{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PPWPA4SRMEM4PXZFOBC6KZXF62","short_pith_number":"pith:PPWPA4SR","schema_version":"1.0","canonical_sha256":"7becf072516119c7df257045e566e5f6bc83342173fed5c07c74754108cb19e3","source":{"kind":"arxiv","id":"2011.09973","version":1},"attestation_state":"computed","paper":{"title":"List-Decodable Mean Estimation in Nearly-PCA Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.DS","authors_text":"Daniel Kongsgaard, Daniel M. Kane, Ilias Diakonikolas, Jerry Li, Kevin Tian","submitted_at":"2020-11-19T17:21:37Z","abstract_excerpt":"Traditionally, robust statistics has focused on designing estimators tolerant to a minority of contaminated data. Robust list-decodable learning focuses on the more challenging regime where only a minority $\\frac 1 k$ fraction of the dataset is drawn from the distribution of interest, and no assumptions are made on the remaining data. We study the fundamental task of list-decodable mean estimation in high dimensions. Our main result is a new list-decodable mean estimation algorithm for bounded covariance distributions with optimal sample complexity and error rate, running in nearly-PCA time. A"},"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":"2011.09973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-11-19T17:21:37Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"a4553448d6ff642ce1002c69d497489d28aaf2ed8a612bd55b4289685e3e1f7b","abstract_canon_sha256":"db1db64047d3213e4da0850cfec22d528d1109c883940b16c5516e2ae8614866"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:03.112532Z","signature_b64":"ZiooVQ0c/766+C5I8jwNjjhSLw5SOJ4z3xEL+ikZZnVRhyp7jk8orblEnLEJKoNRfforfcs7WTNNmdp0S9wmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7becf072516119c7df257045e566e5f6bc83342173fed5c07c74754108cb19e3","last_reissued_at":"2026-07-05T01:53:03.112127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:03.112127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"List-Decodable Mean Estimation in Nearly-PCA Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.DS","authors_text":"Daniel Kongsgaard, Daniel M. Kane, Ilias Diakonikolas, Jerry Li, Kevin Tian","submitted_at":"2020-11-19T17:21:37Z","abstract_excerpt":"Traditionally, robust statistics has focused on designing estimators tolerant to a minority of contaminated data. Robust list-decodable learning focuses on the more challenging regime where only a minority $\\frac 1 k$ fraction of the dataset is drawn from the distribution of interest, and no assumptions are made on the remaining data. We study the fundamental task of list-decodable mean estimation in high dimensions. Our main result is a new list-decodable mean estimation algorithm for bounded covariance distributions with optimal sample complexity and error rate, running in nearly-PCA time. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09973","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.09973/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":"2011.09973","created_at":"2026-07-05T01:53:03.112181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.09973v1","created_at":"2026-07-05T01:53:03.112181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09973","created_at":"2026-07-05T01:53:03.112181+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPWPA4SRMEM4","created_at":"2026-07-05T01:53:03.112181+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPWPA4SRMEM4PXZF","created_at":"2026-07-05T01:53:03.112181+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPWPA4SR","created_at":"2026-07-05T01:53:03.112181+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/PPWPA4SRMEM4PXZFOBC6KZXF62","json":"https://pith.science/pith/PPWPA4SRMEM4PXZFOBC6KZXF62.json","graph_json":"https://pith.science/api/pith-number/PPWPA4SRMEM4PXZFOBC6KZXF62/graph.json","events_json":"https://pith.science/api/pith-number/PPWPA4SRMEM4PXZFOBC6KZXF62/events.json","paper":"https://pith.science/paper/PPWPA4SR"},"agent_actions":{"view_html":"https://pith.science/pith/PPWPA4SRMEM4PXZFOBC6KZXF62","download_json":"https://pith.science/pith/PPWPA4SRMEM4PXZFOBC6KZXF62.json","view_paper":"https://pith.science/paper/PPWPA4SR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.09973&json=true","fetch_graph":"https://pith.science/api/pith-number/PPWPA4SRMEM4PXZFOBC6KZXF62/graph.json","fetch_events":"https://pith.science/api/pith-number/PPWPA4SRMEM4PXZFOBC6KZXF62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPWPA4SRMEM4PXZFOBC6KZXF62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPWPA4SRMEM4PXZFOBC6KZXF62/action/storage_attestation","attest_author":"https://pith.science/pith/PPWPA4SRMEM4PXZFOBC6KZXF62/action/author_attestation","sign_citation":"https://pith.science/pith/PPWPA4SRMEM4PXZFOBC6KZXF62/action/citation_signature","submit_replication":"https://pith.science/pith/PPWPA4SRMEM4PXZFOBC6KZXF62/action/replication_record"}},"created_at":"2026-07-05T01:53:03.112181+00:00","updated_at":"2026-07-05T01:53:03.112181+00:00"}