{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VUPBXBFEE3T5NUQIAN3ARCKXZC","short_pith_number":"pith:VUPBXBFE","canonical_record":{"source":{"id":"1705.03419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-09T16:42:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bdf52cb62412b09845b355dc9e21f1419f8d43ae1b7761cb2888406028ab9f2a","abstract_canon_sha256":"5349a9892d96788d35ad25194f683957f9ff7088c8eec318188b63b71e4f73e0"},"schema_version":"1.0"},"canonical_sha256":"ad1e1b84a426e7d6d2080376088957c8be5c0c26d3abd15142d51cd26999d2a6","source":{"kind":"arxiv","id":"1705.03419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03419","created_at":"2026-05-18T00:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03419v1","created_at":"2026-05-18T00:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03419","created_at":"2026-05-18T00:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"VUPBXBFEE3T5","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VUPBXBFEE3T5NUQI","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VUPBXBFE","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VUPBXBFEE3T5NUQIAN3ARCKXZC","target":"record","payload":{"canonical_record":{"source":{"id":"1705.03419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-09T16:42:32Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bdf52cb62412b09845b355dc9e21f1419f8d43ae1b7761cb2888406028ab9f2a","abstract_canon_sha256":"5349a9892d96788d35ad25194f683957f9ff7088c8eec318188b63b71e4f73e0"},"schema_version":"1.0"},"canonical_sha256":"ad1e1b84a426e7d6d2080376088957c8be5c0c26d3abd15142d51cd26999d2a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:47.908264Z","signature_b64":"tbGnpOIGyjK0SOROHSLHn4JeBQTrJeQztEqViLVrmnCWLGvOCNGzSA93MtEx6eIsUg7in3LtdNot7pma6TOLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad1e1b84a426e7d6d2080376088957c8be5c0c26d3abd15142d51cd26999d2a6","last_reissued_at":"2026-05-18T00:44:47.907626Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:47.907626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.03419","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xuiOUaPeO0J3WMIw96GX9buIcD+IJEtDMCLbN+izR8GGUM58LuxuPyteSYvkwdsPjgKrj6rvkAZHQL98CFSRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T18:37:19.642982Z"},"content_sha256":"b940aa90a9d8f16cf444be7ad77f248fa7a66ad4def1c85a5476f24aeea8b779","schema_version":"1.0","event_id":"sha256:b940aa90a9d8f16cf444be7ad77f248fa7a66ad4def1c85a5476f24aeea8b779"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VUPBXBFEE3T5NUQIAN3ARCKXZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Deep Networks from Noisy Labels with Dropout Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Ishan Jindal, Matthew Nokleby, Xuewen Chen","submitted_at":"2017-05-09T16:42:32Z","abstract_excerpt":"Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective technique for accounting for label noise when training deep neural networks. We augment a standard deep network with a softmax layer that models the label noise statistics. Then, we train the deep network and noise model jointly via end-to-end stochastic gradient descent on the (perhaps mislabeled) dataset. The augmented model is overdetermined, so in order to enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03419","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iX5PBY/1TCjCce80aARBl8i1oWJwsxYV8ztWKy/geo8gYD+aup/yN4XxUXHrvh2LKhiuAZaQPW2n/CZd/1ibBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T18:37:19.643342Z"},"content_sha256":"5230018bfb1126d367ace750f46350b6d229589407e6b58b4cbaeecbe6394f51","schema_version":"1.0","event_id":"sha256:5230018bfb1126d367ace750f46350b6d229589407e6b58b4cbaeecbe6394f51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VUPBXBFEE3T5NUQIAN3ARCKXZC/bundle.json","state_url":"https://pith.science/pith/VUPBXBFEE3T5NUQIAN3ARCKXZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VUPBXBFEE3T5NUQIAN3ARCKXZC/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":"2026-06-02T18:37:19Z","links":{"resolver":"https://pith.science/pith/VUPBXBFEE3T5NUQIAN3ARCKXZC","bundle":"https://pith.science/pith/VUPBXBFEE3T5NUQIAN3ARCKXZC/bundle.json","state":"https://pith.science/pith/VUPBXBFEE3T5NUQIAN3ARCKXZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VUPBXBFEE3T5NUQIAN3ARCKXZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VUPBXBFEE3T5NUQIAN3ARCKXZC","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":"5349a9892d96788d35ad25194f683957f9ff7088c8eec318188b63b71e4f73e0","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-09T16:42:32Z","title_canon_sha256":"bdf52cb62412b09845b355dc9e21f1419f8d43ae1b7761cb2888406028ab9f2a"},"schema_version":"1.0","source":{"id":"1705.03419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03419","created_at":"2026-05-18T00:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03419v1","created_at":"2026-05-18T00:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03419","created_at":"2026-05-18T00:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"VUPBXBFEE3T5","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VUPBXBFEE3T5NUQI","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VUPBXBFE","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:5230018bfb1126d367ace750f46350b6d229589407e6b58b4cbaeecbe6394f51","target":"graph","created_at":"2026-05-18T00:44:47Z","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":"Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective technique for accounting for label noise when training deep neural networks. We augment a standard deep network with a softmax layer that models the label noise statistics. Then, we train the deep network and noise model jointly via end-to-end stochastic gradient descent on the (perhaps mislabeled) dataset. The augmented model is overdetermined, so in order to enco","authors_text":"Ishan Jindal, Matthew Nokleby, Xuewen Chen","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-09T16:42:32Z","title":"Learning Deep Networks from Noisy Labels with Dropout Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03419","kind":"arxiv","version":1},"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:b940aa90a9d8f16cf444be7ad77f248fa7a66ad4def1c85a5476f24aeea8b779","target":"record","created_at":"2026-05-18T00:44:47Z","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":"5349a9892d96788d35ad25194f683957f9ff7088c8eec318188b63b71e4f73e0","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-09T16:42:32Z","title_canon_sha256":"bdf52cb62412b09845b355dc9e21f1419f8d43ae1b7761cb2888406028ab9f2a"},"schema_version":"1.0","source":{"id":"1705.03419","kind":"arxiv","version":1}},"canonical_sha256":"ad1e1b84a426e7d6d2080376088957c8be5c0c26d3abd15142d51cd26999d2a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad1e1b84a426e7d6d2080376088957c8be5c0c26d3abd15142d51cd26999d2a6","first_computed_at":"2026-05-18T00:44:47.907626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:47.907626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tbGnpOIGyjK0SOROHSLHn4JeBQTrJeQztEqViLVrmnCWLGvOCNGzSA93MtEx6eIsUg7in3LtdNot7pma6TOLBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:47.908264Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.03419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b940aa90a9d8f16cf444be7ad77f248fa7a66ad4def1c85a5476f24aeea8b779","sha256:5230018bfb1126d367ace750f46350b6d229589407e6b58b4cbaeecbe6394f51"],"state_sha256":"4b575e3866e5ac7f208aa83edd73c94da030f7a110c270cc812c35996ed94c4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QwqU/hJJJq6drwzsqplUkXe+nxipvW0WZhnhFzDPehx15Suq5XKlUY3PuaZ/nzUo80GtzJGIQ8VZ5xqDTfmuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T18:37:19.645266Z","bundle_sha256":"9f401c584e5b2436e3f5e63dc13f3ac263c01cd0d8ac9f6b6b6dda1937c47c36"}}