{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G7EHDF4XE3DDPIK5BR5CFPAO7U","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":"aa218e4dd6c56ddca314828648af30fdfcccb9802035fa8d4d01afe3166a3061","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-21T12:54:25Z","title_canon_sha256":"2e6f3e7471e02a5a3dc1f669063c6474110c692aa7b967d87e95a3f5dd9765a4"},"schema_version":"1.0","source":{"id":"2502.15427","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15427","created_at":"2026-07-05T10:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15427v1","created_at":"2026-07-05T10:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15427","created_at":"2026-07-05T10:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"G7EHDF4XE3DD","created_at":"2026-07-05T10:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"G7EHDF4XE3DDPIK5","created_at":"2026-07-05T10:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"G7EHDF4X","created_at":"2026-07-05T10:18:01Z"}],"graph_snapshots":[{"event_id":"sha256:5f5fd51a5c81ff8c3c3a98f6e7c5af462a43176321a00ca464d33ede908d8cbb","target":"graph","created_at":"2026-07-05T10:18:01Z","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/2502.15427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) become integrated into everyday applications, ensuring their robustness and security is increasingly critical. In particular, LLMs can be manipulated into unsafe behaviour by prompts known as jailbreaks. The variety of jailbreak styles is growing, necessitating the use of external defences known as guardrails. While many jailbreak defences have been proposed, not all defences are able to handle new out-of-distribution attacks due to the narrow segment of jailbreaks used to align them. Moreover, the lack of systematisation around defences has created significant ","authors_text":"Ambrish Rawat, Beat Buesser, Giandomenico Cornacchia, Giulio Zizzo, Kieran Fraser, Kush Varshney, Mark Purcell, Muhammad Zaid Hameed, Pin-Yu Chen, Prasanna Sattigeri","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-21T12:54:25Z","title":"Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15427","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":"sha256:84a7c17e1f1f3e24f411b6d94e9183d25e95799c4845dd1242caffaa04debe5c","target":"record","created_at":"2026-07-05T10:18:01Z","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":"aa218e4dd6c56ddca314828648af30fdfcccb9802035fa8d4d01afe3166a3061","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-21T12:54:25Z","title_canon_sha256":"2e6f3e7471e02a5a3dc1f669063c6474110c692aa7b967d87e95a3f5dd9765a4"},"schema_version":"1.0","source":{"id":"2502.15427","kind":"arxiv","version":1}},"canonical_sha256":"37c871979726c637a15d0c7a22bc0efd1c2a1ab434570d4f78bc1f73e45e9ca2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37c871979726c637a15d0c7a22bc0efd1c2a1ab434570d4f78bc1f73e45e9ca2","first_computed_at":"2026-07-05T10:18:01.733387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:01.733387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N6p4nxCtBdoHNS4bRkN4r4rC0/7qs2FivshkrgonLMsaLW0DzFPBXFBP7wqJYvsQ0Rk0oNiYDkFIcHmXM77/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:01.733869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15427","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84a7c17e1f1f3e24f411b6d94e9183d25e95799c4845dd1242caffaa04debe5c","sha256:5f5fd51a5c81ff8c3c3a98f6e7c5af462a43176321a00ca464d33ede908d8cbb"],"state_sha256":"21d5317c7f9c7d813c2e8a786b81c6f94d8624739961e91f213d19d9fe67f264"}