{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5JZ4ZJ6SUPKCUPHDGU4XTRAUAL","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":"08be702c3fc9e5375a6218721be13105f4cc0a087f4d9a007764f574b08c7c51","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T16:50:56Z","title_canon_sha256":"39c50ccc005fb201f67c2bf0c578f4d0131df32dd6be4640d80a8a2098a35af8"},"schema_version":"1.0","source":{"id":"2603.24511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.24511","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2603.24511v2","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24511","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"5JZ4ZJ6SUPKC","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"5JZ4ZJ6SUPKCUPHD","created_at":"2026-06-02T01:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"5JZ4ZJ6S","created_at":"2026-06-02T01:03:15Z"}],"graph_snapshots":[{"event_id":"sha256:c9b8426fc62ee6039eba20169529aac19d2bf0ab03fb8bf9d25eaa5342edae4b","target":"graph","created_at":"2026-06-02T01:03:15Z","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/2603.24511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations. We deploy frontier agents, such as Claude Code and Codex, in an autoresearch loop with access to a library of 30+ prior methods and an evaluation script with a fixed compute budget. We show this pipeline to be effective in jailbreaking OpenAI's GPT-OSS-Safeguard-20B and in prompt injections against Meta-SecAlign-70B, an adversarially robust model. For GPT-OSS-Safeguard, the best agent-discovered metho","authors_text":"Alexander Panfilov, Igor Shilov, Jonas Geiping, Maksym Andriushchenko, Peter Romov, Yves-Alexandre de Montjoye","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T16:50:56Z","title":"Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.24511","kind":"arxiv","version":2},"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:a26a91650f627408929351e750bf235df438add3ccf70ba6414a53d4f44da229","target":"record","created_at":"2026-06-02T01:03:15Z","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":"08be702c3fc9e5375a6218721be13105f4cc0a087f4d9a007764f574b08c7c51","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T16:50:56Z","title_canon_sha256":"39c50ccc005fb201f67c2bf0c578f4d0131df32dd6be4640d80a8a2098a35af8"},"schema_version":"1.0","source":{"id":"2603.24511","kind":"arxiv","version":2}},"canonical_sha256":"ea73cca7d2a3d42a3ce3353979c41402fdbdd2b43a779519764b47b3de0d38e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea73cca7d2a3d42a3ce3353979c41402fdbdd2b43a779519764b47b3de0d38e7","first_computed_at":"2026-06-02T01:03:15.958076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:15.958076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dkRxrMFTQh1blDcfT0XuqY2kLGjMODAofunkHLaVNTkkQHQsi0A2AeXGbK6fdYKj13pRTtZGWEyXsvWJ/o4iAg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:15.958689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.24511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26a91650f627408929351e750bf235df438add3ccf70ba6414a53d4f44da229","sha256:c9b8426fc62ee6039eba20169529aac19d2bf0ab03fb8bf9d25eaa5342edae4b"],"state_sha256":"7f052ec65188953d72744046edd9110b07d143b45873609aad3ba531e2ed73ef"}