{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FYPGE3O2N4MIZOTXTPRTTXIHY5","short_pith_number":"pith:FYPGE3O2","schema_version":"1.0","canonical_sha256":"2e1e626dda6f188cba779be339dd07c7748f952cb2c9512b90f44a5474f5d6ee","source":{"kind":"arxiv","id":"1908.07387","version":1},"attestation_state":"computed","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1908.07387","created_at":"2026-07-04T23:58:33.879278+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07387v1","created_at":"2026-07-04T23:58:33.879278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07387","created_at":"2026-07-04T23:58:33.879278+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYPGE3O2N4MI","created_at":"2026-07-04T23:58:33.879278+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYPGE3O2N4MIZOTX","created_at":"2026-07-04T23:58:33.879278+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYPGE3O2","created_at":"2026-07-04T23:58:33.879278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5","json":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5.json","graph_json":"https://pith.science/api/pith-number/FYPGE3O2N4MIZOTXTPRTTXIHY5/graph.json","events_json":"https://pith.science/api/pith-number/FYPGE3O2N4MIZOTXTPRTTXIHY5/events.json","paper":"https://pith.science/paper/FYPGE3O2"},"agent_actions":{"view_html":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5","download_json":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5.json","view_paper":"https://pith.science/paper/FYPGE3O2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07387&json=true","fetch_graph":"https://pith.science/api/pith-number/FYPGE3O2N4MIZOTXTPRTTXIHY5/graph.json","fetch_events":"https://pith.science/api/pith-number/FYPGE3O2N4MIZOTXTPRTTXIHY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/action/storage_attestation","attest_author":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/action/author_attestation","sign_citation":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/action/citation_signature","submit_replication":"https://pith.science/pith/FYPGE3O2N4MIZOTXTPRTTXIHY5/action/replication_record"}},"created_at":"2026-07-04T23:58:33.879278+00:00","updated_at":"2026-07-04T23:58:33.879278+00:00"}