{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:S5J7HYSRWNRJVTTOIUVRQTXG74","short_pith_number":"pith:S5J7HYSR","schema_version":"1.0","canonical_sha256":"9753f3e251b3629ace6e452b184ee6ff31635583dffde8c11b8f38494472b970","source":{"kind":"arxiv","id":"1502.04265","version":3},"attestation_state":"computed","paper":{"title":"Solving $k$-means on High-dimensional Big Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Daniel R. Schmidt, Jan-Philipp W. Kappmeier, Melanie Schmidt","submitted_at":"2015-02-15T01:03:47Z","abstract_excerpt":"In recent years, there have been major efforts to develop data stream algorithms that process inputs in one pass over the data with little memory requirement. For the $k$-means problem, this has led to the development of several $(1+\\varepsilon)$-approximations (under the assumption that $k$ is a constant), but also to the design of algorithms that are extremely fast in practice and compute solutions of high accuracy. However, when not only the length of the stream is high but also the dimensionality of the input points, then current methods reach their limits.\n  We propose two algorithms, pie"},"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":"1502.04265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-02-15T01:03:47Z","cross_cats_sorted":[],"title_canon_sha256":"253728244a0b6daa70fae1e50ecb5a541aa86edbc9e617b0a8b1f2ff5ead6490","abstract_canon_sha256":"f724fa29b112c396e0d130b5786eb73f2e0c32ef6bc879126e886228e0c99a42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:00:02.244377Z","signature_b64":"WEI5y6BaO/23l6ns4drzTH7Pc1ONzrDdnIUWMYntVw6JdZ66DI6wfH3s12LmOeiJzEcu2ZNG0Ook4crX2WNrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9753f3e251b3629ace6e452b184ee6ff31635583dffde8c11b8f38494472b970","last_reissued_at":"2026-05-18T02:00:02.243883Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:00:02.243883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving $k$-means on High-dimensional Big Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Daniel R. Schmidt, Jan-Philipp W. Kappmeier, Melanie Schmidt","submitted_at":"2015-02-15T01:03:47Z","abstract_excerpt":"In recent years, there have been major efforts to develop data stream algorithms that process inputs in one pass over the data with little memory requirement. For the $k$-means problem, this has led to the development of several $(1+\\varepsilon)$-approximations (under the assumption that $k$ is a constant), but also to the design of algorithms that are extremely fast in practice and compute solutions of high accuracy. However, when not only the length of the stream is high but also the dimensionality of the input points, then current methods reach their limits.\n  We propose two algorithms, pie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.04265","kind":"arxiv","version":3},"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":"1502.04265","created_at":"2026-05-18T02:00:02.243952+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.04265v3","created_at":"2026-05-18T02:00:02.243952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.04265","created_at":"2026-05-18T02:00:02.243952+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5J7HYSRWNRJ","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5J7HYSRWNRJVTTO","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5J7HYSR","created_at":"2026-05-18T12:29:39.896362+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/S5J7HYSRWNRJVTTOIUVRQTXG74","json":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74.json","graph_json":"https://pith.science/api/pith-number/S5J7HYSRWNRJVTTOIUVRQTXG74/graph.json","events_json":"https://pith.science/api/pith-number/S5J7HYSRWNRJVTTOIUVRQTXG74/events.json","paper":"https://pith.science/paper/S5J7HYSR"},"agent_actions":{"view_html":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74","download_json":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74.json","view_paper":"https://pith.science/paper/S5J7HYSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.04265&json=true","fetch_graph":"https://pith.science/api/pith-number/S5J7HYSRWNRJVTTOIUVRQTXG74/graph.json","fetch_events":"https://pith.science/api/pith-number/S5J7HYSRWNRJVTTOIUVRQTXG74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/action/storage_attestation","attest_author":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/action/author_attestation","sign_citation":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/action/citation_signature","submit_replication":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/action/replication_record"}},"created_at":"2026-05-18T02:00:02.243952+00:00","updated_at":"2026-05-18T02:00:02.243952+00:00"}