{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:JV5OKTD2QSKTDQUYGYSFTQTLXU","short_pith_number":"pith:JV5OKTD2","schema_version":"1.0","canonical_sha256":"4d7ae54c7a849531c298362459c26bbd150819ec2da8336ea91b1998a8521562","source":{"kind":"arxiv","id":"1403.3610","version":2},"attestation_state":"computed","paper":{"title":"Making Risk Minimization Tolerant to Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aritra Ghosh, Naresh Manwani, P. S. Sastry","submitted_at":"2014-03-14T15:30:23Z","abstract_excerpt":"In many applications, the training data, from which one needs to learn a classifier, is corrupted with label noise. Many standard algorithms such as SVM perform poorly in presence of label noise. In this paper we investigate the robustness of risk minimization to label noise. We prove a sufficient condition on a loss function for the risk minimization under that loss to be tolerant to uniform label noise. We show that the $0-1$ loss, sigmoid loss, ramp loss and probit loss satisfy this condition though none of the standard convex loss functions satisfy it. We also prove that, by choosing a suf"},"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":"1403.3610","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-03-14T15:30:23Z","cross_cats_sorted":[],"title_canon_sha256":"6e454e1c140b8a455608f6f6781e0c05735c0140b717b844d0fb83a74bb63e7c","abstract_canon_sha256":"045eced3e18d300baefabacc44df68b888bed4c7784539d73fc1737d01328e13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:33:32.713046Z","signature_b64":"mnPm9wSleULtGNgeOtWpx1+Th4FeYEX+1cRt2IfxYnZB77SCnQSwWy+Q17DI8gKwX778FDSnz2DL+AkCiPFFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d7ae54c7a849531c298362459c26bbd150819ec2da8336ea91b1998a8521562","last_reissued_at":"2026-05-18T01:33:32.712432Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:33:32.712432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Risk Minimization Tolerant to Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aritra Ghosh, Naresh Manwani, P. S. Sastry","submitted_at":"2014-03-14T15:30:23Z","abstract_excerpt":"In many applications, the training data, from which one needs to learn a classifier, is corrupted with label noise. Many standard algorithms such as SVM perform poorly in presence of label noise. In this paper we investigate the robustness of risk minimization to label noise. We prove a sufficient condition on a loss function for the risk minimization under that loss to be tolerant to uniform label noise. We show that the $0-1$ loss, sigmoid loss, ramp loss and probit loss satisfy this condition though none of the standard convex loss functions satisfy it. We also prove that, by choosing a suf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.3610","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":""},"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":"1403.3610","created_at":"2026-05-18T01:33:32.712534+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.3610v2","created_at":"2026-05-18T01:33:32.712534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.3610","created_at":"2026-05-18T01:33:32.712534+00:00"},{"alias_kind":"pith_short_12","alias_value":"JV5OKTD2QSKT","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_16","alias_value":"JV5OKTD2QSKTDQUY","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_8","alias_value":"JV5OKTD2","created_at":"2026-05-18T12:28:35.611951+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/JV5OKTD2QSKTDQUYGYSFTQTLXU","json":"https://pith.science/pith/JV5OKTD2QSKTDQUYGYSFTQTLXU.json","graph_json":"https://pith.science/api/pith-number/JV5OKTD2QSKTDQUYGYSFTQTLXU/graph.json","events_json":"https://pith.science/api/pith-number/JV5OKTD2QSKTDQUYGYSFTQTLXU/events.json","paper":"https://pith.science/paper/JV5OKTD2"},"agent_actions":{"view_html":"https://pith.science/pith/JV5OKTD2QSKTDQUYGYSFTQTLXU","download_json":"https://pith.science/pith/JV5OKTD2QSKTDQUYGYSFTQTLXU.json","view_paper":"https://pith.science/paper/JV5OKTD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.3610&json=true","fetch_graph":"https://pith.science/api/pith-number/JV5OKTD2QSKTDQUYGYSFTQTLXU/graph.json","fetch_events":"https://pith.science/api/pith-number/JV5OKTD2QSKTDQUYGYSFTQTLXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JV5OKTD2QSKTDQUYGYSFTQTLXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JV5OKTD2QSKTDQUYGYSFTQTLXU/action/storage_attestation","attest_author":"https://pith.science/pith/JV5OKTD2QSKTDQUYGYSFTQTLXU/action/author_attestation","sign_citation":"https://pith.science/pith/JV5OKTD2QSKTDQUYGYSFTQTLXU/action/citation_signature","submit_replication":"https://pith.science/pith/JV5OKTD2QSKTDQUYGYSFTQTLXU/action/replication_record"}},"created_at":"2026-05-18T01:33:32.712534+00:00","updated_at":"2026-05-18T01:33:32.712534+00:00"}