{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JHVG7O2IFPAED6BLRQPV3GAMWS","short_pith_number":"pith:JHVG7O2I","canonical_record":{"source":{"id":"1901.11300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-31T10:41:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ce81e2435d8cbf008b85f145777d0b16f1e45628979f77c1f8aa362270f6b7d4","abstract_canon_sha256":"2305995e360ec05947a764892abd761b81bd8a202bf91358b58c1e32ae7444d3"},"schema_version":"1.0"},"canonical_sha256":"49ea6fbb482bc041f82b8c1f5d980cb4aa3b3ae30b627409fb3d80adb537b954","source":{"kind":"arxiv","id":"1901.11300","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11300","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11300v2","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11300","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"pith_short_12","alias_value":"JHVG7O2IFPAE","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JHVG7O2IFPAED6BL","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JHVG7O2I","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JHVG7O2IFPAED6BLRQPV3GAMWS","target":"record","payload":{"canonical_record":{"source":{"id":"1901.11300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-31T10:41:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ce81e2435d8cbf008b85f145777d0b16f1e45628979f77c1f8aa362270f6b7d4","abstract_canon_sha256":"2305995e360ec05947a764892abd761b81bd8a202bf91358b58c1e32ae7444d3"},"schema_version":"1.0"},"canonical_sha256":"49ea6fbb482bc041f82b8c1f5d980cb4aa3b3ae30b627409fb3d80adb537b954","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:18.734422Z","signature_b64":"tst1PIpaHgy08DpCG/YqmW1ylgtJfhR7CoPw+fCk8RTlZWXsOtPj8sempWQzl3psh4tmvc/3TaVgFwhOCDn/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49ea6fbb482bc041f82b8c1f5d980cb4aa3b3ae30b627409fb3d80adb537b954","last_reissued_at":"2026-05-17T23:46:18.733673Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:18.733673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.11300","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":"2026-05-17T23:46:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AzwLeOZAkTe2dWh4g5hCagl3943XshDy3JaIMiusWpK4vXFxOy8PB+fNaFxv7vyCB8hScLLVWVgtwehTD50cBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T13:10:04.352905Z"},"content_sha256":"ffc6f4fc39d945af098a4a3442b4bc7573c081f41dd8058c0f99ffd5e4a704c2","schema_version":"1.0","event_id":"sha256:ffc6f4fc39d945af098a4a3442b4bc7573c081f41dd8058c0f99ffd5e4a704c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JHVG7O2IFPAED6BLRQPV3GAMWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Inference via Generative Classifiers for Handling Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Li, Honglak Lee, Jinwoo Shin, Kibok Lee, Kimin Lee, Sukmin Yun","submitted_at":"2019-01-31T10:41:13Z","abstract_excerpt":"Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose a novel inference method, termed Robust Generative classifier (RoG), applicable to any discriminative (e.g., softmax) neural classifier pre-trained on noisy datasets. In particular, we induce a generative classifier on top of hidden feature spaces of the pre-trained DNNs, for obtaining a more robust decision boundary. By estimating the parameters of generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11300","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":"2026-05-17T23:46:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oTzajg6/E8XFdRK0YVUBum17+wXmD2wMF9SsP1cn1xew1pLMxTC97CkP+Yd2g0vwDacmFNM2r4R82EmUERNVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T13:10:04.353643Z"},"content_sha256":"01a30ccbd95d829f838e78bc47f8e8ef10dea9d1677dab1f53128a3ffd36bcc8","schema_version":"1.0","event_id":"sha256:01a30ccbd95d829f838e78bc47f8e8ef10dea9d1677dab1f53128a3ffd36bcc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JHVG7O2IFPAED6BLRQPV3GAMWS/bundle.json","state_url":"https://pith.science/pith/JHVG7O2IFPAED6BLRQPV3GAMWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JHVG7O2IFPAED6BLRQPV3GAMWS/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":"2026-05-25T13:10:04Z","links":{"resolver":"https://pith.science/pith/JHVG7O2IFPAED6BLRQPV3GAMWS","bundle":"https://pith.science/pith/JHVG7O2IFPAED6BLRQPV3GAMWS/bundle.json","state":"https://pith.science/pith/JHVG7O2IFPAED6BLRQPV3GAMWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JHVG7O2IFPAED6BLRQPV3GAMWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JHVG7O2IFPAED6BLRQPV3GAMWS","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":"2305995e360ec05947a764892abd761b81bd8a202bf91358b58c1e32ae7444d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-31T10:41:13Z","title_canon_sha256":"ce81e2435d8cbf008b85f145777d0b16f1e45628979f77c1f8aa362270f6b7d4"},"schema_version":"1.0","source":{"id":"1901.11300","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11300","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11300v2","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11300","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"pith_short_12","alias_value":"JHVG7O2IFPAE","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JHVG7O2IFPAED6BL","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JHVG7O2I","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:01a30ccbd95d829f838e78bc47f8e8ef10dea9d1677dab1f53128a3ffd36bcc8","target":"graph","created_at":"2026-05-17T23:46:18Z","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-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose a novel inference method, termed Robust Generative classifier (RoG), applicable to any discriminative (e.g., softmax) neural classifier pre-trained on noisy datasets. In particular, we induce a generative classifier on top of hidden feature spaces of the pre-trained DNNs, for obtaining a more robust decision boundary. By estimating the parameters of generati","authors_text":"Bo Li, Honglak Lee, Jinwoo Shin, Kibok Lee, Kimin Lee, Sukmin Yun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-31T10:41:13Z","title":"Robust Inference via Generative Classifiers for Handling Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11300","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:ffc6f4fc39d945af098a4a3442b4bc7573c081f41dd8058c0f99ffd5e4a704c2","target":"record","created_at":"2026-05-17T23:46:18Z","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":"2305995e360ec05947a764892abd761b81bd8a202bf91358b58c1e32ae7444d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-31T10:41:13Z","title_canon_sha256":"ce81e2435d8cbf008b85f145777d0b16f1e45628979f77c1f8aa362270f6b7d4"},"schema_version":"1.0","source":{"id":"1901.11300","kind":"arxiv","version":2}},"canonical_sha256":"49ea6fbb482bc041f82b8c1f5d980cb4aa3b3ae30b627409fb3d80adb537b954","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49ea6fbb482bc041f82b8c1f5d980cb4aa3b3ae30b627409fb3d80adb537b954","first_computed_at":"2026-05-17T23:46:18.733673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:18.733673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tst1PIpaHgy08DpCG/YqmW1ylgtJfhR7CoPw+fCk8RTlZWXsOtPj8sempWQzl3psh4tmvc/3TaVgFwhOCDn/CQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:18.734422Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.11300","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffc6f4fc39d945af098a4a3442b4bc7573c081f41dd8058c0f99ffd5e4a704c2","sha256:01a30ccbd95d829f838e78bc47f8e8ef10dea9d1677dab1f53128a3ffd36bcc8"],"state_sha256":"2ce307b7e7774e38162a07f894a963a867a53622793293a44c1aa742983f2593"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HTY5P/VLVlyWRB/EXkNEIkRknuXxIbbIEdyaY+/tAhL7PYCEJSsaOt0NxRA/9q8PQUbCrQF5Vq26HaokENVyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T13:10:04.359033Z","bundle_sha256":"e195c3dc2c42bbc344bf4c6eb8a3beac3984daa7cdd3c064c9f446842cd2c75c"}}