{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OTX7UZAXVAFMDBALAKKAHFC5K7","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":"0431aef15265c3399c0fa2e5d761ef63b8ebbc91d72df1b7b293cc5377c3ea7d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T18:00:04Z","title_canon_sha256":"2eabf3f20d2ddd440a03bcad6db5359f0725e6b0954f25ad6ed9b05eaf228728"},"schema_version":"1.0","source":{"id":"2507.02990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02990","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02990v1","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02990","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"OTX7UZAXVAFM","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"OTX7UZAXVAFMDBAL","created_at":"2026-07-05T11:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"OTX7UZAX","created_at":"2026-07-05T11:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:a170c039338532f08c5897f2c16f52f98a7cec0f1632b07e0e8069795c43759b","target":"graph","created_at":"2026-07-05T11:31:50Z","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/2507.02990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and creative forms of adversarial prompting, including manually generated test cases. In this work, we present two new test cases in mental health for (i) suicide and (ii) self-harm, using multi-step, prompt-level jailbreaking and bypass built-in content and safety filters. We show that user intent is disregarded, leading to the generation of detailed harmful co","authors_text":"Annika M Schoene, Cansu Canca","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T18:00:04Z","title":"`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02990","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":"sha256:12c893b4b86ddb884e00fba78f7c950298022cdac2fb61630779fd2e36b7e98f","target":"record","created_at":"2026-07-05T11:31:50Z","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":"0431aef15265c3399c0fa2e5d761ef63b8ebbc91d72df1b7b293cc5377c3ea7d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T18:00:04Z","title_canon_sha256":"2eabf3f20d2ddd440a03bcad6db5359f0725e6b0954f25ad6ed9b05eaf228728"},"schema_version":"1.0","source":{"id":"2507.02990","kind":"arxiv","version":1}},"canonical_sha256":"74effa6417a80ac1840b029403945d57d72d6a4f7e277cc7b6a3ed3513989c6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74effa6417a80ac1840b029403945d57d72d6a4f7e277cc7b6a3ed3513989c6f","first_computed_at":"2026-07-05T11:31:50.213137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:50.213137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aNjEFQCSrOTtWT1zyH42bPsGc6s203P6vepKk4MUV+zcH9jjXMkaEb5Qb6CsLTF2hc7omVsscniVJYpjmF9gDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:50.213657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12c893b4b86ddb884e00fba78f7c950298022cdac2fb61630779fd2e36b7e98f","sha256:a170c039338532f08c5897f2c16f52f98a7cec0f1632b07e0e8069795c43759b"],"state_sha256":"e2878274d6208a5617ccf16611fa5f6e1dfb82c2e8c83c76c59a22078b14707b"}