{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:4SMBDPOJ7J6MVYQJPGKIBIEAW3","short_pith_number":"pith:4SMBDPOJ","schema_version":"1.0","canonical_sha256":"e49811bdc9fa7ccae209799480a080b6c94f7613dfb0a575fa5b75ab28e4e8dc","source":{"kind":"arxiv","id":"1501.05590","version":1},"attestation_state":"computed","paper":{"title":"Sketch and Validate for Big Data Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Georgios B. Giannakis, Konstantinos Slavakis, Panagiotis A. Traganitis","submitted_at":"2015-01-22T18:16:30Z","abstract_excerpt":"In response to the need for learning tools tuned to big data analytics, the present paper introduces a framework for efficient clustering of huge sets of (possibly high-dimensional) data. Building on random sampling and consensus (RANSAC) ideas pursued earlier in a different (computer vision) context for robust regression, a suite of novel dimensionality and set-reduction algorithms is developed. The advocated sketch-and-validate (SkeVa) family includes two algorithms that rely on K-means clustering per iteration on reduced number of dimensions and/or feature vectors: The first operates in a b"},"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":"1501.05590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-22T18:16:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f8242846fbe8b571fb03215ca111cc6e88a0132ca44c86afd28f0d0bafb55ccd","abstract_canon_sha256":"8378d3555b293e3b4ce89ed548a95f72e4041ef5e6e237ee9e5ccc4b249bee29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:36.266721Z","signature_b64":"YWz6Dp5tkIb5O8UubS+SUAUyczin5kxQM0EttCPdWQjYJdldWoBffebpIvVVz5j+O30RrY7yWSDhBwC7aWTDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e49811bdc9fa7ccae209799480a080b6c94f7613dfb0a575fa5b75ab28e4e8dc","last_reissued_at":"2026-05-18T00:58:36.266026Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:36.266026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sketch and Validate for Big Data Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Georgios B. Giannakis, Konstantinos Slavakis, Panagiotis A. Traganitis","submitted_at":"2015-01-22T18:16:30Z","abstract_excerpt":"In response to the need for learning tools tuned to big data analytics, the present paper introduces a framework for efficient clustering of huge sets of (possibly high-dimensional) data. Building on random sampling and consensus (RANSAC) ideas pursued earlier in a different (computer vision) context for robust regression, a suite of novel dimensionality and set-reduction algorithms is developed. The advocated sketch-and-validate (SkeVa) family includes two algorithms that rely on K-means clustering per iteration on reduced number of dimensions and/or feature vectors: The first operates in a b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.05590","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":"1501.05590","created_at":"2026-05-18T00:58:36.266135+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.05590v1","created_at":"2026-05-18T00:58:36.266135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.05590","created_at":"2026-05-18T00:58:36.266135+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SMBDPOJ7J6M","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SMBDPOJ7J6MVYQJ","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SMBDPOJ","created_at":"2026-05-18T12:29:05.191682+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/4SMBDPOJ7J6MVYQJPGKIBIEAW3","json":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3.json","graph_json":"https://pith.science/api/pith-number/4SMBDPOJ7J6MVYQJPGKIBIEAW3/graph.json","events_json":"https://pith.science/api/pith-number/4SMBDPOJ7J6MVYQJPGKIBIEAW3/events.json","paper":"https://pith.science/paper/4SMBDPOJ"},"agent_actions":{"view_html":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3","download_json":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3.json","view_paper":"https://pith.science/paper/4SMBDPOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.05590&json=true","fetch_graph":"https://pith.science/api/pith-number/4SMBDPOJ7J6MVYQJPGKIBIEAW3/graph.json","fetch_events":"https://pith.science/api/pith-number/4SMBDPOJ7J6MVYQJPGKIBIEAW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/action/storage_attestation","attest_author":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/action/author_attestation","sign_citation":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/action/citation_signature","submit_replication":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/action/replication_record"}},"created_at":"2026-05-18T00:58:36.266135+00:00","updated_at":"2026-05-18T00:58:36.266135+00:00"}