{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GVXO5SF2F252IXSQYOQLPXC6BK","short_pith_number":"pith:GVXO5SF2","schema_version":"1.0","canonical_sha256":"356eeec8ba2ebba45e50c3a0b7dc5e0a8437449e1f029647f9c706e4f01bd545","source":{"kind":"arxiv","id":"2006.04787","version":2},"attestation_state":"computed","paper":{"title":"Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Ankur Moitra, Frederic Koehler, Morris Yau, Sitan Chen","submitted_at":"2020-06-08T17:59:11Z","abstract_excerpt":"In this paper we revisit some classic problems on classification under misspecification. In particular, we study the problem of learning halfspaces under Massart noise with rate $\\eta$. In a recent work, Diakonikolas, Goulekakis, and Tzamos resolved a long-standing problem by giving the first efficient algorithm for learning to accuracy $\\eta + \\epsilon$ for any $\\epsilon > 0$. However, their algorithm outputs a complicated hypothesis, which partitions space into $\\text{poly}(d,1/\\epsilon)$ regions. Here we give a much simpler algorithm and in the process resolve a number of outstanding open q"},"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":"2006.04787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T17:59:11Z","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"0010041f67815fda45b2a0b97ae8acec116fb75ae07902d1a00d6dc66c651ba8","abstract_canon_sha256":"cd8664b1f6ed667e375a4fe4f920243381a3e4d4d200089f75b4e798eecf0cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:18.168964Z","signature_b64":"eeXW5775qDrpXPvQ6gqT6rfA57GncfNN2c+iVX7jwvO/u+GE/GAeXWBYi4ojuRRGW/QXTrgxj+pAGMXPwpMTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"356eeec8ba2ebba45e50c3a0b7dc5e0a8437449e1f029647f9c706e4f01bd545","last_reissued_at":"2026-07-05T06:52:18.168501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:18.168501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Ankur Moitra, Frederic Koehler, Morris Yau, Sitan Chen","submitted_at":"2020-06-08T17:59:11Z","abstract_excerpt":"In this paper we revisit some classic problems on classification under misspecification. In particular, we study the problem of learning halfspaces under Massart noise with rate $\\eta$. In a recent work, Diakonikolas, Goulekakis, and Tzamos resolved a long-standing problem by giving the first efficient algorithm for learning to accuracy $\\eta + \\epsilon$ for any $\\epsilon > 0$. However, their algorithm outputs a complicated hypothesis, which partitions space into $\\text{poly}(d,1/\\epsilon)$ regions. Here we give a much simpler algorithm and in the process resolve a number of outstanding open q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04787","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/2006.04787/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":"2006.04787","created_at":"2026-07-05T06:52:18.168552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04787v2","created_at":"2026-07-05T06:52:18.168552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04787","created_at":"2026-07-05T06:52:18.168552+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVXO5SF2F252","created_at":"2026-07-05T06:52:18.168552+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVXO5SF2F252IXSQ","created_at":"2026-07-05T06:52:18.168552+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVXO5SF2","created_at":"2026-07-05T06:52:18.168552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15694","citing_title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","ref_index":2019,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK","json":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK.json","graph_json":"https://pith.science/api/pith-number/GVXO5SF2F252IXSQYOQLPXC6BK/graph.json","events_json":"https://pith.science/api/pith-number/GVXO5SF2F252IXSQYOQLPXC6BK/events.json","paper":"https://pith.science/paper/GVXO5SF2"},"agent_actions":{"view_html":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK","download_json":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK.json","view_paper":"https://pith.science/paper/GVXO5SF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04787&json=true","fetch_graph":"https://pith.science/api/pith-number/GVXO5SF2F252IXSQYOQLPXC6BK/graph.json","fetch_events":"https://pith.science/api/pith-number/GVXO5SF2F252IXSQYOQLPXC6BK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK/action/storage_attestation","attest_author":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK/action/author_attestation","sign_citation":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK/action/citation_signature","submit_replication":"https://pith.science/pith/GVXO5SF2F252IXSQYOQLPXC6BK/action/replication_record"}},"created_at":"2026-07-05T06:52:18.168552+00:00","updated_at":"2026-07-05T06:52:18.168552+00:00"}