{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TAYLZTS2HDEA5WUPNPQMUGXW2G","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":"f4329a531136a528ef8765f52d5a770cd48e433dcd9c183eecffc9b9ce305c4e","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T21:52:50Z","title_canon_sha256":"e778842235cd32302f9df1858363a8af171ea86105ef0e83b4c072d0c2b9a9b7"},"schema_version":"1.0","source":{"id":"2508.02921","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02921","created_at":"2026-07-05T11:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02921v1","created_at":"2026-07-05T11:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02921","created_at":"2026-07-05T11:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"TAYLZTS2HDEA","created_at":"2026-07-05T11:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"TAYLZTS2HDEA5WUP","created_at":"2026-07-05T11:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"TAYLZTS2","created_at":"2026-07-05T11:48:32Z"}],"graph_snapshots":[{"event_id":"sha256:18793a4f5a2c901e2e8b0878fb15f8058d7c71c1834deee70f7e1068fb98a8af","target":"graph","created_at":"2026-07-05T11:48:32Z","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/2508.02921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce PentestJudge, a system for evaluating the operations of penetration testing agents. PentestJudge is a large language model (LLM)-as-judge with access to tools that allow it to consume arbitrary trajectories of agent states and tool call history to determine whether a security agent's actions meet certain operating criteria that would be impractical to evaluate programmatically. We develop rubrics that use a tree structure to hierarchically collapse the penetration testing task for a particular environment into smaller, simpler, and more manageable sub-tasks and criteria until each","authors_text":"Max Harley, Michael Kouremetis, Shane Caldwell, Vincent Abruzzo, Will Pearce","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T21:52:50Z","title":"PentestJudge: Judging Agent Behavior Against Operational Requirements"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02921","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":"sha256:7df5fcdb202c3e8632a6c16911f6f468560948e8257bfd7e54fc09ec140c9e36","target":"record","created_at":"2026-07-05T11:48:32Z","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":"f4329a531136a528ef8765f52d5a770cd48e433dcd9c183eecffc9b9ce305c4e","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T21:52:50Z","title_canon_sha256":"e778842235cd32302f9df1858363a8af171ea86105ef0e83b4c072d0c2b9a9b7"},"schema_version":"1.0","source":{"id":"2508.02921","kind":"arxiv","version":1}},"canonical_sha256":"9830bcce5a38c80eda8f6be0ca1af6d18b73d60240e40eca263b78ba685be7c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9830bcce5a38c80eda8f6be0ca1af6d18b73d60240e40eca263b78ba685be7c9","first_computed_at":"2026-07-05T11:48:32.914291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:32.914291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IYRZzWb5rdpvbdsGjcizt5Can/Vw8NHHhgS7PcmxjrZE/a7NLlaH+MJY9Lv1jOQndAuiR1hNlT6TqLfS7eI7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:32.914714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02921","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7df5fcdb202c3e8632a6c16911f6f468560948e8257bfd7e54fc09ec140c9e36","sha256:18793a4f5a2c901e2e8b0878fb15f8058d7c71c1834deee70f7e1068fb98a8af"],"state_sha256":"f8dfa564d58063bf8a7ba5cd761282cb897b4364f278c361ab82de5f69d58f47"}