{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:62654LPJ75GUURDFJMRUFWBZBF","short_pith_number":"pith:62654LPJ","schema_version":"1.0","canonical_sha256":"f6bdde2de9ff4d4a44654b2342d8390978db7d8d2c4c57abef36bc60a34ff593","source":{"kind":"arxiv","id":"2606.11149","version":1},"attestation_state":"computed","paper":{"title":"Efficiently Learning Drifting Halfspaces with Massart Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guyang Cao, Ilias Diakonikolas, Jelena Diakonikolas, Mingchen Ma","submitted_at":"2026-06-09T17:35:18Z","abstract_excerpt":"We study the problem of learning a drifting concept in the presence of Massart noise. In this framework, an online learner has access to a history of independent samples whose labels are noisy versions of a target concept that may change from round to round. The goal is to output, in each round, a hypothesis with small prediction error. We study the complexity of this learning problem for the fundamental class of margin-separable linear classifiers (halfspaces). On the positive side, we give a computationally efficient learner achieving error $\\eta + \\tilde O(\\Delta^{1/3}/\\gamma)$, where $\\eta"},"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":"2606.11149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T17:35:18Z","cross_cats_sorted":[],"title_canon_sha256":"30e9cf652c940ed03a496dd3d97d3c98787849d62ecdff49eb64ab2cb79434a7","abstract_canon_sha256":"7d14a3333af760ed2615811fac45d8ad7c6f76f65827e8e1a6fd81af80a0e187"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:13.858500Z","signature_b64":"5gEphco0VluN6PBU2jp5j9QdTlUY2Pevcp2VwWbLsRKMm9yG87WSWmxHsn1iLEJYMjkFZLhLvYEo6470VL1lCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6bdde2de9ff4d4a44654b2342d8390978db7d8d2c4c57abef36bc60a34ff593","last_reissued_at":"2026-06-10T01:11:13.857674Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:13.857674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficiently Learning Drifting Halfspaces with Massart Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guyang Cao, Ilias Diakonikolas, Jelena Diakonikolas, Mingchen Ma","submitted_at":"2026-06-09T17:35:18Z","abstract_excerpt":"We study the problem of learning a drifting concept in the presence of Massart noise. In this framework, an online learner has access to a history of independent samples whose labels are noisy versions of a target concept that may change from round to round. The goal is to output, in each round, a hypothesis with small prediction error. We study the complexity of this learning problem for the fundamental class of margin-separable linear classifiers (halfspaces). On the positive side, we give a computationally efficient learner achieving error $\\eta + \\tilde O(\\Delta^{1/3}/\\gamma)$, where $\\eta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11149","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/2606.11149/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":"2606.11149","created_at":"2026-06-10T01:11:13.857811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11149v1","created_at":"2026-06-10T01:11:13.857811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11149","created_at":"2026-06-10T01:11:13.857811+00:00"},{"alias_kind":"pith_short_12","alias_value":"62654LPJ75GU","created_at":"2026-06-10T01:11:13.857811+00:00"},{"alias_kind":"pith_short_16","alias_value":"62654LPJ75GUURDF","created_at":"2026-06-10T01:11:13.857811+00:00"},{"alias_kind":"pith_short_8","alias_value":"62654LPJ","created_at":"2026-06-10T01:11:13.857811+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/62654LPJ75GUURDFJMRUFWBZBF","json":"https://pith.science/pith/62654LPJ75GUURDFJMRUFWBZBF.json","graph_json":"https://pith.science/api/pith-number/62654LPJ75GUURDFJMRUFWBZBF/graph.json","events_json":"https://pith.science/api/pith-number/62654LPJ75GUURDFJMRUFWBZBF/events.json","paper":"https://pith.science/paper/62654LPJ"},"agent_actions":{"view_html":"https://pith.science/pith/62654LPJ75GUURDFJMRUFWBZBF","download_json":"https://pith.science/pith/62654LPJ75GUURDFJMRUFWBZBF.json","view_paper":"https://pith.science/paper/62654LPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11149&json=true","fetch_graph":"https://pith.science/api/pith-number/62654LPJ75GUURDFJMRUFWBZBF/graph.json","fetch_events":"https://pith.science/api/pith-number/62654LPJ75GUURDFJMRUFWBZBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62654LPJ75GUURDFJMRUFWBZBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62654LPJ75GUURDFJMRUFWBZBF/action/storage_attestation","attest_author":"https://pith.science/pith/62654LPJ75GUURDFJMRUFWBZBF/action/author_attestation","sign_citation":"https://pith.science/pith/62654LPJ75GUURDFJMRUFWBZBF/action/citation_signature","submit_replication":"https://pith.science/pith/62654LPJ75GUURDFJMRUFWBZBF/action/replication_record"}},"created_at":"2026-06-10T01:11:13.857811+00:00","updated_at":"2026-06-10T01:11:13.857811+00:00"}