{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z63T3QIIMBUCRXNZQO2G5K2CX5","short_pith_number":"pith:Z63T3QII","schema_version":"1.0","canonical_sha256":"cfb73dc108606828ddb983b46eab42bf625c6a073d6971dc9bb5da2501b4f6b7","source":{"kind":"arxiv","id":"2105.14676","version":2},"attestation_state":"computed","paper":{"title":"NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Jingfeng Zhang, Lizhen Cui, Masashi Sugiyama, Tongliang Liu, Xilie Xu","submitted_at":"2021-05-31T02:17:51Z","abstract_excerpt":"Adversarial training (AT) formulated as the minimax optimization problem can effectively enhance the model's robustness against adversarial attacks. The existing AT methods mainly focused on manipulating the inner maximization for generating quality adversarial variants or manipulating the outer minimization for designing effective learning objectives. However, empirical results of AT always exhibit the robustness at odds with accuracy and the existence of the cross-over mixture problem, which motivates us to study some label randomness for benefiting the AT. First, we thoroughly investigate n"},"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":"2105.14676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-31T02:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"1ff8702c9919ec0a1f0391bfd316a902bdcd9191b828ac2906684874b11d9b04","abstract_canon_sha256":"fe4df8a8d81e5d1ccb9df1b9375fda307be0633bc41245cc3a9fffde72067f84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:56.146973Z","signature_b64":"CDd/Cx/unL0hQP90ta/Q6Osi8eyBJztNKeIioq1kf2gG8GHurD8Xxh6jtgJxVtN6/UIzHmzvVBVUbAeaLPn1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb73dc108606828ddb983b46eab42bf625c6a073d6971dc9bb5da2501b4f6b7","last_reissued_at":"2026-07-05T04:45:56.146497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:56.146497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Jingfeng Zhang, Lizhen Cui, Masashi Sugiyama, Tongliang Liu, Xilie Xu","submitted_at":"2021-05-31T02:17:51Z","abstract_excerpt":"Adversarial training (AT) formulated as the minimax optimization problem can effectively enhance the model's robustness against adversarial attacks. The existing AT methods mainly focused on manipulating the inner maximization for generating quality adversarial variants or manipulating the outer minimization for designing effective learning objectives. However, empirical results of AT always exhibit the robustness at odds with accuracy and the existence of the cross-over mixture problem, which motivates us to study some label randomness for benefiting the AT. First, we thoroughly investigate n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14676","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/2105.14676/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":"2105.14676","created_at":"2026-07-05T04:45:56.146556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14676v2","created_at":"2026-07-05T04:45:56.146556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14676","created_at":"2026-07-05T04:45:56.146556+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z63T3QIIMBUC","created_at":"2026-07-05T04:45:56.146556+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z63T3QIIMBUCRXNZ","created_at":"2026-07-05T04:45:56.146556+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z63T3QII","created_at":"2026-07-05T04:45:56.146556+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/Z63T3QIIMBUCRXNZQO2G5K2CX5","json":"https://pith.science/pith/Z63T3QIIMBUCRXNZQO2G5K2CX5.json","graph_json":"https://pith.science/api/pith-number/Z63T3QIIMBUCRXNZQO2G5K2CX5/graph.json","events_json":"https://pith.science/api/pith-number/Z63T3QIIMBUCRXNZQO2G5K2CX5/events.json","paper":"https://pith.science/paper/Z63T3QII"},"agent_actions":{"view_html":"https://pith.science/pith/Z63T3QIIMBUCRXNZQO2G5K2CX5","download_json":"https://pith.science/pith/Z63T3QIIMBUCRXNZQO2G5K2CX5.json","view_paper":"https://pith.science/paper/Z63T3QII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14676&json=true","fetch_graph":"https://pith.science/api/pith-number/Z63T3QIIMBUCRXNZQO2G5K2CX5/graph.json","fetch_events":"https://pith.science/api/pith-number/Z63T3QIIMBUCRXNZQO2G5K2CX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z63T3QIIMBUCRXNZQO2G5K2CX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z63T3QIIMBUCRXNZQO2G5K2CX5/action/storage_attestation","attest_author":"https://pith.science/pith/Z63T3QIIMBUCRXNZQO2G5K2CX5/action/author_attestation","sign_citation":"https://pith.science/pith/Z63T3QIIMBUCRXNZQO2G5K2CX5/action/citation_signature","submit_replication":"https://pith.science/pith/Z63T3QIIMBUCRXNZQO2G5K2CX5/action/replication_record"}},"created_at":"2026-07-05T04:45:56.146556+00:00","updated_at":"2026-07-05T04:45:56.146556+00:00"}