{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AH4SURWAXRIQFLXFDRZ67LOUDY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a733e4fb07092d4798d503cc345ecc96a0e48a1414c281c122486a17bae3c854","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-02T17:46:06Z","title_canon_sha256":"faa84f93415d05d275ee86af9ff3dee6e5ccb45d2010d8a13dc5f503ff861e0d"},"schema_version":"1.0","source":{"id":"1905.00877","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00877","created_at":"2026-07-05T00:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00877v6","created_at":"2026-07-05T00:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00877","created_at":"2026-07-05T00:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"AH4SURWAXRIQ","created_at":"2026-07-05T00:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"AH4SURWAXRIQFLXF","created_at":"2026-07-05T00:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"AH4SURWA","created_at":"2026-07-05T00:16:19Z"}],"graph_snapshots":[{"event_id":"sha256:7c56e07cd42fae0771ba5669f2cf9481e3c81654e710c688ddee683a622548a0","target":"graph","created_at":"2026-07-05T00:16:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1905.00877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bin Dong, Dinghuai Zhang, Tianyuan Zhang, Yiping Lu, Zhanxing Zhu","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-02T17:46:06Z","title":"You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00877","kind":"arxiv","version":6},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:139590ff83271985653ead1f12015a69f87bd783dc45443f98bafd51edc3c01f","target":"record","created_at":"2026-07-05T00:16:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a733e4fb07092d4798d503cc345ecc96a0e48a1414c281c122486a17bae3c854","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-02T17:46:06Z","title_canon_sha256":"faa84f93415d05d275ee86af9ff3dee6e5ccb45d2010d8a13dc5f503ff861e0d"},"schema_version":"1.0","source":{"id":"1905.00877","kind":"arxiv","version":6}},"canonical_sha256":"01f92a46c0bc5102aee51c73efadd41e2b99469adf96ba08ad6b97a2a2e0617d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01f92a46c0bc5102aee51c73efadd41e2b99469adf96ba08ad6b97a2a2e0617d","first_computed_at":"2026-07-05T00:16:19.992484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:16:19.992484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VbY44pQ/kMwpC31ERdK99GsbWQ4ddLJv+r7nzwoq8EJ4oYZrzKFucD/BMeF8x70NeRDRUeB3oi1Xn9wJVNBaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:16:19.992985Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.00877","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:139590ff83271985653ead1f12015a69f87bd783dc45443f98bafd51edc3c01f","sha256:7c56e07cd42fae0771ba5669f2cf9481e3c81654e710c688ddee683a622548a0"],"state_sha256":"c8d48e291fb3332d0a05fa54b54ffbb4b1a7e8df3a3810f21fd777799223818a"}