{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TJ45PS24S3N5B3FZAXRYX2TXKD","short_pith_number":"pith:TJ45PS24","schema_version":"1.0","canonical_sha256":"9a79d7cb5c96dbd0ecb905e38bea7750d313b51a96db736da3f6241289648a88","source":{"kind":"arxiv","id":"2005.02970","version":3},"attestation_state":"computed","paper":{"title":"Outlier-Robust Clustering of Non-Spherical Mixtures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.DS","authors_text":"Ainesh Bakshi, Pravesh Kothari","submitted_at":"2020-05-06T17:24:27Z","abstract_excerpt":"We give the first outlier-robust efficient algorithm for clustering a mixture of $k$ statistically separated d-dimensional Gaussians (k-GMMs). Concretely, our algorithm takes input an $\\epsilon$-corrupted sample from a $k$-GMM and whp in $d^{\\text{poly}(k/\\eta)}$ time, outputs an approximate clustering that misclassifies at most $k^{O(k)}(\\epsilon+\\eta)$ fraction of the points whenever every pair of mixture components are separated by $1-\\exp(-\\text{poly}(k/\\eta)^k)$ in total variation (TV) distance. Such a result was not previously known even for $k=2$. TV separation is the statistically weak"},"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":"2005.02970","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-05-06T17:24:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ed3e4153f12c8e3ae755fc0565727fc838aaff1752533e399b301b778629ed48","abstract_canon_sha256":"ee2c30d1288f10b9711c348eb68566b2d89111290aa8c5c269b8d4594c79d0f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:11.615418Z","signature_b64":"PLI514l0l3gmPVgjC3RWM4aoEVx1gO/owKx/6NdzHQ9KmUGQn9XTGKPzYm/xRFIUNdVoq8dhhDUUBq8rNVvKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a79d7cb5c96dbd0ecb905e38bea7750d313b51a96db736da3f6241289648a88","last_reissued_at":"2026-07-05T01:59:11.615059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:11.615059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Outlier-Robust Clustering of Non-Spherical Mixtures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.DS","authors_text":"Ainesh Bakshi, Pravesh Kothari","submitted_at":"2020-05-06T17:24:27Z","abstract_excerpt":"We give the first outlier-robust efficient algorithm for clustering a mixture of $k$ statistically separated d-dimensional Gaussians (k-GMMs). Concretely, our algorithm takes input an $\\epsilon$-corrupted sample from a $k$-GMM and whp in $d^{\\text{poly}(k/\\eta)}$ time, outputs an approximate clustering that misclassifies at most $k^{O(k)}(\\epsilon+\\eta)$ fraction of the points whenever every pair of mixture components are separated by $1-\\exp(-\\text{poly}(k/\\eta)^k)$ in total variation (TV) distance. Such a result was not previously known even for $k=2$. TV separation is the statistically weak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02970","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.02970/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":"2005.02970","created_at":"2026-07-05T01:59:11.615113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.02970v3","created_at":"2026-07-05T01:59:11.615113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02970","created_at":"2026-07-05T01:59:11.615113+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJ45PS24S3N5","created_at":"2026-07-05T01:59:11.615113+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJ45PS24S3N5B3FZ","created_at":"2026-07-05T01:59:11.615113+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJ45PS24","created_at":"2026-07-05T01:59:11.615113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12438","citing_title":"Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD","json":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD.json","graph_json":"https://pith.science/api/pith-number/TJ45PS24S3N5B3FZAXRYX2TXKD/graph.json","events_json":"https://pith.science/api/pith-number/TJ45PS24S3N5B3FZAXRYX2TXKD/events.json","paper":"https://pith.science/paper/TJ45PS24"},"agent_actions":{"view_html":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD","download_json":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD.json","view_paper":"https://pith.science/paper/TJ45PS24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.02970&json=true","fetch_graph":"https://pith.science/api/pith-number/TJ45PS24S3N5B3FZAXRYX2TXKD/graph.json","fetch_events":"https://pith.science/api/pith-number/TJ45PS24S3N5B3FZAXRYX2TXKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD/action/storage_attestation","attest_author":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD/action/author_attestation","sign_citation":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD/action/citation_signature","submit_replication":"https://pith.science/pith/TJ45PS24S3N5B3FZAXRYX2TXKD/action/replication_record"}},"created_at":"2026-07-05T01:59:11.615113+00:00","updated_at":"2026-07-05T01:59:11.615113+00:00"}