{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AH4SURWAXRIQFLXFDRZ67LOUDY","short_pith_number":"pith:AH4SURWA","schema_version":"1.0","canonical_sha256":"01f92a46c0bc5102aee51c73efadd41e2b99469adf96ba08ad6b97a2a2e0617d","source":{"kind":"arxiv","id":"1905.00877","version":6},"attestation_state":"computed","paper":{"title":"You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Bin Dong, Dinghuai Zhang, Tianyuan Zhang, Yiping Lu, Zhanxing Zhu","submitted_at":"2019-05-02T17:46:06Z","abstract_excerpt":"Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnerable to adversarial perturbations, which raised a serious robustness issue of deep networks. Adversarial training, typically formulated as a robust optimization problem, is an effective way of improving the robustness of deep networks. A major drawback of existing adversarial training algorithms is the computational overhead of the generation of adversarial examples, typically far greater than that of the network trai"},"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":"1905.00877","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-02T17:46:06Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"faa84f93415d05d275ee86af9ff3dee6e5ccb45d2010d8a13dc5f503ff861e0d","abstract_canon_sha256":"a733e4fb07092d4798d503cc345ecc96a0e48a1414c281c122486a17bae3c854"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:19.992985Z","signature_b64":"VbY44pQ/kMwpC31ERdK99GsbWQ4ddLJv+r7nzwoq8EJ4oYZrzKFucD/BMeF8x70NeRDRUeB3oi1Xn9wJVNBaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01f92a46c0bc5102aee51c73efadd41e2b99469adf96ba08ad6b97a2a2e0617d","last_reissued_at":"2026-07-05T00:16:19.992484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:19.992484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Bin Dong, Dinghuai Zhang, Tianyuan Zhang, Yiping Lu, Zhanxing Zhu","submitted_at":"2019-05-02T17:46:06Z","abstract_excerpt":"Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnerable to adversarial perturbations, which raised a serious robustness issue of deep networks. Adversarial training, typically formulated as a robust optimization problem, is an effective way of improving the robustness of deep networks. A major drawback of existing adversarial training algorithms is the computational overhead of the generation of adversarial examples, typically far greater than that of the network trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00877","kind":"arxiv","version":6},"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/1905.00877/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":"1905.00877","created_at":"2026-07-05T00:16:19.992552+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.00877v6","created_at":"2026-07-05T00:16:19.992552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00877","created_at":"2026-07-05T00:16:19.992552+00:00"},{"alias_kind":"pith_short_12","alias_value":"AH4SURWAXRIQ","created_at":"2026-07-05T00:16:19.992552+00:00"},{"alias_kind":"pith_short_16","alias_value":"AH4SURWAXRIQFLXF","created_at":"2026-07-05T00:16:19.992552+00:00"},{"alias_kind":"pith_short_8","alias_value":"AH4SURWA","created_at":"2026-07-05T00:16:19.992552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00738","citing_title":"SORA: Free Second-Order Attacks in Fast Adversarial Training","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY","json":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY.json","graph_json":"https://pith.science/api/pith-number/AH4SURWAXRIQFLXFDRZ67LOUDY/graph.json","events_json":"https://pith.science/api/pith-number/AH4SURWAXRIQFLXFDRZ67LOUDY/events.json","paper":"https://pith.science/paper/AH4SURWA"},"agent_actions":{"view_html":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY","download_json":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY.json","view_paper":"https://pith.science/paper/AH4SURWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.00877&json=true","fetch_graph":"https://pith.science/api/pith-number/AH4SURWAXRIQFLXFDRZ67LOUDY/graph.json","fetch_events":"https://pith.science/api/pith-number/AH4SURWAXRIQFLXFDRZ67LOUDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY/action/storage_attestation","attest_author":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY/action/author_attestation","sign_citation":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY/action/citation_signature","submit_replication":"https://pith.science/pith/AH4SURWAXRIQFLXFDRZ67LOUDY/action/replication_record"}},"created_at":"2026-07-05T00:16:19.992552+00:00","updated_at":"2026-07-05T00:16:19.992552+00:00"}