{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LJCGXXBQKPPIX5MUJKGD6D3D4U","short_pith_number":"pith:LJCGXXBQ","schema_version":"1.0","canonical_sha256":"5a446bdc3053de8bf5944a8c3f0f63e520fa28e201ce03153992a0e301b8f558","source":{"kind":"arxiv","id":"2411.12438","version":2},"attestation_state":"computed","paper":{"title":"Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"David Steurer, Mitali Bafna, Prashanti Anderson, Pravesh K. Kothari, Rares-Darius Buhai","submitted_at":"2024-11-19T11:58:51Z","abstract_excerpt":"We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that finds a low-dimensional separation-preserving projection of the input data. Our method gives a non-spherical analog of the classical dimension reduction, based on singular value decomposition, that, among several other applications, forms a key component of the celebrated spherical clustering algorithm of Vempala and Wang [VW04].\n  As applications, we obtain an algorithm to (1) cluster an arbitrary total-variation sepa"},"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":"2411.12438","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2024-11-19T11:58:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"125665ae6221985cb3e8274c4aefa78e236080d6e818bb715242bfb19f5d2391","abstract_canon_sha256":"708879892ecdb31506b6d8bf78a297df2d3179b5c8e6163d91d5c27ae0f83210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:45.379603Z","signature_b64":"N7KKPdQcyE6NnzZ8NJ3X/R48/QQTqNcfU6uLj3qI+CqAmouHH6gnqXg76p6x01kztXsXVH2fajU2Lf+pN91yBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a446bdc3053de8bf5944a8c3f0f63e520fa28e201ce03153992a0e301b8f558","last_reissued_at":"2026-06-02T02:04:45.379074Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:45.379074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"David Steurer, Mitali Bafna, Prashanti Anderson, Pravesh K. Kothari, Rares-Darius Buhai","submitted_at":"2024-11-19T11:58:51Z","abstract_excerpt":"We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that finds a low-dimensional separation-preserving projection of the input data. Our method gives a non-spherical analog of the classical dimension reduction, based on singular value decomposition, that, among several other applications, forms a key component of the celebrated spherical clustering algorithm of Vempala and Wang [VW04].\n  As applications, we obtain an algorithm to (1) cluster an arbitrary total-variation sepa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12438","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.12438/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":"2411.12438","created_at":"2026-06-02T02:04:45.379134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12438v2","created_at":"2026-06-02T02:04:45.379134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12438","created_at":"2026-06-02T02:04:45.379134+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJCGXXBQKPPI","created_at":"2026-06-02T02:04:45.379134+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJCGXXBQKPPIX5MU","created_at":"2026-06-02T02:04:45.379134+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJCGXXBQ","created_at":"2026-06-02T02:04:45.379134+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/LJCGXXBQKPPIX5MUJKGD6D3D4U","json":"https://pith.science/pith/LJCGXXBQKPPIX5MUJKGD6D3D4U.json","graph_json":"https://pith.science/api/pith-number/LJCGXXBQKPPIX5MUJKGD6D3D4U/graph.json","events_json":"https://pith.science/api/pith-number/LJCGXXBQKPPIX5MUJKGD6D3D4U/events.json","paper":"https://pith.science/paper/LJCGXXBQ"},"agent_actions":{"view_html":"https://pith.science/pith/LJCGXXBQKPPIX5MUJKGD6D3D4U","download_json":"https://pith.science/pith/LJCGXXBQKPPIX5MUJKGD6D3D4U.json","view_paper":"https://pith.science/paper/LJCGXXBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12438&json=true","fetch_graph":"https://pith.science/api/pith-number/LJCGXXBQKPPIX5MUJKGD6D3D4U/graph.json","fetch_events":"https://pith.science/api/pith-number/LJCGXXBQKPPIX5MUJKGD6D3D4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJCGXXBQKPPIX5MUJKGD6D3D4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJCGXXBQKPPIX5MUJKGD6D3D4U/action/storage_attestation","attest_author":"https://pith.science/pith/LJCGXXBQKPPIX5MUJKGD6D3D4U/action/author_attestation","sign_citation":"https://pith.science/pith/LJCGXXBQKPPIX5MUJKGD6D3D4U/action/citation_signature","submit_replication":"https://pith.science/pith/LJCGXXBQKPPIX5MUJKGD6D3D4U/action/replication_record"}},"created_at":"2026-06-02T02:04:45.379134+00:00","updated_at":"2026-06-02T02:04:45.379134+00:00"}