{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:4EPIOFB6QWWXXJD6QN36PECCJ2","short_pith_number":"pith:4EPIOFB6","schema_version":"1.0","canonical_sha256":"e11e87143e85ad7ba47e8377e790424eb3ca254ae26415fdcb6c6fd047f4b14b","source":{"kind":"arxiv","id":"1203.6402","version":1},"attestation_state":"computed","paper":{"title":"Scalable K-Means++","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrea Vattani, Bahman Bahmani, Benjamin Moseley, Ravi Kumar, Sergei Vassilvitskii","submitted_at":"2012-03-29T00:06:07Z","abstract_excerpt":"Over half a century old and showing no signs of aging, k-means remains one of the most popular data processing algorithms. As is well-known, a proper initialization of k-means is crucial for obtaining a good final solution. The recently proposed k-means++ initialization algorithm achieves this, obtaining an initial set of centers that is provably close to the optimum solution. A major downside of the k-means++ is its inherent sequential nature, which limits its applicability to massive data: one must make k passes over the data to find a good initial set of centers. In this work we show how to"},"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":"1203.6402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:06:07Z","cross_cats_sorted":[],"title_canon_sha256":"6a08cf86de757952ccec9892cbc2e74c0d96ffa6d2e9cc10019616581921df05","abstract_canon_sha256":"b1f1b45c4c738c7407f3f9f1af88f4c1e16e4be2bd369b97e7aa8de3496dfdbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:59:02.624858Z","signature_b64":"i34x10uoyU6LgXln0byVgeOraJuHj1j+W8S6XEhxQ9YNVDOoymAMMVWfYqR59e3V9uxR+fdW/YTN276++ursDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e11e87143e85ad7ba47e8377e790424eb3ca254ae26415fdcb6c6fd047f4b14b","last_reissued_at":"2026-05-18T03:59:02.624181Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:59:02.624181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable K-Means++","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrea Vattani, Bahman Bahmani, Benjamin Moseley, Ravi Kumar, Sergei Vassilvitskii","submitted_at":"2012-03-29T00:06:07Z","abstract_excerpt":"Over half a century old and showing no signs of aging, k-means remains one of the most popular data processing algorithms. As is well-known, a proper initialization of k-means is crucial for obtaining a good final solution. The recently proposed k-means++ initialization algorithm achieves this, obtaining an initial set of centers that is provably close to the optimum solution. A major downside of the k-means++ is its inherent sequential nature, which limits its applicability to massive data: one must make k passes over the data to find a good initial set of centers. In this work we show how to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1203.6402","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":"1203.6402","created_at":"2026-05-18T03:59:02.624278+00:00"},{"alias_kind":"arxiv_version","alias_value":"1203.6402v1","created_at":"2026-05-18T03:59:02.624278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1203.6402","created_at":"2026-05-18T03:59:02.624278+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EPIOFB6QWWX","created_at":"2026-05-18T12:26:53.410803+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EPIOFB6QWWXXJD6","created_at":"2026-05-18T12:26:53.410803+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EPIOFB6","created_at":"2026-05-18T12:26:53.410803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05857","citing_title":"Weight-Informed Self-Explaining Clustering for Mixed-Type Tabular Data","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2","json":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2.json","graph_json":"https://pith.science/api/pith-number/4EPIOFB6QWWXXJD6QN36PECCJ2/graph.json","events_json":"https://pith.science/api/pith-number/4EPIOFB6QWWXXJD6QN36PECCJ2/events.json","paper":"https://pith.science/paper/4EPIOFB6"},"agent_actions":{"view_html":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2","download_json":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2.json","view_paper":"https://pith.science/paper/4EPIOFB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1203.6402&json=true","fetch_graph":"https://pith.science/api/pith-number/4EPIOFB6QWWXXJD6QN36PECCJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/4EPIOFB6QWWXXJD6QN36PECCJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/action/storage_attestation","attest_author":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/action/author_attestation","sign_citation":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/action/citation_signature","submit_replication":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/action/replication_record"}},"created_at":"2026-05-18T03:59:02.624278+00:00","updated_at":"2026-05-18T03:59:02.624278+00:00"}