{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EEROSX4PRK2JSYZZUX3BBO5UHX","short_pith_number":"pith:EEROSX4P","schema_version":"1.0","canonical_sha256":"2122e95f8f8ab4996339a5f610bbb43ddfadfc22159dcf9c2431e43ca3cc22d5","source":{"kind":"arxiv","id":"2405.12958","version":1},"attestation_state":"computed","paper":{"title":"Online Learning of Halfspaces with Massart Noise","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":"Christos Tzamos, Ilias Diakonikolas, Nikos Zarifis, Vasilis Kontonis","submitted_at":"2024-05-21T17:31:10Z","abstract_excerpt":"We study the task of online learning in the presence of Massart noise. Instead of assuming that the online adversary chooses an arbitrary sequence of labels, we assume that the context $\\mathbf{x}$ is selected adversarially but the label $y$ presented to the learner disagrees with the ground-truth label of $\\mathbf{x}$ with unknown probability at most $\\eta$. We study the fundamental class of $\\gamma$-margin linear classifiers and present a computationally efficient algorithm that achieves mistake bound $\\eta T + o(T)$. Our mistake bound is qualitatively tight for efficient algorithms: it is k"},"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":"2405.12958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-21T17:31:10Z","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"cb13f7b52af9cc1aa5b51c3a416ad74974b4e8fe557de6f19602c58c8a779976","abstract_canon_sha256":"229e9662d16ebb209796c8e5409d06112aaaf5b19409b5f7077b5653f1c197f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:28.932420Z","signature_b64":"jStP3yesHSfbXZRUMjzN9MQ+T9tDfz88jTt0oni9INqIb4lwKdblaacIacLcnQd6Mx5bbNFkyMfqIaSBv1w8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2122e95f8f8ab4996339a5f610bbb43ddfadfc22159dcf9c2431e43ca3cc22d5","last_reissued_at":"2026-07-05T08:21:28.931934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:28.931934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning of Halfspaces with Massart Noise","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":"Christos Tzamos, Ilias Diakonikolas, Nikos Zarifis, Vasilis Kontonis","submitted_at":"2024-05-21T17:31:10Z","abstract_excerpt":"We study the task of online learning in the presence of Massart noise. Instead of assuming that the online adversary chooses an arbitrary sequence of labels, we assume that the context $\\mathbf{x}$ is selected adversarially but the label $y$ presented to the learner disagrees with the ground-truth label of $\\mathbf{x}$ with unknown probability at most $\\eta$. We study the fundamental class of $\\gamma$-margin linear classifiers and present a computationally efficient algorithm that achieves mistake bound $\\eta T + o(T)$. Our mistake bound is qualitatively tight for efficient algorithms: it is k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12958","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/2405.12958/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":"2405.12958","created_at":"2026-07-05T08:21:28.931986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12958v1","created_at":"2026-07-05T08:21:28.931986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12958","created_at":"2026-07-05T08:21:28.931986+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEROSX4PRK2J","created_at":"2026-07-05T08:21:28.931986+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEROSX4PRK2JSYZZ","created_at":"2026-07-05T08:21:28.931986+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEROSX4P","created_at":"2026-07-05T08:21:28.931986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.01020","citing_title":"The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX","json":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX.json","graph_json":"https://pith.science/api/pith-number/EEROSX4PRK2JSYZZUX3BBO5UHX/graph.json","events_json":"https://pith.science/api/pith-number/EEROSX4PRK2JSYZZUX3BBO5UHX/events.json","paper":"https://pith.science/paper/EEROSX4P"},"agent_actions":{"view_html":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX","download_json":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX.json","view_paper":"https://pith.science/paper/EEROSX4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12958&json=true","fetch_graph":"https://pith.science/api/pith-number/EEROSX4PRK2JSYZZUX3BBO5UHX/graph.json","fetch_events":"https://pith.science/api/pith-number/EEROSX4PRK2JSYZZUX3BBO5UHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX/action/storage_attestation","attest_author":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX/action/author_attestation","sign_citation":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX/action/citation_signature","submit_replication":"https://pith.science/pith/EEROSX4PRK2JSYZZUX3BBO5UHX/action/replication_record"}},"created_at":"2026-07-05T08:21:28.931986+00:00","updated_at":"2026-07-05T08:21:28.931986+00:00"}