{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DT4AINRYSCDA3QBRNDC544U3W7","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":"72bd10a1655aa2a6faa9b4aac679a3600aae4de991c067c98c3fbd32fc0cc414","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-13T16:59:43Z","title_canon_sha256":"b9650c94ed8711f58905836cdadb27caa51fce4ec6b5bd83e7c7826b5d57e994"},"schema_version":"1.0","source":{"id":"2406.09321","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09321","created_at":"2026-07-05T10:09:05Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09321v2","created_at":"2026-07-05T10:09:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09321","created_at":"2026-07-05T10:09:05Z"},{"alias_kind":"pith_short_12","alias_value":"DT4AINRYSCDA","created_at":"2026-07-05T10:09:05Z"},{"alias_kind":"pith_short_16","alias_value":"DT4AINRYSCDA3QBR","created_at":"2026-07-05T10:09:05Z"},{"alias_kind":"pith_short_8","alias_value":"DT4AINRY","created_at":"2026-07-05T10:09:05Z"}],"graph_snapshots":[{"event_id":"sha256:4225eb19173f5e0575eccb06f3eebf428f8766d2e0c133b741f1fb3b3fb9842c","target":"graph","created_at":"2026-07-05T10:09:05Z","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/2406.09321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Jailbreak attacks induce Large Language Models (LLMs) to generate harmful responses, posing severe misuse threats. Though research on jailbreak attacks and defenses is emerging, there is no consensus on evaluating jailbreaks, i.e., the methods to assess the harmfulness of an LLM's response are varied. Each approach has its own set of strengths and weaknesses, impacting their alignment with human values, as well as the time and financial cost. This diversity challenges researchers in choosing suitable evaluation methods and comparing different attacks and defenses. In this paper, we conduct a c","authors_text":"Anyu Wang, Delong Ran, Jingyi Zheng, Jinyuan Liu, Tianshuo Cong, Xinlei He, Yichen Gong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-13T16:59:43Z","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09321","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":"sha256:136421d666f1bed5029948f1a375ac49830b731aa4def4cca4847ce81304cf59","target":"record","created_at":"2026-07-05T10:09:05Z","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":"72bd10a1655aa2a6faa9b4aac679a3600aae4de991c067c98c3fbd32fc0cc414","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-13T16:59:43Z","title_canon_sha256":"b9650c94ed8711f58905836cdadb27caa51fce4ec6b5bd83e7c7826b5d57e994"},"schema_version":"1.0","source":{"id":"2406.09321","kind":"arxiv","version":2}},"canonical_sha256":"1cf804363890860dc03168c5de729bb7ed838c76a47d9e956d3c0987b1a165eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cf804363890860dc03168c5de729bb7ed838c76a47d9e956d3c0987b1a165eb","first_computed_at":"2026-07-05T10:09:05.180961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:05.180961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o/3T8xfoVoM+w8lGcmcy0ijnthx+amH/K9FROX8BxALxH0qM4F2Qf1A//lmjURL7YGnOkfpkzOVQJ4tcJFL1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:05.181556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09321","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:136421d666f1bed5029948f1a375ac49830b731aa4def4cca4847ce81304cf59","sha256:4225eb19173f5e0575eccb06f3eebf428f8766d2e0c133b741f1fb3b3fb9842c"],"state_sha256":"94035bb742cfed5c3c93de0bbd14d47f2797073df330adadc0043469729c0360"}