{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TT6X4SZI6A24HMQ5PZSCRMR3FU","short_pith_number":"pith:TT6X4SZI","canonical_record":{"source":{"id":"2103.12002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-22T16:52:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a8b57a259ebddca52f4209b81bbdaf076fce2f90fc7c67ec304c2b38bfa69e4e","abstract_canon_sha256":"f4474e3e6c4d20385f8a535eeb1aabc8caae31520221dfb8a923c975d4f2cd27"},"schema_version":"1.0"},"canonical_sha256":"9cfd7e4b28f035c3b21d7e6428b23b2d087ce9ac6426756fffb71b4bed4d1294","source":{"kind":"arxiv","id":"2103.12002","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12002","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12002v1","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12002","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"TT6X4SZI6A24","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"pith_short_16","alias_value":"TT6X4SZI6A24HMQ5","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"pith_short_8","alias_value":"TT6X4SZI","created_at":"2026-07-05T02:25:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TT6X4SZI6A24HMQ5PZSCRMR3FU","target":"record","payload":{"canonical_record":{"source":{"id":"2103.12002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-22T16:52:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a8b57a259ebddca52f4209b81bbdaf076fce2f90fc7c67ec304c2b38bfa69e4e","abstract_canon_sha256":"f4474e3e6c4d20385f8a535eeb1aabc8caae31520221dfb8a923c975d4f2cd27"},"schema_version":"1.0"},"canonical_sha256":"9cfd7e4b28f035c3b21d7e6428b23b2d087ce9ac6426756fffb71b4bed4d1294","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:14.154983Z","signature_b64":"mrTMiVKElmC1vZQmy9OqUq0aN2pOV2HOw0A5X7dHmKNk2/Czv2246IW/UdXuSoXZw+P/qVOApZ0L3FwV1E2DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cfd7e4b28f035c3b21d7e6428b23b2d087ce9ac6426756fffb71b4bed4d1294","last_reissued_at":"2026-07-05T02:25:14.154560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:14.154560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.12002","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":"2026-07-05T02:25:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IRuzV3X+rGgkRl1s5EeqxwsoVLXynWMY5dgTj9OksDnc4ZxZeOhSnzDwh6KuT/eZhLCSqr4CmXdu9g6Q3lbgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T00:08:10.955106Z"},"content_sha256":"25151bdc57202e7c3742d7ea51139fb81e83432505c54045ee3a4947c7f2ba43","schema_version":"1.0","event_id":"sha256:25151bdc57202e7c3742d7ea51139fb81e83432505c54045ee3a4947c7f2ba43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TT6X4SZI6A24HMQ5PZSCRMR3FU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Robustness of Monte Carlo Dropout Trained with Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Li Chen, Purvi Goel","submitted_at":"2021-03-22T16:52:42Z","abstract_excerpt":"The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels. Prior study has discovered that epistemic uncertainty techniques are robust when trained with noisy labels compared with neural networks without uncertainty estimation. They obtain prolonged memorization effect and better generalization performance under the adversarial setting of noisy labels. Due to its superior performance amongst other selected epistemic uncertainty methods under noisy labels, we focus on Monte Carlo Dropout (MCDropout) and investigate why"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12002","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.12002/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:25:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0mvwRenuLe6+7qNRBVs+6YI3nt0SK0I+inVcxIxA++sIbJ3Kab+e9oBIy/P/9yyZx4KLYPMAyGBWvNFIhKnLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T00:08:10.955608Z"},"content_sha256":"dc2f3c23eb12956355e574081bf390d22a67da9b2907874f45b28cf098a272ff","schema_version":"1.0","event_id":"sha256:dc2f3c23eb12956355e574081bf390d22a67da9b2907874f45b28cf098a272ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TT6X4SZI6A24HMQ5PZSCRMR3FU/bundle.json","state_url":"https://pith.science/pith/TT6X4SZI6A24HMQ5PZSCRMR3FU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TT6X4SZI6A24HMQ5PZSCRMR3FU/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":"2026-08-01T00:08:10Z","links":{"resolver":"https://pith.science/pith/TT6X4SZI6A24HMQ5PZSCRMR3FU","bundle":"https://pith.science/pith/TT6X4SZI6A24HMQ5PZSCRMR3FU/bundle.json","state":"https://pith.science/pith/TT6X4SZI6A24HMQ5PZSCRMR3FU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TT6X4SZI6A24HMQ5PZSCRMR3FU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TT6X4SZI6A24HMQ5PZSCRMR3FU","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":"f4474e3e6c4d20385f8a535eeb1aabc8caae31520221dfb8a923c975d4f2cd27","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-22T16:52:42Z","title_canon_sha256":"a8b57a259ebddca52f4209b81bbdaf076fce2f90fc7c67ec304c2b38bfa69e4e"},"schema_version":"1.0","source":{"id":"2103.12002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12002","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12002v1","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12002","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"TT6X4SZI6A24","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"pith_short_16","alias_value":"TT6X4SZI6A24HMQ5","created_at":"2026-07-05T02:25:14Z"},{"alias_kind":"pith_short_8","alias_value":"TT6X4SZI","created_at":"2026-07-05T02:25:14Z"}],"graph_snapshots":[{"event_id":"sha256:dc2f3c23eb12956355e574081bf390d22a67da9b2907874f45b28cf098a272ff","target":"graph","created_at":"2026-07-05T02:25:14Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.12002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels. Prior study has discovered that epistemic uncertainty techniques are robust when trained with noisy labels compared with neural networks without uncertainty estimation. They obtain prolonged memorization effect and better generalization performance under the adversarial setting of noisy labels. Due to its superior performance amongst other selected epistemic uncertainty methods under noisy labels, we focus on Monte Carlo Dropout (MCDropout) and investigate why","authors_text":"Li Chen, Purvi Goel","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-22T16:52:42Z","title":"On the Robustness of Monte Carlo Dropout Trained with Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12002","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":"sha256:25151bdc57202e7c3742d7ea51139fb81e83432505c54045ee3a4947c7f2ba43","target":"record","created_at":"2026-07-05T02:25:14Z","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":"f4474e3e6c4d20385f8a535eeb1aabc8caae31520221dfb8a923c975d4f2cd27","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-22T16:52:42Z","title_canon_sha256":"a8b57a259ebddca52f4209b81bbdaf076fce2f90fc7c67ec304c2b38bfa69e4e"},"schema_version":"1.0","source":{"id":"2103.12002","kind":"arxiv","version":1}},"canonical_sha256":"9cfd7e4b28f035c3b21d7e6428b23b2d087ce9ac6426756fffb71b4bed4d1294","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cfd7e4b28f035c3b21d7e6428b23b2d087ce9ac6426756fffb71b4bed4d1294","first_computed_at":"2026-07-05T02:25:14.154560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:25:14.154560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mrTMiVKElmC1vZQmy9OqUq0aN2pOV2HOw0A5X7dHmKNk2/Czv2246IW/UdXuSoXZw+P/qVOApZ0L3FwV1E2DAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:25:14.154983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25151bdc57202e7c3742d7ea51139fb81e83432505c54045ee3a4947c7f2ba43","sha256:dc2f3c23eb12956355e574081bf390d22a67da9b2907874f45b28cf098a272ff"],"state_sha256":"39e3754b85fd6c896e634ac8c24d40a53243ec7b8e1e186e497bd31777f99d2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuMY0o4OknsVt0HS1thNvoDmHOMTP0ooyPT2faGLWbQ7umDEbA8pUlhO1RwPoq4aBcb0wPL/tIhhB9I3mM5pCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T00:08:10.961344Z","bundle_sha256":"f7e2ba3a5a4a55e797ef04a7d665d3460a62450b19927c7b2808da7e7f69bcfa"}}