{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XAH345MIO3UQYALFZEENVWSHJO","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":"c9208c3a4974418675acc35858151a583cab81366a0165245460f1e8b51949d6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-06-02T16:25:26Z","title_canon_sha256":"a766dfd877a32de7f27e4ca889b244a0ff4cb2b2d998ebb95d6d26556e773b43"},"schema_version":"1.0","source":{"id":"2406.01637","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01637","created_at":"2026-07-05T10:41:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01637v2","created_at":"2026-07-05T10:41:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01637","created_at":"2026-07-05T10:41:12Z"},{"alias_kind":"pith_short_12","alias_value":"XAH345MIO3UQ","created_at":"2026-07-05T10:41:12Z"},{"alias_kind":"pith_short_16","alias_value":"XAH345MIO3UQYALF","created_at":"2026-07-05T10:41:12Z"},{"alias_kind":"pith_short_8","alias_value":"XAH345MI","created_at":"2026-07-05T10:41:12Z"}],"graph_snapshots":[{"event_id":"sha256:531f5dfe6ced5baa327d992c1053a77fb90a738d6c720b05bc2c45260c8bf9c9","target":"graph","created_at":"2026-07-05T10:41:12Z","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/2406.01637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when given a description of the vulnerability and toy capture-the-flag problems. However, these agents still perform poorly on real-world vulnerabilities that are unknown to the agent ahead of time (zero-day vulnerabilities).\n  In this work, we show that teams of LLM agents can exploit real-world, zero-day vulnerabilities. Prior agents struggle with exploring many different vulnerabilities and long-range planning when used al","authors_text":"Akul Gupta, Antony Kellermann, Daniel Kang, Philip Li, Richard Fang, Rohan Bindu, Yuxuan Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-06-02T16:25:26Z","title":"Teams of LLM Agents can Exploit Zero-Day Vulnerabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01637","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":"sha256:7e74a6b96b46a0a46edad9466809213b0a8dd48d73a598098b24db8ae6b07265","target":"record","created_at":"2026-07-05T10:41:12Z","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":"c9208c3a4974418675acc35858151a583cab81366a0165245460f1e8b51949d6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-06-02T16:25:26Z","title_canon_sha256":"a766dfd877a32de7f27e4ca889b244a0ff4cb2b2d998ebb95d6d26556e773b43"},"schema_version":"1.0","source":{"id":"2406.01637","kind":"arxiv","version":2}},"canonical_sha256":"b80fbe758876e90c0165c908dada474b9826daaad30659ef5f7da5985e407be3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b80fbe758876e90c0165c908dada474b9826daaad30659ef5f7da5985e407be3","first_computed_at":"2026-07-05T10:41:12.860150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:12.860150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vQ0Q/3smvQqcl6GcASKmiwKwLl9R5UADdukarpDzmgjK0vxiRRHOiMC8su8RcpFEWa288S2cGjzPyK9C+h8TDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:12.860638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01637","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e74a6b96b46a0a46edad9466809213b0a8dd48d73a598098b24db8ae6b07265","sha256:531f5dfe6ced5baa327d992c1053a77fb90a738d6c720b05bc2c45260c8bf9c9"],"state_sha256":"fb8b1a36252068333388def6c1c71d7e9837ea81ce66e3a4466482bb8b1daf7f"}