{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QMXHK4PF3MOKQRQBJKPL5NIAIB","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":"c2efde5639ce331dab7594432c6564829a18542cdc54059a861ff8df3be29661","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T13:52:00Z","title_canon_sha256":"84a0f52cb3ce3a33b377765739c8217d6df66e8aa8d0988ff5727a4da1793de6"},"schema_version":"1.0","source":{"id":"2508.04451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04451","created_at":"2026-07-05T11:49:37Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04451v1","created_at":"2026-07-05T11:49:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04451","created_at":"2026-07-05T11:49:37Z"},{"alias_kind":"pith_short_12","alias_value":"QMXHK4PF3MOK","created_at":"2026-07-05T11:49:37Z"},{"alias_kind":"pith_short_16","alias_value":"QMXHK4PF3MOKQRQB","created_at":"2026-07-05T11:49:37Z"},{"alias_kind":"pith_short_8","alias_value":"QMXHK4PF","created_at":"2026-07-05T11:49:37Z"}],"graph_snapshots":[{"event_id":"sha256:5699ca252da30b72b09ee6546d0678c0ecd238fd0633719865c20d902f130dfc","target":"graph","created_at":"2026-07-05T11:49:37Z","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/2508.04451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Red teaming is critical for identifying vulnerabilities and building trust in current LLMs. However, current automated methods for Large Language Models (LLMs) rely on brittle prompt templates or single-turn attacks, failing to capture the complex, interactive nature of real-world adversarial dialogues. We propose a novel paradigm: training an AI to strategically `break' another AI. By formalizing red teaming as a Markov Decision Process (MDP) and employing a hierarchical Reinforcement Learning (RL) framework, we effectively address the inherent sparse reward and long-horizon challenges. Our g","authors_text":"Arunesh Sinha, Pradeep Varakantham, Roman Belaire","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T13:52:00Z","title":"Automatic LLM Red Teaming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04451","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":"sha256:0b78e6a845764985328639bda106fcc91f85bd1bb2149cd6383819d08d52de94","target":"record","created_at":"2026-07-05T11:49:37Z","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":"c2efde5639ce331dab7594432c6564829a18542cdc54059a861ff8df3be29661","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T13:52:00Z","title_canon_sha256":"84a0f52cb3ce3a33b377765739c8217d6df66e8aa8d0988ff5727a4da1793de6"},"schema_version":"1.0","source":{"id":"2508.04451","kind":"arxiv","version":1}},"canonical_sha256":"832e7571e5db1ca846014a9ebeb500405f0b77bf5c90c00b594e18658d510bfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"832e7571e5db1ca846014a9ebeb500405f0b77bf5c90c00b594e18658d510bfd","first_computed_at":"2026-07-05T11:49:37.022058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:37.022058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uUYBZugL1yn7yj97MdxQK0dUUFB1M1MLVJE1CvvSrahLwP+L+86WPtrMLy2cC3L3ZbxpcgIE+6GzquevRp1gAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:37.022423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b78e6a845764985328639bda106fcc91f85bd1bb2149cd6383819d08d52de94","sha256:5699ca252da30b72b09ee6546d0678c0ecd238fd0633719865c20d902f130dfc"],"state_sha256":"4f733d912d6151333fd6ee276197f24833416dc7b52e8cd2b01b514013c63c95"}