{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:32D27Z2Z4UAB3XAUTQDDWR2PF2","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":"90b7a1245302486d1bfbbc61be9d4875428b15b36152429ec752231ca7e3f12d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T14:08:26Z","title_canon_sha256":"d7edfd2958604da819bad5bde1dfe3cd404657ed0fa21fa9c4c7a44f26065878"},"schema_version":"1.0","source":{"id":"2310.15851","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15851","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15851v2","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15851","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"32D27Z2Z4UAB","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"32D27Z2Z4UAB3XAU","created_at":"2026-07-05T07:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"32D27Z2Z","created_at":"2026-07-05T07:59:19Z"}],"graph_snapshots":[{"event_id":"sha256:ac6c3d85d6ce829edaca8f197205c2bbbd31a87ea59ddbe4e3ea987508f79f65","target":"graph","created_at":"2026-07-05T07:59:19Z","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/2310.15851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak attacks: safety training and safeguards. Safety training focuses on further training LLM to enhance its safety. On the other hand, safeguards involve implementing external models or filters to prevent harmful outputs. However, safety training has constraints in its ability to adapt to new attack types and often leads to a drop in model performance. Safeguards h","authors_text":"Fangkai Yang, Hongru Wang, Kam-Fai Wong, Liang Chen, Lu Wang, Pu Zhao, Qingwei Lin, Zezhong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T14:08:26Z","title":"Self-Guard: Empower the LLM to Safeguard Itself"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15851","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":"sha256:9a2b33d383f96300250b5e2ccbe4d2992405fa2b86125c50f6f80013ab4ead9a","target":"record","created_at":"2026-07-05T07:59:19Z","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":"90b7a1245302486d1bfbbc61be9d4875428b15b36152429ec752231ca7e3f12d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T14:08:26Z","title_canon_sha256":"d7edfd2958604da819bad5bde1dfe3cd404657ed0fa21fa9c4c7a44f26065878"},"schema_version":"1.0","source":{"id":"2310.15851","kind":"arxiv","version":2}},"canonical_sha256":"de87afe759e5001ddc149c063b474f2e80602659021b051cb0852a87ac2a6b37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de87afe759e5001ddc149c063b474f2e80602659021b051cb0852a87ac2a6b37","first_computed_at":"2026-07-05T07:59:19.127352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:19.127352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M3i2Vd8ZpxKnLVNUvsqVmgeLQ/19cRuD1x2NS7S5Ncledm4xVeL6QBbjvv3xAXzvQyf4ROwcm0fVJic7NZO0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:19.127794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15851","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a2b33d383f96300250b5e2ccbe4d2992405fa2b86125c50f6f80013ab4ead9a","sha256:ac6c3d85d6ce829edaca8f197205c2bbbd31a87ea59ddbe4e3ea987508f79f65"],"state_sha256":"9da2125d9416e339649abae07790856c3726c2ca70c85761af7457301dbd13db"}