{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RWZSLLY354OABOK5IKFWQR64IC","short_pith_number":"pith:RWZSLLY3","schema_version":"1.0","canonical_sha256":"8db325af1bef1c00b95d428b6847dc40aac545e02cd70c787de632e97724d3bd","source":{"kind":"arxiv","id":"1609.03683","version":2},"attestation_state":"computed","paper":{"title":"Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aditya Menon, Alessandro Rozza, Giorgio Patrini, Lizhen Qu, Richard Nock","submitted_at":"2016-09-13T05:23:29Z","abstract_excerpt":"We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and network architecture. They simply amount to at most a matrix inversion and multiplication, provided that we know the probability of each class being corrupted into another. We further show how one can estimate these probabilities, adapting a recent technique for noise estimation to the multi-class setting, and thus providing an end-to-end framework. Extensi"},"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":"1609.03683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-09-13T05:23:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"65d866d3806280cb9832257fae078c742d70bf320ae2359ce2cbe12c124e3079","abstract_canon_sha256":"921a251d6ca82b7eab5dba89a7f2016c8e3f11c5cedddfd3d40f702647fd53d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:09.613659Z","signature_b64":"vAU/4KeBMgN5g0tEI75/XFsn/dN2gQDet42gaPXrriybBmIlTc+XZM5w1FwsZGdlgUKp0geZS5IuNkPPLWnBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8db325af1bef1c00b95d428b6847dc40aac545e02cd70c787de632e97724d3bd","last_reissued_at":"2026-05-18T00:48:09.613191Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:09.613191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aditya Menon, Alessandro Rozza, Giorgio Patrini, Lizhen Qu, Richard Nock","submitted_at":"2016-09-13T05:23:29Z","abstract_excerpt":"We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and network architecture. They simply amount to at most a matrix inversion and multiplication, provided that we know the probability of each class being corrupted into another. We further show how one can estimate these probabilities, adapting a recent technique for noise estimation to the multi-class setting, and thus providing an end-to-end framework. Extensi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03683","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":"1609.03683","created_at":"2026-05-18T00:48:09.613266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.03683v2","created_at":"2026-05-18T00:48:09.613266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03683","created_at":"2026-05-18T00:48:09.613266+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWZSLLY354OA","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWZSLLY354OABOK5","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWZSLLY3","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.24985","citing_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC","json":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC.json","graph_json":"https://pith.science/api/pith-number/RWZSLLY354OABOK5IKFWQR64IC/graph.json","events_json":"https://pith.science/api/pith-number/RWZSLLY354OABOK5IKFWQR64IC/events.json","paper":"https://pith.science/paper/RWZSLLY3"},"agent_actions":{"view_html":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC","download_json":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC.json","view_paper":"https://pith.science/paper/RWZSLLY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.03683&json=true","fetch_graph":"https://pith.science/api/pith-number/RWZSLLY354OABOK5IKFWQR64IC/graph.json","fetch_events":"https://pith.science/api/pith-number/RWZSLLY354OABOK5IKFWQR64IC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/action/storage_attestation","attest_author":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/action/author_attestation","sign_citation":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/action/citation_signature","submit_replication":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/action/replication_record"}},"created_at":"2026-05-18T00:48:09.613266+00:00","updated_at":"2026-05-18T00:48:09.613266+00:00"}