{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2IPJIRO2NI4ENC4UMERAZ2UUP3","short_pith_number":"pith:2IPJIRO2","schema_version":"1.0","canonical_sha256":"d21e9445da6a38468b9461220cea947eef494806dfb415b2e552a338c9ab2a89","source":{"kind":"arxiv","id":"2401.05574","version":3},"attestation_state":"computed","paper":{"title":"A provable initialization and robust clustering method for general mixture models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jianqing Fan, Sanjeev Kulkarni, Soham Jana","submitted_at":"2024-01-10T22:56:44Z","abstract_excerpt":"Clustering is a fundamental tool in statistical machine learning in the presence of heterogeneous data. Most recent results focus primarily on optimal mislabeling guarantees when data are distributed around centroids with sub-Gaussian errors. Yet, the restrictive sub-Gaussian model is often invalid in practice since various real-world applications exhibit heavy tail distributions around the centroids or suffer from possible adversarial attacks that call for robust clustering with a robust data-driven initialization. In this paper, we present initialization and subsequent clustering methods tha"},"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":"2401.05574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2024-01-10T22:56:44Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"f4861551f1d19741d04810b27e6a53672eb7a5ad68bcf2f74c70645431fd0f79","abstract_canon_sha256":"54be21da0fead57bc79cd5d98bbe6ce4e042f8faff56e7947ac6e79c80579334"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:15.775119Z","signature_b64":"L2YGHhFbsM8c+KqwIBVS87Qo5qN6kaYIhcU796z+8KLjb066x6OMXkvn5yji8dHm2yc9xXSv1i4VmVqQSLinCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d21e9445da6a38468b9461220cea947eef494806dfb415b2e552a338c9ab2a89","last_reissued_at":"2026-07-05T09:24:15.774670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:15.774670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A provable initialization and robust clustering method for general mixture models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jianqing Fan, Sanjeev Kulkarni, Soham Jana","submitted_at":"2024-01-10T22:56:44Z","abstract_excerpt":"Clustering is a fundamental tool in statistical machine learning in the presence of heterogeneous data. Most recent results focus primarily on optimal mislabeling guarantees when data are distributed around centroids with sub-Gaussian errors. Yet, the restrictive sub-Gaussian model is often invalid in practice since various real-world applications exhibit heavy tail distributions around the centroids or suffer from possible adversarial attacks that call for robust clustering with a robust data-driven initialization. In this paper, we present initialization and subsequent clustering methods tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05574","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/2401.05574/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":"2401.05574","created_at":"2026-07-05T09:24:15.774725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05574v3","created_at":"2026-07-05T09:24:15.774725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05574","created_at":"2026-07-05T09:24:15.774725+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IPJIRO2NI4E","created_at":"2026-07-05T09:24:15.774725+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IPJIRO2NI4ENC4U","created_at":"2026-07-05T09:24:15.774725+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IPJIRO2","created_at":"2026-07-05T09:24:15.774725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.10704","citing_title":"Estimation beyond Missing (Completely) at Random","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3","json":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3.json","graph_json":"https://pith.science/api/pith-number/2IPJIRO2NI4ENC4UMERAZ2UUP3/graph.json","events_json":"https://pith.science/api/pith-number/2IPJIRO2NI4ENC4UMERAZ2UUP3/events.json","paper":"https://pith.science/paper/2IPJIRO2"},"agent_actions":{"view_html":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3","download_json":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3.json","view_paper":"https://pith.science/paper/2IPJIRO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05574&json=true","fetch_graph":"https://pith.science/api/pith-number/2IPJIRO2NI4ENC4UMERAZ2UUP3/graph.json","fetch_events":"https://pith.science/api/pith-number/2IPJIRO2NI4ENC4UMERAZ2UUP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3/action/storage_attestation","attest_author":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3/action/author_attestation","sign_citation":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3/action/citation_signature","submit_replication":"https://pith.science/pith/2IPJIRO2NI4ENC4UMERAZ2UUP3/action/replication_record"}},"created_at":"2026-07-05T09:24:15.774725+00:00","updated_at":"2026-07-05T09:24:15.774725+00:00"}