{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:4AUFBBKBLFKC7S4KNVYCWXVPEC","short_pith_number":"pith:4AUFBBKB","schema_version":"1.0","canonical_sha256":"e02850854159542fcb8a6d702b5eaf20850306314c2ca1eb70ae85667a9560e7","source":{"kind":"arxiv","id":"1410.6801","version":3},"attestation_state":"computed","paper":{"title":"Dimensionality Reduction for k-Means Clustering and Low Rank Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Cameron Musco, Christopher Musco, Madalina Persu, Michael B. Cohen, Sam Elder","submitted_at":"2014-10-24T19:43:16Z","abstract_excerpt":"We show how to approximate a data matrix $\\mathbf{A}$ with a much smaller sketch $\\mathbf{\\tilde A}$ that can be used to solve a general class of constrained k-rank approximation problems to within $(1+\\epsilon)$ error. Importantly, this class of problems includes $k$-means clustering and unconstrained low rank approximation (i.e. principal component analysis). By reducing data points to just $O(k)$ dimensions, our methods generically accelerate any exact, approximate, or heuristic algorithm for these ubiquitous problems.\n  For $k$-means dimensionality reduction, we provide $(1+\\epsilon)$ rela"},"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":"1410.6801","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-10-24T19:43:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a13a656831f3a979ed248d4928591ebc5bcbc5302c7d1c6a3e08d01784db1425","abstract_canon_sha256":"6a9a229df9418caba74057c14a73add7c55759a0a3fa578aa5ff978e8b4e02fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:42.502734Z","signature_b64":"kAUNdEmpl+PmkQnWovgBAM9XhIc/LxDHdymsJ92Bs188wAknbcG00Bx0LNjpGKK4hE5us1xDqVkP8+l7f+wQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e02850854159542fcb8a6d702b5eaf20850306314c2ca1eb70ae85667a9560e7","last_reissued_at":"2026-05-18T02:19:42.502263Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:42.502263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimensionality Reduction for k-Means Clustering and Low Rank Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Cameron Musco, Christopher Musco, Madalina Persu, Michael B. Cohen, Sam Elder","submitted_at":"2014-10-24T19:43:16Z","abstract_excerpt":"We show how to approximate a data matrix $\\mathbf{A}$ with a much smaller sketch $\\mathbf{\\tilde A}$ that can be used to solve a general class of constrained k-rank approximation problems to within $(1+\\epsilon)$ error. Importantly, this class of problems includes $k$-means clustering and unconstrained low rank approximation (i.e. principal component analysis). By reducing data points to just $O(k)$ dimensions, our methods generically accelerate any exact, approximate, or heuristic algorithm for these ubiquitous problems.\n  For $k$-means dimensionality reduction, we provide $(1+\\epsilon)$ rela"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.6801","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":"1410.6801","created_at":"2026-05-18T02:19:42.502345+00:00"},{"alias_kind":"arxiv_version","alias_value":"1410.6801v3","created_at":"2026-05-18T02:19:42.502345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.6801","created_at":"2026-05-18T02:19:42.502345+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AUFBBKBLFKC","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AUFBBKBLFKC7S4K","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AUFBBKB","created_at":"2026-05-18T12:28:14.216126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01433","citing_title":"Tight Sensitivity Bounds For Smaller Coresets","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC","json":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC.json","graph_json":"https://pith.science/api/pith-number/4AUFBBKBLFKC7S4KNVYCWXVPEC/graph.json","events_json":"https://pith.science/api/pith-number/4AUFBBKBLFKC7S4KNVYCWXVPEC/events.json","paper":"https://pith.science/paper/4AUFBBKB"},"agent_actions":{"view_html":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC","download_json":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC.json","view_paper":"https://pith.science/paper/4AUFBBKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1410.6801&json=true","fetch_graph":"https://pith.science/api/pith-number/4AUFBBKBLFKC7S4KNVYCWXVPEC/graph.json","fetch_events":"https://pith.science/api/pith-number/4AUFBBKBLFKC7S4KNVYCWXVPEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC/action/storage_attestation","attest_author":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC/action/author_attestation","sign_citation":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC/action/citation_signature","submit_replication":"https://pith.science/pith/4AUFBBKBLFKC7S4KNVYCWXVPEC/action/replication_record"}},"created_at":"2026-05-18T02:19:42.502345+00:00","updated_at":"2026-05-18T02:19:42.502345+00:00"}