{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZY6AD72DYOUWR3YEP36VC2ZZ5W","short_pith_number":"pith:ZY6AD72D","canonical_record":{"source":{"id":"2203.06020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-11T15:40:57Z","cross_cats_sorted":[],"title_canon_sha256":"894d86783552aef0408509f412f8ac7ae232cb5b305c10d101aaedcd402c078e","abstract_canon_sha256":"0b04bf306a9a10c7bc63fa20a2f776dfed054ea266f084a12fe93f5ae57be87d"},"schema_version":"1.0"},"canonical_sha256":"ce3c01ff43c3a968ef047efd516b39ed855ba75dd80c53bc37bdfa3899da7303","source":{"kind":"arxiv","id":"2203.06020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06020","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06020v1","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06020","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZY6AD72DYOUW","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZY6AD72DYOUWR3YE","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZY6AD72D","created_at":"2026-07-05T04:04:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZY6AD72DYOUWR3YEP36VC2ZZ5W","target":"record","payload":{"canonical_record":{"source":{"id":"2203.06020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-11T15:40:57Z","cross_cats_sorted":[],"title_canon_sha256":"894d86783552aef0408509f412f8ac7ae232cb5b305c10d101aaedcd402c078e","abstract_canon_sha256":"0b04bf306a9a10c7bc63fa20a2f776dfed054ea266f084a12fe93f5ae57be87d"},"schema_version":"1.0"},"canonical_sha256":"ce3c01ff43c3a968ef047efd516b39ed855ba75dd80c53bc37bdfa3899da7303","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:12.022008Z","signature_b64":"AVP0N0QQi3yy+X1N/fXl8QdUBG+0IkZjj1eqnNhLHTB59XA9LxVX81sN9nwFZ/ONYG278knbC2lMN2ZKop49Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce3c01ff43c3a968ef047efd516b39ed855ba75dd80c53bc37bdfa3899da7303","last_reissued_at":"2026-07-05T04:04:12.021626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:12.021626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.06020","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:04:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m4nkPjBjnM0/Xd+buRBTAeiHm3AbzpzXSr4ULkNp00yH1WnjSAWavxmXaztjOnjLupZfoPb0Fjvpzg8SfUBHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T22:12:34.953023Z"},"content_sha256":"c5791854b17ff43b4d0eedbb6c4069ce056d43f524de7d44c119289def9d4ede","schema_version":"1.0","event_id":"sha256:c5791854b17ff43b4d0eedbb6c4069ce056d43f524de7d44c119289def9d4ede"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZY6AD72DYOUWR3YEP36VC2ZZ5W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Adversarial Training with Second-Order Statistics of Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gaojie Jin, Sven Schewe, Wei Huang, Xiaowei Huang, Xinping Yi","submitted_at":"2022-03-11T15:40:57Z","abstract_excerpt":"Adversarial training has been shown to be one of the most effective approaches to improve the robustness of deep neural networks. It is formalized as a min-max optimization over model weights and adversarial perturbations, where the weights can be optimized through gradient descent methods like SGD. In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through \\textbf{S}econd-Order \\textbf{S}tatistics \\textbf{O}ptimization (S$^2$O) with respect to the weights. By relaxing a common (but unrealistic) assumption of previous PAC-Bayesian f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06020","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/2203.06020/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:04:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6bw+1qIy0de0SgBQI6NILI4yl9yojkuwLtf0IdOSwV8I5Ki7sifHHvidSNWIQeboBV2Zll7Y4/xkhBC8jSRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T22:12:34.953416Z"},"content_sha256":"636a51af5a965cd8198fcc83bf920171a7025d727b8a56b0c9305665160eba00","schema_version":"1.0","event_id":"sha256:636a51af5a965cd8198fcc83bf920171a7025d727b8a56b0c9305665160eba00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZY6AD72DYOUWR3YEP36VC2ZZ5W/bundle.json","state_url":"https://pith.science/pith