{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MSINUROHKYACIIPRGJU6T6ZYZ5","short_pith_number":"pith:MSINUROH","canonical_record":{"source":{"id":"1811.03821","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T09:07:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8c1efc837bbf5f9834c5b5e32c5325ab2e8e8d2c4ec874c85730982000bf6527","abstract_canon_sha256":"ee1161250b9eb2d607b71379b2d3668f1548ae96066195e6851d5029b78e9719"},"schema_version":"1.0"},"canonical_sha256":"6490da45c756002421f13269e9fb38cf713f0e18bd09dd82f1300c3ac9acc79b","source":{"kind":"arxiv","id":"1811.03821","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03821","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03821v3","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03821","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"MSINUROHKYAC","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MSINUROHKYACIIPR","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MSINUROH","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MSINUROHKYACIIPRGJU6T6ZYZ5","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03821","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T09:07:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8c1efc837bbf5f9834c5b5e32c5325ab2e8e8d2c4ec874c85730982000bf6527","abstract_canon_sha256":"ee1161250b9eb2d607b71379b2d3668f1548ae96066195e6851d5029b78e9719"},"schema_version":"1.0"},"canonical_sha256":"6490da45c756002421f13269e9fb38cf713f0e18bd09dd82f1300c3ac9acc79b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:29.227123Z","signature_b64":"9ckSq5ujCEjTxjdeYfjk3ZnZxINctcLN+bobLIY7iIpAk1mkKlrvTDpm8L2XhiH9pk1/i53R0N20BWt5owzkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6490da45c756002421f13269e9fb38cf713f0e18bd09dd82f1300c3ac9acc79b","last_reissued_at":"2026-05-17T23:56:29.226659Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:29.226659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03821","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JnD+FivPlv+nvh9FAcLHv5RCRVSg3j6o03VT3biJQLAGA0Bx42CmT5bGrRjR3yyJ1sYyzYMxjnq5xaSoPzeaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T00:27:10.146629Z"},"content_sha256":"9e8c0d7ed378918248c62ac4ddb484a9c17fe6bcc45688ce0fac97853f3aee1d","schema_version":"1.0","event_id":"sha256:9e8c0d7ed378918248c62ac4ddb484a9c17fe6bcc45688ce0fac97853f3aee1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MSINUROHKYACIIPRGJU6T6ZYZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skeptical Deep Learning with Distribution Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuanren Liu, Fangzhao Wu, Guangyi Lv, Jianhui Ma, Mingxiao An, Qi Liu, Yongzhou Chen","submitted_at":"2018-11-09T09:07:06Z","abstract_excerpt":"Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world applications. One solution is to make supervised learning robust with imperfectly labeled input. In this paper, we develop a distribution correction approach that allows deep neural networks to avoid overfitting imperfect training data. Specifically, we treat the noisy input as samples from an incorrect distribution, which will be automatically corrected dur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03821","kind":"arxiv","version":3},"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":"2026-05-17T23:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nnIhwuFGrzSQ7MG3MhT3TwF6/UogKYU0yn2zkHDn9LxS9ws8Bg6AUhR0IbMD1qBwzaHc/1tPPexSQJAsni7GBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T00:27:10.147081Z"},"content_sha256":"189dd115048a3748767fe60c68fa88beeb58f6279ac8978a822ef21eda391a5d","schema_version":"1.0","event_id":"sha256:189dd115048a3748767fe60c68fa88beeb58f6279ac8978a822ef21eda391a5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSINUROHKYACIIPRGJU6T6ZYZ5/bundle.json","state_url":"https://pith.science/pith/MSINUROHKYACIIPRGJU6T6ZYZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSINUROHKYACIIPRGJU6T6ZYZ5/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":"2026-06-12T00:27:10Z","links":{"resolver":"https://pith.science/pith/MSINUROHKYACIIPRGJU6T6ZYZ5","bundle":"https://pith.science/pith/MSINUROHKYACIIPRGJU6T6ZYZ5/bundle.json","state":"https://pith.science/pith/MSINUROHKYACIIPRGJU6T6ZYZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSINUROHKYACIIPRGJU6T6ZYZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MSINUROHKYACIIPRGJU6T6ZYZ5","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":"ee1161250b9eb2d607b71379b2d3668f1548ae96066195e6851d5029b78e9719","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T09:07:06Z","title_canon_sha256":"8c1efc837bbf5f9834c5b5e32c5325ab2e8e8d2c4ec874c85730982000bf6527"},"schema_version":"1.0","source":{"id":"1811.03821","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03821","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03821v3","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03821","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"MSINUROHKYAC","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MSINUROHKYACIIPR","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MSINUROH","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:189dd115048a3748767fe60c68fa88beeb58f6279ac8978a822ef21eda391a5d","target":"graph","created_at":"2026-05-17T23:56:29Z","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":"Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world applications. One solution is to make supervised learning robust with imperfectly labeled input. In this paper, we develop a distribution correction approach that allows deep neural networks to avoid overfitting imperfect training data. Specifically, we treat the noisy input as samples from an incorrect distribution, which will be automatically corrected dur","authors_text":"Chuanren Liu, Fangzhao Wu, Guangyi Lv, Jianhui Ma, Mingxiao An, Qi Liu, Yongzhou Chen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T09:07:06Z","title":"Skeptical Deep Learning with Distribution Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03821","kind":"arxiv","version":3},"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":"sha256:9e8c0d7ed378918248c62ac4ddb484a9c17fe6bcc45688ce0fac97853f3aee1d","target":"record","created_at":"2026-05-17T23:56:29Z","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":"ee1161250b9eb2d607b71379b2d3668f1548ae96066195e6851d5029b78e9719","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T09:07:06Z","title_canon_sha256":"8c1efc837bbf5f9834c5b5e32c5325ab2e8e8d2c4ec874c85730982000bf6527"},"schema_version":"1.0","source":{"id":"1811.03821","kind":"arxiv","version":3}},"canonical_sha256":"6490da45c756002421f13269e9fb38cf713f0e18bd09dd82f1300c3ac9acc79b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6490da45c756002421f13269e9fb38cf713f0e18bd09dd82f1300c3ac9acc79b","first_computed_at":"2026-05-17T23:56:29.226659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:29.226659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ckSq5ujCEjTxjdeYfjk3ZnZxINctcLN+bobLIY7iIpAk1mkKlrvTDpm8L2XhiH9pk1/i53R0N20BWt5owzkAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:29.227123Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03821","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e8c0d7ed378918248c62ac4ddb484a9c17fe6bcc45688ce0fac97853f3aee1d","sha256:189dd115048a3748767fe60c68fa88beeb58f6279ac8978a822ef21eda391a5d"],"state_sha256":"cecd8133591eee8b65c8ebab03b8c0d7033427301724f2f64ae7941588dab4ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TtC835d+aVkkhL5WlqUgnbV9vIvyJ9iQZQsgnw6qb2Oynzv/nrc2dDes0cHo/1ly+fe6xt/95LU3aAzl5vHBBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T00:27:10.149273Z","bundle_sha256":"e85e800c2145f0c4067e4cfefb15f01c209c66ff00ff74cb8eb03c7171eae74d"}}