{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GLGLNX55XBTYX4UXZ5II3CDH7Y","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":"b636d2fd9611bc06a3fe18afa6a5b0125f0ee78f911c989ba7aa93753cdfa91b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T16:55:06Z","title_canon_sha256":"764509b81657611b4cdee1fb775dc02e556c45b5b7cefe3f035efedca3c2b47c"},"schema_version":"1.0","source":{"id":"2408.02632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02632","created_at":"2026-07-05T09:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02632v2","created_at":"2026-07-05T09:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02632","created_at":"2026-07-05T09:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"GLGLNX55XBTY","created_at":"2026-07-05T09:53:03Z"},{"alias_kind":"pith_short_16","alias_value":"GLGLNX55XBTYX4UX","created_at":"2026-07-05T09:53:03Z"},{"alias_kind":"pith_short_8","alias_value":"GLGLNX55","created_at":"2026-07-05T09:53:03Z"}],"graph_snapshots":[{"event_id":"sha256:fd97221418e819103ac43bdba6067b01300bc9295791269c01b5568eba9cb08c","target":"graph","created_at":"2026-07-05T09:53:03Z","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/2408.02632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to address these concerns involves training models to automatically generate adversarial prompts for red teaming. However, the evolving subtlety of vulnerabilities in LLMs challenges the effectiveness of current adversarial methods, which struggle to specifically target and explore the weaknesses of these models. To tackle these challenges, we introduce the $\\mathbf{S}\\text{elf-}\\mathbf{E}\\text{volving }\\mathbf{A}\\text{","authors_text":"Guogang Liao, Jingang Wang, Muxi Diao, Rumei Li, Shiyang Liu, Weiran Xu, Xunliang Cai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T16:55:06Z","title":"SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02632","kind":"arxiv","version":2},"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":"sha256:269abd278cb405ca445a16ed6e691bccb86c67b726b66796ebbb5d988ad24486","target":"record","created_at":"2026-07-05T09:53:03Z","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":"b636d2fd9611bc06a3fe18afa6a5b0125f0ee78f911c989ba7aa93753cdfa91b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T16:55:06Z","title_canon_sha256":"764509b81657611b4cdee1fb775dc02e556c45b5b7cefe3f035efedca3c2b47c"},"schema_version":"1.0","source":{"id":"2408.02632","kind":"arxiv","version":2}},"canonical_sha256":"32ccb6dfbdb8678bf297cf508d8867fe127420ef100195342e73012f87ac9aed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32ccb6dfbdb8678bf297cf508d8867fe127420ef100195342e73012f87ac9aed","first_computed_at":"2026-07-05T09:53:03.409390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:03.409390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lBL98BKEi4TCSV54mRnK99yWnOHLMl+TPdIMZjQTf9GvwgMNbzHuzo9aFngMK9deMiB8KoQ9O+TdnDOMBpCVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:03.409855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:269abd278cb405ca445a16ed6e691bccb86c67b726b66796ebbb5d988ad24486","sha256:fd97221418e819103ac43bdba6067b01300bc9295791269c01b5568eba9cb08c"],"state_sha256":"41d0a7bf5f1316406003d7c41e2e6ded5777a45ceb03a0d4fc105fe7bd65aff2"}