{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RBJCMBBDJW46QUVEL3XIOHWEHP","short_pith_number":"pith:RBJCMBBD","schema_version":"1.0","canonical_sha256":"88522604234db9e852a45eee871ec43bdc7f1b4752a764852ffeaaca88f5dde9","source":{"kind":"arxiv","id":"2308.11443","version":1},"attestation_state":"computed","paper":{"title":"Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Xue, Jindong Gu, Ranjie Duan, Rong Zhang, Xiaochun Cao, Xiaofeng Mao, Xiaojun Jia, Yuefeng Chen","submitted_at":"2023-08-22T13:50:49Z","abstract_excerpt":"Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often suffers from Catastrophic Overfitting (CO), which results in poor robustness performance. Catastrophic Overfitting describes the phenomenon of a sudden and significant decrease in robust accuracy during the training of fast adversarial training. Many effective techniques have been developed to prevent Catastrophic Overfitting and improve the model robustness from different perspectives. However, these techniques ado"},"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":"2308.11443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-22T13:50:49Z","cross_cats_sorted":[],"title_canon_sha256":"215d190ceb27a97ba889f309215f959b460ad982dc865ca2eae5d6e0d622aee3","abstract_canon_sha256":"93a5d782e4a93c539fdf1029f43ff635c0ee24e1155cae71487841feee86a0c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:34.775710Z","signature_b64":"GCdC24NfdRecBs1EhzzvRTYzY99TfZ6VbZX5VXCWSpTQlJRcrCJVCXQYrBMCNak/7JOf3zmi1Oxoz4O1RJerDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88522604234db9e852a45eee871ec43bdc7f1b4752a764852ffeaaca88f5dde9","last_reissued_at":"2026-07-05T06:43:34.775268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:34.775268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Xue, Jindong Gu, Ranjie Duan, Rong Zhang, Xiaochun Cao, Xiaofeng Mao, Xiaojun Jia, Yuefeng Chen","submitted_at":"2023-08-22T13:50:49Z","abstract_excerpt":"Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often suffers from Catastrophic Overfitting (CO), which results in poor robustness performance. Catastrophic Overfitting describes the phenomenon of a sudden and significant decrease in robust accuracy during the training of fast adversarial training. Many effective techniques have been developed to prevent Catastrophic Overfitting and improve the model robustness from different perspectives. However, these techniques ado"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11443","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/2308.11443/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":"2308.11443","created_at":"2026-07-05T06:43:34.775325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11443v1","created_at":"2026-07-05T06:43:34.775325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11443","created_at":"2026-07-05T06:43:34.775325+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBJCMBBDJW46","created_at":"2026-07-05T06:43:34.775325+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBJCMBBDJW46QUVE","created_at":"2026-07-05T06:43:34.775325+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBJCMBBD","created_at":"2026-07-05T06:43:34.775325+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/RBJCMBBDJW46QUVEL3XIOHWEHP","json":"https://pith.science/pith/RBJCMBBDJW46QUVEL3XIOHWEHP.json","graph_json":"https://pith.science/api/pith-number/RBJCMBBDJW46QUVEL3XIOHWEHP/graph.json","events_json":"https://pith.science/api/pith-number/RBJCMBBDJW46QUVEL3XIOHWEHP/events.json","paper":"https://pith.science/paper/RBJCMBBD"},"agent_actions":{"view_html":"https://pith.science/pith/RBJCMBBDJW46QUVEL3XIOHWEHP","download_json":"https://pith.science/pith/RBJCMBBDJW46QUVEL3XIOHWEHP.json","view_paper":"https://pith.science/paper/RBJCMBBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11443&json=true","fetch_graph":"https://pith.science/api/pith-number/RBJCMBBDJW46QUVEL3XIOHWEHP/graph.json","fetch_events":"https://pith.science/api/pith-number/RBJCMBBDJW46QUVEL3XIOHWEHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBJCMBBDJW46QUVEL3XIOHWEHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBJCMBBDJW46QUVEL3XIOHWEHP/action/storage_attestation","attest_author":"https://pith.science/pith/RBJCMBBDJW46QUVEL3XIOHWEHP/action/author_attestation","sign_citation":"https://pith.science/pith/RBJCMBBDJW46QUVEL3XIOHWEHP/action/citation_signature","submit_replication":"https://pith.science/pith/RBJCMBBDJW46QUVEL3XIOHWEHP/action/replication_record"}},"created_at":"2026-07-05T06:43:34.775325+00:00","updated_at":"2026-07-05T06:43:34.775325+00:00"}