/ZY6AD72DYOUWR3YEP36VC2ZZ5W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZY6AD72DYOUWR3YEP36VC2ZZ5W/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-11T22:12:34Z","links":{"resolver":"https://pith.science/pith/ZY6AD72DYOUWR3YEP36VC2ZZ5W","bundle":"https://pith.science/pith/ZY6AD72DYOUWR3YEP36VC2ZZ5W/bundle.json","state":"https://pith.science/pith/ZY6AD72DYOUWR3YEP36VC2ZZ5W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZY6AD72DYOUWR3YEP36VC2ZZ5W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZY6AD72DYOUWR3YEP36VC2ZZ5W","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":"0b04bf306a9a10c7bc63fa20a2f776dfed054ea266f084a12fe93f5ae57be87d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-11T15:40:57Z","title_canon_sha256":"894d86783552aef0408509f412f8ac7ae232cb5b305c10d101aaedcd402c078e"},"schema_version":"1.0","source":{"id":"2203.06020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06020","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06020v1","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06020","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZY6AD72DYOUW","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZY6AD72DYOUWR3YE","created_at":"2026-07-05T04:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZY6AD72D","created_at":"2026-07-05T04:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:636a51af5a965cd8198fcc83bf920171a7025d727b8a56b0c9305665160eba00","target":"graph","created_at":"2026-07-05T04:04:12Z","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/2203.06020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial training has been shown to be one of the most effective approaches to improve the robustness of deep neural networks. It is formalized as a min-max optimization over model weights and adversarial perturbations, where the weights can be optimized through gradient descent methods like SGD. In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through \\textbf{S}econd-Order \\textbf{S}tatistics \\textbf{O}ptimization (S$^2$O) with respect to the weights. By relaxing a common (but unrealistic) assumption of previous PAC-Bayesian f","authors_text":"Gaojie Jin, Sven Schewe, Wei Huang, Xiaowei Huang, Xinping Yi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-11T15:40:57Z","title":"Enhancing Adversarial Training with Second-Order Statistics of Weights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06020","kind":"arxiv","version":1},"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:c5791854b17ff43b4d0eedbb6c4069ce056d43f524de7d44c119289def9d4ede","target":"record","created_at":"2026-07-05T04:04:12Z","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":"0b04bf306a9a10c7bc63fa20a2f776dfed054ea266f084a12fe93f5ae57be87d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-11T15:40:57Z","title_canon_sha256":"894d86783552aef0408509f412f8ac7ae232cb5b305c10d101aaedcd402c078e"},"schema_version":"1.0","source":{"id":"2203.06020","kind":"arxiv","version":1}},"canonical_sha256":"ce3c01ff43c3a968ef047efd516b39ed855ba75dd80c53bc37bdfa3899da7303","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce3c01ff43c3a968ef047efd516b39ed855ba75dd80c53bc37bdfa3899da7303","first_computed_at":"2026-07-05T04:04:12.021626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:12.021626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AVP0N0QQi3yy+X1N/fXl8QdUBG+0IkZjj1eqnNhLHTB59XA9LxVX81sN9nwFZ/ONYG278knbC2lMN2ZKop49Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:12.022008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5791854b17ff43b4d0eedbb6c4069ce056d43f524de7d44c119289def9d4ede","sha256:636a51af5a965cd8198fcc83bf920171a7025d727b8a56b0c9305665160eba00"],"state_sha256":"6774989b49f4884baa7640932743fd9f96583589aa0ff06a32924a1def2192d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IgOtAnvbcpK7cgiUmmIdkquxnLlao5xc4quYWlff8COMUSWWyEN0cTKg3nwTL+CZP0GwHPK7d0U75MEKPvs/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T22:12:34.956389Z","bundle_sha256":"3dfa3831ff6d0d35e307247700400987a85703d6d1b3fc8b409e61e01c895cab"}}