{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H3SHDKWN7HO4XYYY66ZOUVHFHN","short_pith_number":"pith:H3SHDKWN","schema_version":"1.0","canonical_sha256":"3ee471aacdf9ddcbe318f7b2ea54e53b7c60937e79a36f3c390eac9f70cfe10c","source":{"kind":"arxiv","id":"2502.02085","version":1},"attestation_state":"computed","paper":{"title":"A New Rejection Sampling Approach to $k$-$\\mathtt{means}$++ With Improved Trade-Offs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Poojan Shah, Ragesh Jaiswal, Shashwat Agrawal","submitted_at":"2025-02-04T08:05:34Z","abstract_excerpt":"The $k$-$\\mathtt{means}$++ seeding algorithm (Arthur & Vassilvitskii, 2007) is widely used in practice for the $k$-means clustering problem where the goal is to cluster a dataset $\\mathcal{X} \\subset \\mathbb{R} ^d$ into $k$ clusters.\n  The popularity of this algorithm is due to its simplicity and provable guarantee of being $O(\\log k)$ competitive with the optimal solution in expectation. However, its running time is $O(|\\mathcal{X}|kd)$, making it expensive for large datasets.\n  In this work, we present a simple and effective rejection sampling based approach for speeding up $k$-$\\mathtt{mean"},"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":"2502.02085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2025-02-04T08:05:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"58a5c5f572aa74a151b1e8f33d22cd35c2fc472efffabd8b7d2d7a18f64ca63c","abstract_canon_sha256":"394454f5e4835c6a7a1d62113bd33b1c6e89173462a5ae0b7d335d2b3fac8afd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:23.559390Z","signature_b64":"9LCbViVumU3zLGaSk5hRs3s7yCYCgd2m/VyO1Fc0z1uxqbL+Cl+ZdYtSQ4O7iYXCWi/qLFm9D/r5Q+TVmp1PCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee471aacdf9ddcbe318f7b2ea54e53b7c60937e79a36f3c390eac9f70cfe10c","last_reissued_at":"2026-07-05T10:09:23.558964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:23.558964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New Rejection Sampling Approach to $k$-$\\mathtt{means}$++ With Improved Trade-Offs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Poojan Shah, Ragesh Jaiswal, Shashwat Agrawal","submitted_at":"2025-02-04T08:05:34Z","abstract_excerpt":"The $k$-$\\mathtt{means}$++ seeding algorithm (Arthur & Vassilvitskii, 2007) is widely used in practice for the $k$-means clustering problem where the goal is to cluster a dataset $\\mathcal{X} \\subset \\mathbb{R} ^d$ into $k$ clusters.\n  The popularity of this algorithm is due to its simplicity and provable guarantee of being $O(\\log k)$ competitive with the optimal solution in expectation. However, its running time is $O(|\\mathcal{X}|kd)$, making it expensive for large datasets.\n  In this work, we present a simple and effective rejection sampling based approach for speeding up $k$-$\\mathtt{mean"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02085","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/2502.02085/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":"2502.02085","created_at":"2026-07-05T10:09:23.559020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02085v1","created_at":"2026-07-05T10:09:23.559020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02085","created_at":"2026-07-05T10:09:23.559020+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3SHDKWN7HO4","created_at":"2026-07-05T10:09:23.559020+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3SHDKWN7HO4XYYY","created_at":"2026-07-05T10:09:23.559020+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3SHDKWN","created_at":"2026-07-05T10:09:23.559020+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/H3SHDKWN7HO4XYYY66ZOUVHFHN","json":"https://pith.science/pith/H3SHDKWN7HO4XYYY66ZOUVHFHN.json","graph_json":"https://pith.science/api/pith-number/H3SHDKWN7HO4XYYY66ZOUVHFHN/graph.json","events_json":"https://pith.science/api/pith-number/H3SHDKWN7HO4XYYY66ZOUVHFHN/events.json","paper":"https://pith.science/paper/H3SHDKWN"},"agent_actions":{"view_html":"https://pith.science/pith/H3SHDKWN7HO4XYYY66ZOUVHFHN","download_json":"https://pith.science/pith/H3SHDKWN7HO4XYYY66ZOUVHFHN.json","view_paper":"https://pith.science/paper/H3SHDKWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02085&json=true","fetch_graph":"https://pith.science/api/pith-number/H3SHDKWN7HO4XYYY66ZOUVHFHN/graph.json","fetch_events":"https://pith.science/api/pith-number/H3SHDKWN7HO4XYYY66ZOUVHFHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3SHDKWN7HO4XYYY66ZOUVHFHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3SHDKWN7HO4XYYY66ZOUVHFHN/action/storage_attestation","attest_author":"https://pith.science/pith/H3SHDKWN7HO4XYYY66ZOUVHFHN/action/author_attestation","sign_citation":"https://pith.science/pith/H3SHDKWN7HO4XYYY66ZOUVHFHN/action/citation_signature","submit_replication":"https://pith.science/pith/H3SHDKWN7HO4XYYY66ZOUVHFHN/action/replication_record"}},"created_at":"2026-07-05T10:09:23.559020+00:00","updated_at":"2026-07-05T10:09:23.559020+00:00"}