{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2IAMVTQ6I2JSDDFPJM25HYLT53","short_pith_number":"pith:2IAMVTQ6","schema_version":"1.0","canonical_sha256":"d200cace1e4693218caf4b35d3e173eee6a91940ebf0c81f4419864769dd7440","source":{"kind":"arxiv","id":"2504.16229","version":1},"attestation_state":"computed","paper":{"title":"Fast, Space-Optimal Streaming Algorithms for Clustering and Subspace Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"David P. Woodruff, Liudeng Wang, Samson Zhou, Vincent Cohen-Addad","submitted_at":"2025-04-22T19:49:52Z","abstract_excerpt":"We show that both clustering and subspace embeddings can be performed in the streaming model with the same asymptotic efficiency as in the central/offline setting.\n  For $(k, z)$-clustering in the streaming model, we achieve a number of words of memory which is independent of the number $n$ of input points and the aspect ratio $\\Delta$, yielding an optimal bound of $\\tilde{\\mathcal{O}}\\left(\\frac{dk}{\\min(\\varepsilon^4,\\varepsilon^{z+2})}\\right)$ words for accuracy parameter $\\varepsilon$ on $d$-dimensional points. Additionally, we obtain amortized update time of $d\\,\\log(k)\\cdot\\text{polylog}"},"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":"2504.16229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2025-04-22T19:49:52Z","cross_cats_sorted":[],"title_canon_sha256":"689b76b1631f2a721788de85eaae5a8fb3188867353496d502f10418487ea4b4","abstract_canon_sha256":"421fdd1b0181d144521215ea7fbc98838670a3ff98dc3abae2f6ba531f2b07f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:43.546255Z","signature_b64":"KG5SrXf0xMWRYVI/jGxQAi1JnRCTbQHkcM+x2rSq3khAGS47bUbcR/nXtrA7qxnYsd6zA4EjfR2iJ5386oJVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d200cace1e4693218caf4b35d3e173eee6a91940ebf0c81f4419864769dd7440","last_reissued_at":"2026-07-05T10:52:43.545821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:43.545821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast, Space-Optimal Streaming Algorithms for Clustering and Subspace Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"David P. Woodruff, Liudeng Wang, Samson Zhou, Vincent Cohen-Addad","submitted_at":"2025-04-22T19:49:52Z","abstract_excerpt":"We show that both clustering and subspace embeddings can be performed in the streaming model with the same asymptotic efficiency as in the central/offline setting.\n  For $(k, z)$-clustering in the streaming model, we achieve a number of words of memory which is independent of the number $n$ of input points and the aspect ratio $\\Delta$, yielding an optimal bound of $\\tilde{\\mathcal{O}}\\left(\\frac{dk}{\\min(\\varepsilon^4,\\varepsilon^{z+2})}\\right)$ words for accuracy parameter $\\varepsilon$ on $d$-dimensional points. Additionally, we obtain amortized update time of $d\\,\\log(k)\\cdot\\text{polylog}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16229","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/2504.16229/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":"2504.16229","created_at":"2026-07-05T10:52:43.545876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16229v1","created_at":"2026-07-05T10:52:43.545876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16229","created_at":"2026-07-05T10:52:43.545876+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IAMVTQ6I2JS","created_at":"2026-07-05T10:52:43.545876+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IAMVTQ6I2JSDDFP","created_at":"2026-07-05T10:52:43.545876+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IAMVTQ6","created_at":"2026-07-05T10:52:43.545876+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/2IAMVTQ6I2JSDDFPJM25HYLT53","json":"https://pith.science/pith/2IAMVTQ6I2JSDDFPJM25HYLT53.json","graph_json":"https://pith.science/api/pith-number/2IAMVTQ6I2JSDDFPJM25HYLT53/graph.json","events_json":"https://pith.science/api/pith-number/2IAMVTQ6I2JSDDFPJM25HYLT53/events.json","paper":"https://pith.science/paper/2IAMVTQ6"},"agent_actions":{"view_html":"https://pith.science/pith/2IAMVTQ6I2JSDDFPJM25HYLT53","download_json":"https://pith.science/pith/2IAMVTQ6I2JSDDFPJM25HYLT53.json","view_paper":"https://pith.science/paper/2IAMVTQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16229&json=true","fetch_graph":"https://pith.science/api/pith-number/2IAMVTQ6I2JSDDFPJM25HYLT53/graph.json","fetch_events":"https://pith.science/api/pith-number/2IAMVTQ6I2JSDDFPJM25HYLT53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IAMVTQ6I2JSDDFPJM25HYLT53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IAMVTQ6I2JSDDFPJM25HYLT53/action/storage_attestation","attest_author":"https://pith.science/pith/2IAMVTQ6I2JSDDFPJM25HYLT53/action/author_attestation","sign_citation":"https://pith.science/pith/2IAMVTQ6I2JSDDFPJM25HYLT53/action/citation_signature","submit_replication":"https://pith.science/pith/2IAMVTQ6I2JSDDFPJM25HYLT53/action/replication_record"}},"created_at":"2026-07-05T10:52:43.545876+00:00","updated_at":"2026-07-05T10:52:43.545876+00:00"}