{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RWZSLLY354OABOK5IKFWQR64IC","short_pith_number":"pith:RWZSLLY3","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"},"canonical_sha256":"8db325af1bef1c00b95d428b6847dc40aac545e02cd70c787de632e97724d3bd","source":{"kind":"arxiv","id":"1609.03683","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.03683","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"1609.03683v2","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03683","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"RWZSLLY354OA","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RWZSLLY354OABOK5","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RWZSLLY3","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RWZSLLY354OABOK5IKFWQR64IC","target":"record","payload":{"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"},"canonical_sha256":"8db325af1bef1c00b95d428b6847dc40aac545e02cd70c787de632e97724d3bd","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"},"source_kind":"arxiv","source_id":"1609.03683","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQWI6+hLW5nmO3wtfwvwsqwV/rGCQtv29B5A/VPyeVWYEjsmrmiNYQnCB0hI4KE1TVt+BSzq0r0NESnX8OIADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T15:12:28.298968Z"},"content_sha256":"1ed852e446c0e8dbfadb7147b5cd019a409caf4270e645f79136051da0546217","schema_version":"1.0","event_id":"sha256:1ed852e446c0e8dbfadb7147b5cd019a409caf4270e645f79136051da0546217"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RWZSLLY354OABOK5IKFWQR64IC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y8kG62cs9r9oGhOqzenW3DmOPnfJfAz0UW3gAU7BzaxdBSXeVAv8Ys41UtumAU+3rLq0L+3UrSN8oiA42yprCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T15:12:28.299304Z"},"content_sha256":"a86d874034e72c838b91b7b583395182f42e6e4d597bdd5df772a046ec62f133","schema_version":"1.0","event_id":"sha256:a86d874034e72c838b91b7b583395182f42e6e4d597bdd5df772a046ec62f133"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/bundle.json","state_url":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWZSLLY354OABOK5IKFWQR64IC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-26T15:12:28Z","links":{"resolver":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC","bundle":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/bundle.json","state":"https://pith.science/pith/RWZSLLY354OABOK5IKFWQR64IC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWZSLLY354OABOK5IKFWQR64IC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RWZSLLY354OABOK5IKFWQR64IC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"921a251d6ca82b7eab5dba89a7f2016c8e3f11c5cedddfd3d40f702647fd53d9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-09-13T05:23:29Z","title_canon_sha256":"65d866d3806280cb9832257fae078c742d70bf320ae2359ce2cbe12c124e3079"},"schema_version":"1.0","source":{"id":"1609.03683","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.03683","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"1609.03683v2","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03683","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"RWZSLLY354OA","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RWZSLLY354OABOK5","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RWZSLLY3","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:a86d874034e72c838b91b7b583395182f42e6e4d597bdd5df772a046ec62f133","target":"graph","created_at":"2026-05-18T00:48:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Aditya Menon, Alessandro Rozza, Giorgio Patrini, Lizhen Qu, Richard Nock","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-09-13T05:23:29Z","title":"Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03683","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1ed852e446c0e8dbfadb7147b5cd019a409caf4270e645f79136051da0546217","target":"record","created_at":"2026-05-18T00:48:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"921a251d6ca82b7eab5dba89a7f2016c8e3f11c5cedddfd3d40f702647fd53d9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-09-13T05:23:29Z","title_canon_sha256":"65d866d3806280cb9832257fae078c742d70bf320ae2359ce2cbe12c124e3079"},"schema_version":"1.0","source":{"id":"1609.03683","kind":"arxiv","version":2}},"canonical_sha256":"8db325af1bef1c00b95d428b6847dc40aac545e02cd70c787de632e97724d3bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8db325af1bef1c00b95d428b6847dc40aac545e02cd70c787de632e97724d3bd","first_computed_at":"2026-05-18T00:48:09.613191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:09.613191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vAU/4KeBMgN5g0tEI75/XFsn/dN2gQDet42gaPXrriybBmIlTc+XZM5w1FwsZGdlgUKp0geZS5IuNkPPLWnBCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:09.613659Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.03683","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ed852e446c0e8dbfadb7147b5cd019a409caf4270e645f79136051da0546217","sha256:a86d874034e72c838b91b7b583395182f42e6e4d597bdd5df772a046ec62f133"],"state_sha256":"3dc5ac0fc40aeb3b8abaf2da0c1a117cafa0dd805a66ebcad2e89037340c53c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"02Z5Z6QLuHTe3LF6RgwtQA3GgguyI1bE9BAilc0KDKiwxBTHcdgeJ24JeCRORxr33MqegG5TYlRJDGo4qPu6AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T15:12:28.301228Z","bundle_sha256":"b0faa510ea11c3c8e76b589e5706624f9d3a52bc4a26d02bafe768742a1f70ae"}}