{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QQ4NGASHKPR5VP7465HUEX3YSO","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":"3063c1b18c981c14534d3d364352b9c0ace6655bb59aedce4746ba979226f6f9","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-02T10:36:01Z","title_canon_sha256":"6cd2e10a5bfbdfdfc59c8eafb99acc90959ed99e2de8220b3abff21a553f1657"},"schema_version":"1.0","source":{"id":"2508.01306","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01306","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01306v1","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01306","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"QQ4NGASHKPR5","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"pith_short_16","alias_value":"QQ4NGASHKPR5VP74","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"pith_short_8","alias_value":"QQ4NGASH","created_at":"2026-07-05T11:47:37Z"}],"graph_snapshots":[{"event_id":"sha256:0e248a3c05aa485d942871025965ce6eaade1728e1787269a80db80f1e2b60b1","target":"graph","created_at":"2026-07-05T11:47:37Z","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/2508.01306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) are increasingly deployed across diverse domains, ensuring their safety has become a critical concern. In response, studies on jailbreak attacks have been actively growing. Existing approaches typically rely on iterative prompt engineering or semantic transformations of harmful instructions to evade detection. In this work, we introduce PUZZLED, a novel jailbreak method that leverages the LLM's reasoning capabilities. It masks keywords in a harmful instruction and presents them as word puzzles for the LLM to solve. We design three puzzle types-word search, anagr","authors_text":"Jaejin Lee, Yelim Ahn","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-02T10:36:01Z","title":"PUZZLED: Jailbreaking LLMs through Word-Based Puzzles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01306","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:d6e06133b6a536c334f7b6ce502119c9d5f95cfcd6706ac985695768066d8761","target":"record","created_at":"2026-07-05T11:47:37Z","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":"3063c1b18c981c14534d3d364352b9c0ace6655bb59aedce4746ba979226f6f9","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-02T10:36:01Z","title_canon_sha256":"6cd2e10a5bfbdfdfc59c8eafb99acc90959ed99e2de8220b3abff21a553f1657"},"schema_version":"1.0","source":{"id":"2508.01306","kind":"arxiv","version":1}},"canonical_sha256":"8438d3024753e3dabffcf74f425f78938ccea72f2c458ca6eba702832394f97c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8438d3024753e3dabffcf74f425f78938ccea72f2c458ca6eba702832394f97c","first_computed_at":"2026-07-05T11:47:37.047032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:37.047032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ACXFtuXxk3aXQGIbu8AIJGT04D7ariE7EKvAyJ/8YbG0FoERGcrtW7PNMTF1N1i3WwzSuMqYKXRfJKVkX5E6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:37.047531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01306","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6e06133b6a536c334f7b6ce502119c9d5f95cfcd6706ac985695768066d8761","sha256:0e248a3c05aa485d942871025965ce6eaade1728e1787269a80db80f1e2b60b1"],"state_sha256":"0895d010dcddbb13c8a4481cd81e5a2ba6e530cc7cc7164739c2a284149ee85b"}