{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QYNPNYIZNDJOXPTL5SBBCQD5TL","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":"58a7bcdbba1ec2d48df6220f9f2682f95038f5f4d069fd353a3eb03624135634","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T15:14:35Z","title_canon_sha256":"176d4e36c52cc1f4cb4dee27fbd5478d9f2eb5d0512fe4b6d4d40f7c984da01c"},"schema_version":"1.0","source":{"id":"2406.12702","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12702","created_at":"2026-07-05T08:35:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12702v2","created_at":"2026-07-05T08:35:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12702","created_at":"2026-07-05T08:35:04Z"},{"alias_kind":"pith_short_12","alias_value":"QYNPNYIZNDJO","created_at":"2026-07-05T08:35:04Z"},{"alias_kind":"pith_short_16","alias_value":"QYNPNYIZNDJOXPTL","created_at":"2026-07-05T08:35:04Z"},{"alias_kind":"pith_short_8","alias_value":"QYNPNYIZ","created_at":"2026-07-05T08:35:04Z"}],"graph_snapshots":[{"event_id":"sha256:73da3a16a46a0c2f5bf75981b67d66257a1386054e3930ce6c85529907c20f54","target":"graph","created_at":"2026-07-05T08:35:04Z","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/2406.12702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce two paradoxes concerning jailbreak of foundation models: First, it is impossible to construct a perfect jailbreak classifier, and second, a weaker model cannot consistently detect whether a stronger (in a pareto-dominant sense) model is jailbroken or not. We provide formal proofs for these paradoxes and a short case study on Llama and GPT4-o to demonstrate this. We discuss broader theoretical and practical repercussions of these results.","authors_text":"Abhinav Rao, Monojit Choudhury, Somak Aditya","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T15:14:35Z","title":"[WIP] Jailbreak Paradox: The Achilles' Heel of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12702","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":"sha256:884315cea5a87d5ea85751bd5c6fdea680afd70440678211f7bb3562307f1cbf","target":"record","created_at":"2026-07-05T08:35:04Z","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":"58a7bcdbba1ec2d48df6220f9f2682f95038f5f4d069fd353a3eb03624135634","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T15:14:35Z","title_canon_sha256":"176d4e36c52cc1f4cb4dee27fbd5478d9f2eb5d0512fe4b6d4d40f7c984da01c"},"schema_version":"1.0","source":{"id":"2406.12702","kind":"arxiv","version":2}},"canonical_sha256":"861af6e11968d2ebbe6bec8211407d9afcaf4eb163a38460f9475bd069fe3f6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"861af6e11968d2ebbe6bec8211407d9afcaf4eb163a38460f9475bd069fe3f6b","first_computed_at":"2026-07-05T08:35:04.392895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:04.392895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TjU61wI6lnTK+s9Gibu1q4XMn+SZGTioRxj2StLq51KlzAf0X/WJoZKm+Gp5c1FsjfiM5BcPBMZEqg2hXgUEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:04.393305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12702","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:884315cea5a87d5ea85751bd5c6fdea680afd70440678211f7bb3562307f1cbf","sha256:73da3a16a46a0c2f5bf75981b67d66257a1386054e3930ce6c85529907c20f54"],"state_sha256":"3536c4a618e4d66a27cf4f27415f2c22347a7177883791ce983fd50fcd8ec7a2"}