{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QUHUWX2WAFZUZU2BYL2OBXDLZ3","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":"9bf1298db3bd706ad1ec31e8376c06e623a1d974c2c26e3524326fa50c6e2e87","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-04T08:24:15Z","title_canon_sha256":"d93f47cbbed5c5771d1a82c13d5e8a7cf7e14cbb9a687fd9020c038f015bac47"},"schema_version":"1.0","source":{"id":"2410.03225","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03225","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03225v2","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03225","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"pith_short_12","alias_value":"QUHUWX2WAFZU","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"pith_short_16","alias_value":"QUHUWX2WAFZUZU2B","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"pith_short_8","alias_value":"QUHUWX2W","created_at":"2026-07-05T09:27:05Z"}],"graph_snapshots":[{"event_id":"sha256:d6d40a43734627af4d40930062ecdcb6f3c8d7b9c5105de897581ce4c109793a","target":"graph","created_at":"2026-07-05T09:27:05Z","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/2410.03225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity and the diverse strategies to simulate cyber-attacks. Despite growing interest and initial studies in automating penetration testing with generative agents, there remains a significant gap in the form of a comprehensive and standard framework for their evaluation and development. This paper introduces AutoPenBench, an open benchmark for evaluating generative a","authors_text":"Alexander Delsanto, Giuseppe Siracusano, Idilio Drago, Luca Gioacchini, Marco Mellia, Roberto Bifulco","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-04T08:24:15Z","title":"AutoPenBench: Benchmarking Generative Agents for Penetration Testing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03225","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":"sha256:6927d9a0ac55c41fe6b05b96d55f7ee768b258d1e16c334b0c639bd224be8af5","target":"record","created_at":"2026-07-05T09:27:05Z","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":"9bf1298db3bd706ad1ec31e8376c06e623a1d974c2c26e3524326fa50c6e2e87","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-04T08:24:15Z","title_canon_sha256":"d93f47cbbed5c5771d1a82c13d5e8a7cf7e14cbb9a687fd9020c038f015bac47"},"schema_version":"1.0","source":{"id":"2410.03225","kind":"arxiv","version":2}},"canonical_sha256":"850f4b5f5601734cd341c2f4e0dc6bcef07bf3bd1d1ecff55d96e4ecbc962a17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"850f4b5f5601734cd341c2f4e0dc6bcef07bf3bd1d1ecff55d96e4ecbc962a17","first_computed_at":"2026-07-05T09:27:05.424652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:05.424652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ghwlIPEwxtnEDiDpPO6jRF5/d5uTg19URm5tJBfel6yMNmNAnSv+HLXaiq4YVBc6WUv8UIZJckAU3cD8D7weBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:05.425127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03225","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6927d9a0ac55c41fe6b05b96d55f7ee768b258d1e16c334b0c639bd224be8af5","sha256:d6d40a43734627af4d40930062ecdcb6f3c8d7b9c5105de897581ce4c109793a"],"state_sha256":"87e861b681ae3ef86c51fab01f9d1e8d06d6f4374188d4210f483bdbb66fd26c"}