{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AHZF3RFSZ6BQCERNLYY66WEM7J","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":"0495108ba4e238d401e838f969d23cfdac9c55c6a311e00414517d41afba77fc","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-09T01:45:39Z","title_canon_sha256":"bfab6943f905ba59c3d64b99b323c50d1a90d8e27db06a2472067b95aa75c0b1"},"schema_version":"1.0","source":{"id":"2408.04811","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04811","created_at":"2026-07-05T10:38:35Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04811v4","created_at":"2026-07-05T10:38:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04811","created_at":"2026-07-05T10:38:35Z"},{"alias_kind":"pith_short_12","alias_value":"AHZF3RFSZ6BQ","created_at":"2026-07-05T10:38:35Z"},{"alias_kind":"pith_short_16","alias_value":"AHZF3RFSZ6BQCERN","created_at":"2026-07-05T10:38:35Z"},{"alias_kind":"pith_short_8","alias_value":"AHZF3RFS","created_at":"2026-07-05T10:38:35Z"}],"graph_snapshots":[{"event_id":"sha256:f10c47bc3dbdd16079c30557d936f45aab3d49ccdc1c3dc239eba929bb43fe08","target":"graph","created_at":"2026-07-05T10:38:35Z","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/2408.04811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their demonstrated valuable capabilities, state-of-the-art (SOTA) widely deployed large language models (LLMs) still have the potential to cause harm to society due to the ineffectiveness of their safety filters, which can be bypassed by prompt transformations called jailbreak attacks. Current approaches to LLM safety assessment, which employ datasets of templated prompts and benchmarking pipelines, fail to cover sufficiently large and diverse sets of jailbreak attacks, leading to the widespread deployment of unsafe LLMs. Recent research showed that novel jailbreak attacks could be der","authors_text":"Ananjan Nandi, Anna Goldie, Christopher D. Manning, Dan Jurafsky, Davide Ghilardi, Federico Bianchi, Gabriel Poesia, Moussa Koulako Bala Doumbouya","cross_cats":["cs.AI","cs.CL","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-09T01:45:39Z","title":"h4rm3l: A language for Composable Jailbreak Attack Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04811","kind":"arxiv","version":4},"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":"sha256:2c8265a551c2107136ac0c0568212ba498d61139bef040938a2c5e3e3fbb2d99","target":"record","created_at":"2026-07-05T10:38:35Z","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":"0495108ba4e238d401e838f969d23cfdac9c55c6a311e00414517d41afba77fc","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2024-08-09T01:45:39Z","title_canon_sha256":"bfab6943f905ba59c3d64b99b323c50d1a90d8e27db06a2472067b95aa75c0b1"},"schema_version":"1.0","source":{"id":"2408.04811","kind":"arxiv","version":4}},"canonical_sha256":"01f25dc4b2cf8301122d5e31ef588cfa69b68c5b852783a8e450acfa11c613ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01f25dc4b2cf8301122d5e31ef588cfa69b68c5b852783a8e450acfa11c613ff","first_computed_at":"2026-07-05T10:38:35.148066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:35.148066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QpidqN2jK4iO5FiQqKvYC0iT0dvpe3O1wCrnnzHCieeNqbznLyQgbKgbGhBaITAT/O/PHGO/BWqjDMc4VYwYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:35.148551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04811","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c8265a551c2107136ac0c0568212ba498d61139bef040938a2c5e3e3fbb2d99","sha256:f10c47bc3dbdd16079c30557d936f45aab3d49ccdc1c3dc239eba929bb43fe08"],"state_sha256":"62a1c19372619073d0155417653ddd73e8bb4bda1339488fb6a5a7da00c784f8"}