{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UBL2LPB4UVAPYZ6RQJ3MG2H2R2","short_pith_number":"pith:UBL2LPB4","schema_version":"1.0","canonical_sha256":"a057a5bc3ca540fc67d18276c368fa8ea659808dffc3c50e16d63b2db1ec1098","source":{"kind":"arxiv","id":"2601.05157","version":2},"attestation_state":"computed","paper":{"title":"Learning Mixture Models via Efficient High-dimensional Sparse Fourier Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Alkis Kalavasis, Manolis Zampetakis, Pravesh K. Kothari, Shuchen Li","submitted_at":"2026-01-08T17:47:58Z","abstract_excerpt":"In this work, we give a ${\\rm poly}(d,k)$ time and sample algorithm for efficiently learning the parameters of a mixture of $k$ spherical distributions in $d$ dimensions. Unlike all previous methods, our techniques apply to heavy-tailed distributions and include examples that do not even have finite covariances. Our method succeeds whenever the cluster distributions have a characteristic function with sufficiently heavy tails. Such distributions include the Laplace distribution but crucially exclude Gaussians.\n  All previous methods for learning mixture models relied implicitly or explicitly o"},"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":"2601.05157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2026-01-08T17:47:58Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"50a06ea108f32e7c21ea9d8c66c87e574672c68fc5cc3a3a56aa973009a3e545","abstract_canon_sha256":"34151525789c44ed8041bb900ee89b361a64aa4cdd37cce9c52c8837a28cf766"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:53.718767Z","signature_b64":"HeTlVXeWTXvJtUW9ggoxfxD1aC1DrE1fCDBDWRAIy80KiRT7H0jNCHopaXwgPLEi/gzIAvHDZoY/V+FX3HmpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a057a5bc3ca540fc67d18276c368fa8ea659808dffc3c50e16d63b2db1ec1098","last_reissued_at":"2026-05-22T01:03:53.717902Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:53.717902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Mixture Models via Efficient High-dimensional Sparse Fourier Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Alkis Kalavasis, Manolis Zampetakis, Pravesh K. Kothari, Shuchen Li","submitted_at":"2026-01-08T17:47:58Z","abstract_excerpt":"In this work, we give a ${\\rm poly}(d,k)$ time and sample algorithm for efficiently learning the parameters of a mixture of $k$ spherical distributions in $d$ dimensions. Unlike all previous methods, our techniques apply to heavy-tailed distributions and include examples that do not even have finite covariances. Our method succeeds whenever the cluster distributions have a characteristic function with sufficiently heavy tails. Such distributions include the Laplace distribution but crucially exclude Gaussians.\n  All previous methods for learning mixture models relied implicitly or explicitly o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05157","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/2601.05157/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":"2601.05157","created_at":"2026-05-22T01:03:53.718008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.05157v2","created_at":"2026-05-22T01:03:53.718008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05157","created_at":"2026-05-22T01:03:53.718008+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBL2LPB4UVAP","created_at":"2026-05-22T01:03:53.718008+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBL2LPB4UVAPYZ6R","created_at":"2026-05-22T01:03:53.718008+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBL2LPB4","created_at":"2026-05-22T01:03:53.718008+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/UBL2LPB4UVAPYZ6RQJ3MG2H2R2","json":"https://pith.science/pith/UBL2LPB4UVAPYZ6RQJ3MG2H2R2.json","graph_json":"https://pith.science/api/pith-number/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/graph.json","events_json":"https://pith.science/api/pith-number/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/events.json","paper":"https://pith.science/paper/UBL2LPB4"},"agent_actions":{"view_html":"https://pith.science/pith/UBL2LPB4UVAPYZ6RQJ3MG2H2R2","download_json":"https://pith.science/pith/UBL2LPB4UVAPYZ6RQJ3MG2H2R2.json","view_paper":"https://pith.science/paper/UBL2LPB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.05157&json=true","fetch_graph":"https://pith.science/api/pith-number/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/graph.json","fetch_events":"https://pith.science/api/pith-number/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/action/storage_attestation","attest_author":"https://pith.science/pith/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/action/author_attestation","sign_citation":"https://pith.science/pith/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/action/citation_signature","submit_replication":"https://pith.science/pith/UBL2LPB4UVAPYZ6RQJ3MG2H2R2/action/replication_record"}},"created_at":"2026-05-22T01:03:53.718008+00:00","updated_at":"2026-05-22T01:03:53.718008+00:00"}