_graph":"https://pith.science/api/pith-number/EHXEOSDRVXBP4K6S3B2LWBUTMD/graph.json","fetch_events":"https://pith.science/api/pith-number/EHXEOSDRVXBP4K6S3B2LWBUTMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHXEOSDRVXBP4K6S3B2LWBUTMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHXEOSDRVXBP4K6S3B2LWBUTMD/action/storage_attestation","attest_author":"https://pith.science/pith/EHXEOSDRVXBP4K6S3B2LWBUTMD/action/author_attestation","sign_citation":"https://pith.science/pith/EHXEOSDRVXBP4K6S3B2LWBUTMD/action/citation_signature","submit_replication":"https://pith.science/pith/EHXEOSDRVXBP4K6S3B2LWBUTMD/action/replication_record"}},"created_at":"2026-07-05T10:11:48.455325+00:00","updated_at":"2026-07-05T10:11:48.455325+00:00"}