{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2AZN4T3IWWHUL2Z2HS2QUGTQK2","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":"eaa3461325f7ccca9410d7664fa9835a76907e85ffceb8fd6a5449e7761e75ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T14:49:26Z","title_canon_sha256":"07c4cdd18810533b08dc1b9e4481ad6fda860ff0b013ea4f7a340e9617993759"},"schema_version":"1.0","source":{"id":"2406.09187","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09187","created_at":"2026-05-21T01:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09187v3","created_at":"2026-05-21T01:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09187","created_at":"2026-05-21T01:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"2AZN4T3IWWHU","created_at":"2026-05-21T01:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"2AZN4T3IWWHUL2Z2","created_at":"2026-05-21T01:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"2AZN4T3I","created_at":"2026-05-21T01:52:24Z"}],"graph_snapshots":[{"event_id":"sha256:600d4af679fc76d7e80d230b556d5c283d543f61d4fddddf8638336f5308238d","target":"graph","created_at":"2026-05-21T01:52:24Z","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/2406.09187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether their actions satisfy given safety guard requests. Specifically, GuardAgent first analyzes the safety guard requests to generate a task plan, and then maps this plan into guardrail code for execution. By performing the code execution, GuardAgent can deterministically follow the safety guard request and safeguard target agents. In both steps, an LLM is utili","authors_text":"Bo Li, Carl Yang, Chulin Xie, Dawn Song, Han Xie, Jiawei Zhang, Junyuan Hong, Linzhi Zheng, Qinbin Li, Yanjie Li, Zhen Xiang, Zidi Xiong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T14:49:26Z","title":"GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09187","kind":"arxiv","version":3},"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:e0f44678492e177de5a91afbec086a4cb6d35206297a71738bdb1950fa6ecfed","target":"record","created_at":"2026-05-21T01:52:24Z","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":"eaa3461325f7ccca9410d7664fa9835a76907e85ffceb8fd6a5449e7761e75ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T14:49:26Z","title_canon_sha256":"07c4cdd18810533b08dc1b9e4481ad6fda860ff0b013ea4f7a340e9617993759"},"schema_version":"1.0","source":{"id":"2406.09187","kind":"arxiv","version":3}},"canonical_sha256":"d032de4f68b58f45eb3a3cb50a1a7056af15fe195c74d2401ade832940e11fe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d032de4f68b58f45eb3a3cb50a1a7056af15fe195c74d2401ade832940e11fe5","first_computed_at":"2026-05-21T01:52:24.267505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:52:24.267505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FP3Q5lHDjDkfWbT20arlx68re34RjLcIOIj60n6DF409Q7KQfiwfXbbffx3m3Bb4PY/OJBhHNN2ev6GkkcnwBg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:52:24.270754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09187","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0f44678492e177de5a91afbec086a4cb6d35206297a71738bdb1950fa6ecfed","sha256:600d4af679fc76d7e80d230b556d5c283d543f61d4fddddf8638336f5308238d"],"state_sha256":"4e989dea0900455626c8fc4ae68f6691bbb0f2cb42dbec00a867d334f112d8b3"}