{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EUH5A3O2EVYSZ3M265HSAZU2QU","short_pith_number":"pith:EUH5A3O2","schema_version":"1.0","canonical_sha256":"250fd06dda25712ced9af74f20669a851cfeda33ddd6b4320cce47aab24520e6","source":{"kind":"arxiv","id":"1802.00459","version":2},"attestation_state":"computed","paper":{"title":"Nearly Optimal Dynamic $k$-Means Clustering for High-Dimensional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Lin F. Yang, Peilin Zhong, Wei Hu, Zhao Song","submitted_at":"2018-02-01T19:07:51Z","abstract_excerpt":"We consider the $k$-means clustering problem in the dynamic streaming setting, where points from a discrete Euclidean space $\\{1, 2, \\ldots, \\Delta\\}^d$ can be dynamically inserted to or deleted from the dataset. For this problem, we provide a one-pass coreset construction algorithm using space $\\tilde{O}(k\\cdot \\mathrm{poly}(d, \\log\\Delta))$, where $k$ is the target number of centers. To our knowledge, this is the first dynamic geometric data stream algorithm for $k$-means using space polynomial in dimension and nearly optimal (linear) in $k$."},"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":"1802.00459","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2018-02-01T19:07:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bfb09cc9ae993811474157f2a9731488d11fdd28b38da1362ccac76e69abef98","abstract_canon_sha256":"1aec197f9f006d6bfd90a74c999c013aa5181716d77d74733e9880098d1a40af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:34.611544Z","signature_b64":"0Mm8FdWiUXiCDmWc3lXPUIhZpXPMxAUwYxhAgG9udtB+EYsCXO/oaBlDtNiSR/61fwXXymXrMBY0TU5dceYnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"250fd06dda25712ced9af74f20669a851cfeda33ddd6b4320cce47aab24520e6","last_reissued_at":"2026-05-17T23:54:34.611116Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:34.611116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nearly Optimal Dynamic $k$-Means Clustering for High-Dimensional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Lin F. Yang, Peilin Zhong, Wei Hu, Zhao Song","submitted_at":"2018-02-01T19:07:51Z","abstract_excerpt":"We consider the $k$-means clustering problem in the dynamic streaming setting, where points from a discrete Euclidean space $\\{1, 2, \\ldots, \\Delta\\}^d$ can be dynamically inserted to or deleted from the dataset. For this problem, we provide a one-pass coreset construction algorithm using space $\\tilde{O}(k\\cdot \\mathrm{poly}(d, \\log\\Delta))$, where $k$ is the target number of centers. To our knowledge, this is the first dynamic geometric data stream algorithm for $k$-means using space polynomial in dimension and nearly optimal (linear) in $k$."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00459","kind":"arxiv","version":2},"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":"1802.00459","created_at":"2026-05-17T23:54:34.611172+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.00459v2","created_at":"2026-05-17T23:54:34.611172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00459","created_at":"2026-05-17T23:54:34.611172+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUH5A3O2EVYS","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUH5A3O2EVYSZ3M2","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUH5A3O2","created_at":"2026-05-18T12:32:22.470017+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/EUH5A3O2EVYSZ3M265HSAZU2QU","json":"https://pith.science/pith/EUH5A3O2EVYSZ3M265HSAZU2QU.json","graph_json":"https://pith.science/api/pith-number/EUH5A3O2EVYSZ3M265HSAZU2QU/graph.json","events_json":"https://pith.science/api/pith-number/EUH5A3O2EVYSZ3M265HSAZU2QU/events.json","paper":"https://pith.science/paper/EUH5A3O2"},"agent_actions":{"view_html":"https://pith.science/pith/EUH5A3O2EVYSZ3M265HSAZU2QU","download_json":"https://pith.science/pith/EUH5A3O2EVYSZ3M265HSAZU2QU.json","view_paper":"https://pith.science/paper/EUH5A3O2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.00459&json=true","fetch_graph":"https://pith.science/api/pith-number/EUH5A3O2EVYSZ3M265HSAZU2QU/graph.json","fetch_events":"https://pith.science/api/pith-number/EUH5A3O2EVYSZ3M265HSAZU2QU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUH5A3O2EVYSZ3M265HSAZU2QU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUH5A3O2EVYSZ3M265HSAZU2QU/action/storage_attestation","attest_author":"https://pith.science/pith/EUH5A3O2EVYSZ3M265HSAZU2QU/action/author_attestation","sign_citation":"https://pith.science/pith/EUH5A3O2EVYSZ3M265HSAZU2QU/action/citation_signature","submit_replication":"https://pith.science/pith/EUH5A3O2EVYSZ3M265HSAZU2QU/action/replication_record"}},"created_at":"2026-05-17T23:54:34.611172+00:00","updated_at":"2026-05-17T23:54:34.611172+00:00"}