{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X4GCMOPER7XPWARESDC2EU2YKX","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":"24ed5f55a9b7d792532957a5868f7d8e43b42e4c488a3a28fba5b6c2cb405c00","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T18:59:02Z","title_canon_sha256":"3d42621ad67702b49bc7ee22ffad0966001c44f86a10025a9b111d06f6e41340"},"schema_version":"1.0","source":{"id":"2502.04322","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04322","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04322v3","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04322","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"pith_short_12","alias_value":"X4GCMOPER7XP","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"pith_short_16","alias_value":"X4GCMOPER7XPWARE","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"pith_short_8","alias_value":"X4GCMOPE","created_at":"2026-07-05T11:47:18Z"}],"graph_snapshots":[{"event_id":"sha256:3bf7487a6ff2441ad4bc9bbf85463ed4e433bd991f00e6982f035685b06a3ab4","target":"graph","created_at":"2026-07-05T11:47:18Z","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/2502.04322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite extensive safety alignment efforts, large language models (LLMs) remain vulnerable to jailbreak attacks that elicit harmful behavior. While existing studies predominantly focus on attack methods that require technical expertise, two critical questions remain underexplored: (1) Are jailbroken responses truly useful in enabling average users to carry out harmful actions? (2) Do safety vulnerabilities exist in more common, simple human-LLM interactions? In this paper, we demonstrate that LLM responses most effectively facilitate harmful actions when they are both actionable and informativ","authors_text":"Marzyeh Ghassemi, Narutatsu Ri, Yik Siu Chan, Yuxin Xiao","cross_cats":["cs.AI","cs.CL","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T18:59:02Z","title":"Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04322","kind":"arxiv","version":3},"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:fd9c61bf5d39fed361bf6033363ba3b1af96e6a77ef6140876fe3819efaab785","target":"record","created_at":"2026-07-05T11:47:18Z","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":"24ed5f55a9b7d792532957a5868f7d8e43b42e4c488a3a28fba5b6c2cb405c00","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T18:59:02Z","title_canon_sha256":"3d42621ad67702b49bc7ee22ffad0966001c44f86a10025a9b111d06f6e41340"},"schema_version":"1.0","source":{"id":"2502.04322","kind":"arxiv","version":3}},"canonical_sha256":"bf0c2639e48feefb022490c5a2535855c3cebe93edb9e7e3065ae0edabcbb02e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf0c2639e48feefb022490c5a2535855c3cebe93edb9e7e3065ae0edabcbb02e","first_computed_at":"2026-07-05T11:47:18.834925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:18.834925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0mzyYURUCMIfYwRHTSlKJYSpCF9cp4oOUoBdU3OdhI/PXxOdNUlu/mTt7i5ijDpet5pNypknDw6Oa5UZ8RHFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:18.835435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04322","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd9c61bf5d39fed361bf6033363ba3b1af96e6a77ef6140876fe3819efaab785","sha256:3bf7487a6ff2441ad4bc9bbf85463ed4e433bd991f00e6982f035685b06a3ab4"],"state_sha256":"4e80844ea740fd1c16eba55456285450b708ae17484a9c17688a86b20ef5d63e"}