{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VO6U4TY7BSXAPUX2I4VV677KHF","short_pith_number":"pith:VO6U4TY7","schema_version":"1.0","canonical_sha256":"abbd4e4f1f0cae07d2fa472b5f7fea395114ae81adae343f7bdae9461b389141","source":{"kind":"arxiv","id":"1712.09482","version":1},"attestation_state":"computed","paper":{"title":"Robust Loss Functions under Label Noise for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aritra Ghosh, Himanshu kumar, P.S. Sastry","submitted_at":"2017-12-27T03:07:57Z","abstract_excerpt":"In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and on algorithms for estimating true labels from noisy labels. An alternate approach would be to look for loss functions that are inherently noise-tolerant. For binary classification there exist theoretical results on loss functions that are robust to label noise. In this paper, we"},"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":"1712.09482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-27T03:07:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e1525217d1efee5818b0329612f60b744df87fff92ca1448ff1cab6595fe9abf","abstract_canon_sha256":"c5f518905f5fc8fd3f3a21f171db979334c6bb96b5986be2d58b7de01c44119c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:08.255622Z","signature_b64":"pPV4gtyYvFqI6TMnzKf25ubvxp+8TzT7Z6QI4jMe+ytUySEOP2RPJRJJiIcSWHcYXwo8RNNgb1f85wPzV31wAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abbd4e4f1f0cae07d2fa472b5f7fea395114ae81adae343f7bdae9461b389141","last_reissued_at":"2026-05-18T00:27:08.254983Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:08.254983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Loss Functions under Label Noise for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aritra Ghosh, Himanshu kumar, P.S. Sastry","submitted_at":"2017-12-27T03:07:57Z","abstract_excerpt":"In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and on algorithms for estimating true labels from noisy labels. An alternate approach would be to look for loss functions that are inherently noise-tolerant. For binary classification there exist theoretical results on loss functions that are robust to label noise. In this paper, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09482","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":""},"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":"1712.09482","created_at":"2026-05-18T00:27:08.255074+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09482v1","created_at":"2026-05-18T00:27:08.255074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09482","created_at":"2026-05-18T00:27:08.255074+00:00"},{"alias_kind":"pith_short_12","alias_value":"VO6U4TY7BSXA","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VO6U4TY7BSXAPUX2","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VO6U4TY7","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2210.09817","citing_title":"Universal hidden monotonic trend estimation with contrastive learning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2410.15761","citing_title":"Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF","json":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF.json","graph_json":"https://pith.science/api/pith-number/VO6U4TY7BSXAPUX2I4VV677KHF/graph.json","events_json":"https://pith.science/api/pith-number/VO6U4TY7BSXAPUX2I4VV677KHF/events.json","paper":"https://pith.science/paper/VO6U4TY7"},"agent_actions":{"view_html":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF","download_json":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF.json","view_paper":"https://pith.science/paper/VO6U4TY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09482&json=true","fetch_graph":"https://pith.science/api/pith-number/VO6U4TY7BSXAPUX2I4VV677KHF/graph.json","fetch_events":"https://pith.science/api/pith-number/VO6U4TY7BSXAPUX2I4VV677KHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF/action/storage_attestation","attest_author":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF/action/author_attestation","sign_citation":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF/action/citation_signature","submit_replication":"https://pith.science/pith/VO6U4TY7BSXAPUX2I4VV677KHF/action/replication_record"}},"created_at":"2026-05-18T00:27:08.255074+00:00","updated_at":"2026-05-18T00:27:08.255074+00:00"}