{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BDGGYWFIXH7UOE4TX4KR7HFWTQ","short_pith_number":"pith:BDGGYWFI","canonical_record":{"source":{"id":"1908.02160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T13:43:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbed263eb068aa44bf1fe9de35162926f065105bf61f47a9b000c3da2569d2ee","abstract_canon_sha256":"5463668a689eaacd67a54e73e83d2fae038a332416cc8679ebbebae7feed8a15"},"schema_version":"1.0"},"canonical_sha256":"08cc6c58a8b9ff471393bf151f9cb69c28b0c2c89ecd6a5202b61ff2589172ee","source":{"kind":"arxiv","id":"1908.02160","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02160","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02160v2","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02160","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"BDGGYWFIXH7U","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"BDGGYWFIXH7UOE4T","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"BDGGYWFI","created_at":"2026-07-04T23:58:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BDGGYWFIXH7UOE4TX4KR7HFWTQ","target":"record","payload":{"canonical_record":{"source":{"id":"1908.02160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T13:43:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbed263eb068aa44bf1fe9de35162926f065105bf61f47a9b000c3da2569d2ee","abstract_canon_sha256":"5463668a689eaacd67a54e73e83d2fae038a332416cc8679ebbebae7feed8a15"},"schema_version":"1.0"},"canonical_sha256":"08cc6c58a8b9ff471393bf151f9cb69c28b0c2c89ecd6a5202b61ff2589172ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:28.531419Z","signature_b64":"UZ+jqz6ez7CtEPumx1EfQea4uUDrjW0frxBhJ4HdysP26ZWwRE//Ahx0hyM87ZsQSkgP9U9Zo8n613rQ23sPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08cc6c58a8b9ff471393bf151f9cb69c28b0c2c89ecd6a5202b61ff2589172ee","last_reissued_at":"2026-07-04T23:58:28.530986Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:28.530986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.02160","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":"2026-07-04T23:58:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YDtQKV5JhAOV3hHzphgjgxPTsuJRnTe63ZzW6Vk/oICHEqnbZksllbTwgA810BdusVmG97L/77aUgOL2wkccAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:07:12.338168Z"},"content_sha256":"c5943968fc25a6a78118a91ea67d9d0e7af0a3bbea6cff60bd1d0bb06f6fe923","schema_version":"1.0","event_id":"sha256:c5943968fc25a6a78118a91ea67d9d0e7af0a3bbea6cff60bd1d0bb06f6fe923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BDGGYWFIXH7UOE4TX4KR7HFWTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Self-Learning From Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiangfan Han, Ping Luo, Xiaogang Wang","submitted_at":"2019-08-06T13:43:58Z","abstract_excerpt":"ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real noisy cases, this work presents a novel deep self-learning framework to train a robust network on the real noisy datasets without extra supervision. The proposed approach has several appealing benefits. (1) Different from most existing work, it does not rely on any assumption on the distribution of the noisy labels, making it robust to real noises. (2) It does"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02160","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.02160/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":"2026-07-04T23:58:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NkELtLuIqyXhi0ZBHZxTjwz2vgEJkllJE5s+DS8mblOe6O26PE7ve3+1kEP7K9XxbEpuIdWKoQH2tWgHhZKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:07:12.338671Z"},"content_sha256":"92aa979d080432533a0ee7008c1b95516cdf5001c80b68d4b2f0b3d7309f61e4","schema_version":"1.0","event_id":"sha256:92aa979d080432533a0ee7008c1b95516cdf5001c80b68d4b2f0b3d7309f61e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BDGGYWFIXH7UOE4TX4KR7HFWTQ/bundle.json","state_url":"https://pith.science/pith/BDGGYWFIXH7UOE4TX4KR7HFWTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BDGGYWFIXH7UOE4TX4KR7HFWTQ/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":"2026-08-16T20:07:12Z","links":{"resolver":"https://pith.science/pith/BDGGYWFIXH7UOE4TX4KR7HFWTQ","bundle":"https://pith.science/pith/BDGGYWFIXH7UOE4TX4KR7HFWTQ/bundle.json","state":"https://pith.science/pith/BDGGYWFIXH7UOE4TX4KR7HFWTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BDGGYWFIXH7UOE4TX4KR7HFWTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BDGGYWFIXH7UOE4TX4KR7HFWTQ","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":"5463668a689eaacd67a54e73e83d2fae038a332416cc8679ebbebae7feed8a15","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T13:43:58Z","title_canon_sha256":"fbed263eb068aa44bf1fe9de35162926f065105bf61f47a9b000c3da2569d2ee"},"schema_version":"1.0","source":{"id":"1908.02160","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02160","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02160v2","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02160","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"BDGGYWFIXH7U","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"BDGGYWFIXH7UOE4T","created_at":"2026-07-04T23:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"BDGGYWFI","created_at":"2026-07-04T23:58:28Z"}],"graph_snapshots":[{"event_id":"sha256:92aa979d080432533a0ee7008c1b95516cdf5001c80b68d4b2f0b3d7309f61e4","target":"graph","created_at":"2026-07-04T23:58:28Z","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/1908.02160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real noisy cases, this work presents a novel deep self-learning framework to train a robust network on the real noisy datasets without extra supervision. The proposed approach has several appealing benefits. (1) Different from most existing work, it does not rely on any assumption on the distribution of the noisy labels, making it robust to real noises. (2) It does","authors_text":"Jiangfan Han, Ping Luo, Xiaogang Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T13:43:58Z","title":"Deep Self-Learning From Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02160","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:c5943968fc25a6a78118a91ea67d9d0e7af0a3bbea6cff60bd1d0bb06f6fe923","target":"record","created_at":"2026-07-04T23:58:28Z","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":"5463668a689eaacd67a54e73e83d2fae038a332416cc8679ebbebae7feed8a15","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T13:43:58Z","title_canon_sha256":"fbed263eb068aa44bf1fe9de35162926f065105bf61f47a9b000c3da2569d2ee"},"schema_version":"1.0","source":{"id":"1908.02160","kind":"arxiv","version":2}},"canonical_sha256":"08cc6c58a8b9ff471393bf151f9cb69c28b0c2c89ecd6a5202b61ff2589172ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08cc6c58a8b9ff471393bf151f9cb69c28b0c2c89ecd6a5202b61ff2589172ee","first_computed_at":"2026-07-04T23:58:28.530986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:58:28.530986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UZ+jqz6ez7CtEPumx1EfQea4uUDrjW0frxBhJ4HdysP26ZWwRE//Ahx0hyM87ZsQSkgP9U9Zo8n613rQ23sPDw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:58:28.531419Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.02160","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5943968fc25a6a78118a91ea67d9d0e7af0a3bbea6cff60bd1d0bb06f6fe923","sha256:92aa979d080432533a0ee7008c1b95516cdf5001c80b68d4b2f0b3d7309f61e4"],"state_sha256":"222c5d64c3564d77936a56f1015b5b4f5eb0c963584798db0664df4b9bb7feae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lqY+0lEjdOp3sORcEQ5z9UOi+BYK5qjLINw8aVV8JJQ4+0KibsEM628u7O1ZLggwxboyS/rkM7QsdHHu+cNqAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:07:12.343265Z","bundle_sha256":"22042f83fecfe01ae2a10dfa90e3df49e147d633eb207235d4d09962319ff066"}}