{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T4FCKCBJNKPHRURSNDLEYTGDNJ","short_pith_number":"pith:T4FCKCBJ","schema_version":"1.0","canonical_sha256":"9f0a2508296a9e78d23268d64c4cc36a598a737dce436036a556b2dd7e381d46","source":{"kind":"arxiv","id":"2104.06574","version":1},"attestation_state":"computed","paper":{"title":"Joint Negative and Positive Learning for Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyounguk Shon, Junmo Kim, Juseung Yun, Youngdong Kim","submitted_at":"2021-04-14T01:32:25Z","abstract_excerpt":"Training of Convolutional Neural Networks (CNNs) with data with noisy labels is known to be a challenge. Based on the fact that directly providing the label to the data (Positive Learning; PL) has a risk of allowing CNNs to memorize the contaminated labels for the case of noisy data, the indirect learning approach that uses complementary labels (Negative Learning for Noisy Labels; NLNL) has proven to be highly effective in preventing overfitting to noisy data as it reduces the risk of providing faulty target. NLNL further employs a three-stage pipeline to improve convergence. As a result, filt"},"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":"2104.06574","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-14T01:32:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"59457df4ab499ab42f822fbd671e457b33058650b03f2728b3b6aa9859e8149e","abstract_canon_sha256":"c8790970e659746cd2688343ce98585c3be284bdf37ed6e6e3078eaf295d0f46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:07.156988Z","signature_b64":"kaxvJlarhCF9qkFS8CPC4mstB+txaVSmvnP2sCLwiYuVb81nqAPXPkGW5g7VhSxy15e5Ib0yYCz4VQN1+viCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f0a2508296a9e78d23268d64c4cc36a598a737dce436036a556b2dd7e381d46","last_reissued_at":"2026-07-05T02:32:07.156501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:07.156501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Negative and Positive Learning for Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyounguk Shon, Junmo Kim, Juseung Yun, Youngdong Kim","submitted_at":"2021-04-14T01:32:25Z","abstract_excerpt":"Training of Convolutional Neural Networks (CNNs) with data with noisy labels is known to be a challenge. Based on the fact that directly providing the label to the data (Positive Learning; PL) has a risk of allowing CNNs to memorize the contaminated labels for the case of noisy data, the indirect learning approach that uses complementary labels (Negative Learning for Noisy Labels; NLNL) has proven to be highly effective in preventing overfitting to noisy data as it reduces the risk of providing faulty target. NLNL further employs a three-stage pipeline to improve convergence. As a result, filt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06574","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/2104.06574/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":"2104.06574","created_at":"2026-07-05T02:32:07.156574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06574v1","created_at":"2026-07-05T02:32:07.156574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06574","created_at":"2026-07-05T02:32:07.156574+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4FCKCBJNKPH","created_at":"2026-07-05T02:32:07.156574+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4FCKCBJNKPHRURS","created_at":"2026-07-05T02:32:07.156574+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4FCKCBJ","created_at":"2026-07-05T02:32:07.156574+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/T4FCKCBJNKPHRURSNDLEYTGDNJ","json":"https://pith.science/pith/T4FCKCBJNKPHRURSNDLEYTGDNJ.json","graph_json":"https://pith.science/api/pith-number/T4FCKCBJNKPHRURSNDLEYTGDNJ/graph.json","events_json":"https://pith.science/api/pith-number/T4FCKCBJNKPHRURSNDLEYTGDNJ/events.json","paper":"https://pith.science/paper/T4FCKCBJ"},"agent_actions":{"view_html":"https://pith.science/pith/T4FCKCBJNKPHRURSNDLEYTGDNJ","download_json":"https://pith.science/pith/T4FCKCBJNKPHRURSNDLEYTGDNJ.json","view_paper":"https://pith.science/paper/T4FCKCBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06574&json=true","fetch_graph":"https://pith.science/api/pith-number/T4FCKCBJNKPHRURSNDLEYTGDNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/T4FCKCBJNKPHRURSNDLEYTGDNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4FCKCBJNKPHRURSNDLEYTGDNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4FCKCBJNKPHRURSNDLEYTGDNJ/action/storage_attestation","attest_author":"https://pith.science/pith/T4FCKCBJNKPHRURSNDLEYTGDNJ/action/author_attestation","sign_citation":"https://pith.science/pith/T4FCKCBJNKPHRURSNDLEYTGDNJ/action/citation_signature","submit_replication":"https://pith.science/pith/T4FCKCBJNKPHRURSNDLEYTGDNJ/action/replication_record"}},"created_at":"2026-07-05T02:32:07.156574+00:00","updated_at":"2026-07-05T02:32:07.156574+00:00"}