{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FYPGE3O2N4MIZOTXTPRTTXIHY5","short_pith_number":"pith:FYPGE3O2","canonical_record":{"source":{"id":"1908.07387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T06:22:37Z","cross_cats_sorted":[],"title_canon_sha256":"3847f05c564b4759b9d62b0ab5756d5c349baaa2ffb5ea6763774ab23f90582f","abstract_canon_sha256":"f7dba1efdbf3ac76710c4057d1e3e5607d65d83c73010e7afa0f69004210e60b"},"schema_version":"1.0"},"canonical_sha256":"2e1e626dda6f188cba779be339dd07c7748f952cb2c9512b90f44a5474f5d6ee","source":{"kind":"arxiv","id":"1908.07387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.07387","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"arxiv_version","alias_value":"1908.07387v1","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07387","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"pith_short_12","alias_value":"FYPGE3O2N4MI","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"pith_short_16","alias_value":"FYPGE3O2N4MIZOTX","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"pith_short_8","alias_value":"FYPGE3O2","created_at":"2026-07-04T23:58:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FYPGE3O2N4MIZOTXTPRTTXIHY5","target":"record","payload":{"canonical_record":{"source":{"id":"1908.07387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T06:22:37Z","cross_cats_sorted":[],"title_canon_sha256":"3847f05c564b4759b9d62b0ab5756d5c349baaa2ffb5ea6763774ab23f90582f","abstract_canon_sha256":"f7dba1efdbf3ac76710c4057d1e3e5607d65d83c73010e7afa0f69004210e60b"},"schema_version":"1.0"},"canonical_sha256":"2e1e626dda6f188cba779be339dd07c7748f952cb2c9512b90f44a5474f5d6ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:33.879560Z","signature_b64":"7F/KiWnPtMfkjkvjmiWSU1Q402KLxi7kV/5WnZCfz551AFQsfqHQ0XfJ8fc0IQJto9nQiHABxx6yAo+uhobPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e1e626dda6f188cba779be339dd07c7748f952cb2c9512b90f44a5474f5d6ee","last_reissued_at":"2026-07-04T23:58:33.879229Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:33.879229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.07387","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":"2026-07-04T23:58:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"96fbGbjHZC6S7hqdDfcrwd63vjg5gmDWBDv/xiUuED3bdlFf8bFjL2HRyjxMmedvbnDXtvQUhsYe6RxX+yOPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:37:57.938589Z"},"content_sha256":"7f6d4c57f32df0af3dde886364854b399c01f6d4bd6c55cffe750fadeafd173e","schema_version":"1.0","event_id":"sha256:7f6d4c57f32df0af3dde886364854b399c01f6d4bd6c55cffe750fadeafd173e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FYPGE3O2N4MIZOTXTPRTTXIHY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NLNL: Negative Learning for Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junho Yim, Junmo Kim, Juseung Yun, Youngdong Kim","submitted_at":"2019-08-19T06:22:37Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) provide excellent performance when used for image classification. The classical method of training CNNs is by labeling images in a supervised manner as in \"input image belongs to this label\" (Positive Learning; PL), which is a fast and accurate method if the labels are assigned correctly to all images. However, if inaccurate labels, or noisy labels, exist, training with PL will provide wrong information, thus severely degrading performance. To address this issue, we start with an indirect learning method called Negative Learning (NL), in which the CNNs are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07387","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/1908.07387/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":"2026-07-04T23:58:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZkCrju2GINtNfqIcD4TU2/YdoGC9eeNc4xH4AmSaqqqIELFn3WmlPgxRCkufwSbdb/DZgEOWuZAYLZHitbqWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:37:57.938961Z"},"content_sha256":"66af8d2c9ec60f3f3443f0a4cee2c4af9fa84bd7a80dfbffaf67085b43965d72","schema_version":"1.0","event_id":"sha256:66af8d2c9ec60f3f3443f0a4cee2c4af9fa84bd7a80dfbffaf67085b43965d72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/bundle.json","state_url":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/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":"2026-07-08T18:37:57Z","links":{"resolver":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5","bundle":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/bundle.json","state":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FYPGE3O2N4MIZOTXTPRTTXIHY5","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":"f7dba1efdbf3ac76710c4057d1e3e5607d65d83c73010e7afa0f69004210e60b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T06:22:37Z","title_canon_sha256":"3847f05c564b4759b9d62b0ab5756d5c349baaa2ffb5ea6763774ab23f90582f"},"schema_version":"1.0","source":{"id":"1908.07387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.07387","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"arxiv_version","alias_value":"1908.07387v1","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07387","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"pith_short_12","alias_value":"FYPGE3O2N4MI","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"pith_short_16","alias_value":"FYPGE3O2N4MIZOTX","created_at":"2026-07-04T23:58:33Z"},{"alias_kind":"pith_short_8","alias_value":"FYPGE3O2","created_at":"2026-07-04T23:58:33Z"}],"graph_snapshots":[{"event_id":"sha256:66af8d2c9ec60f3f3443f0a4cee2c4af9fa84bd7a80dfbffaf67085b43965d72","target":"graph","created_at":"2026-07-04T23:58:33Z","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/1908.07387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convolutional Neural Networks (CNNs) provide excellent performance when used for image classification. The classical method of training CNNs is by labeling images in a supervised manner as in \"input image belongs to this label\" (Positive Learning; PL), which is a fast and accurate method if the labels are assigned correctly to all images. However, if inaccurate labels, or noisy labels, exist, training with PL will provide wrong information, thus severely degrading performance. To address this issue, we start with an indirect learning method called Negative Learning (NL), in which the CNNs are ","authors_text":"Junho Yim, Junmo Kim, Juseung Yun, Youngdong Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T06:22:37Z","title":"NLNL: Negative Learning for Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07387","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":"sha256:7f6d4c57f32df0af3dde886364854b399c01f6d4bd6c55cffe750fadeafd173e","target":"record","created_at":"2026-07-04T23:58:33Z","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":"f7dba1efdbf3ac76710c4057d1e3e5607d65d83c73010e7afa0f69004210e60b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T06:22:37Z","title_canon_sha256":"3847f05c564b4759b9d62b0ab5756d5c349baaa2ffb5ea6763774ab23f90582f"},"schema_version":"1.0","source":{"id":"1908.07387","kind":"arxiv","version":1}},"canonical_sha256":"2e1e626dda6f188cba779be339dd07c7748f952cb2c9512b90f44a5474f5d6ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e1e626dda6f188cba779be339dd07c7748f952cb2c9512b90f44a5474f5d6ee","first_computed_at":"2026-07-04T23:58:33.879229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:58:33.879229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7F/KiWnPtMfkjkvjmiWSU1Q402KLxi7kV/5WnZCfz551AFQsfqHQ0XfJ8fc0IQJto9nQiHABxx6yAo+uhobPCg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:58:33.879560Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.07387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f6d4c57f32df0af3dde886364854b399c01f6d4bd6c55cffe750fadeafd173e","sha256:66af8d2c9ec60f3f3443f0a4cee2c4af9fa84bd7a80dfbffaf67085b43965d72"],"state_sha256":"6daaf2efabe5d8498816415a5779fe47a56d819730ad9c21e88de97d03632694"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvDIjYFftqSvWYEmVo8TODdjeEEiuuezAqjfVgP/qwcBjY6+byuyIiB8Io0sWiKgBp91iY4H5lavVMkA5SVhDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T18:37:57.940976Z","bundle_sha256":"9e7330449d739d721de57cb07134ca41db95ac1adf4ac83b70da3ed3b5f47297"}}