{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5BZ22R6TOXIFOLEGZ6A7J5D5O6","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":"1d99af3f78f6c3f4a395d0e06153603601f8e1f99eb9ea8346d4990fd3f8ba9a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-16T17:54:47Z","title_canon_sha256":"262f09037b27da4de42ad78b0a582198722f204708f1400995554b7a9b330a68"},"schema_version":"1.0","source":{"id":"2607.15263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15263","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15263v1","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15263","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"5BZ22R6TOXIF","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"5BZ22R6TOXIFOLEG","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"5BZ22R6T","created_at":"2026-07-17T01:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:16557a1787c096c3cb3a736b9c37b68c4265cea7cabb96189bbfd0486a2894f5","target":"graph","created_at":"2026-07-17T01:22:17Z","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/2607.15263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool call, telemetry query, and enrichment request consumes budget. We evaluate language-model security agents through this cost-success lens on offensive Cybench challenges and defensive Splunk BOTS v1 investigation challenges. Instead of reporting only best-case success, we compare models at fixed cost","authors_text":"Blaine Nelson, Paul Kassianik, Yaron Singer","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-16T17:54:47Z","title":"Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15263","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":"sha256:94fd07643139eea732b61a35cac8a18bd3837066e7036d10c34e4beeebdf1404","target":"record","created_at":"2026-07-17T01:22:17Z","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":"1d99af3f78f6c3f4a395d0e06153603601f8e1f99eb9ea8346d4990fd3f8ba9a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-16T17:54:47Z","title_canon_sha256":"262f09037b27da4de42ad78b0a582198722f204708f1400995554b7a9b330a68"},"schema_version":"1.0","source":{"id":"2607.15263","kind":"arxiv","version":1}},"canonical_sha256":"e873ad47d375d0572c86cf81f4f47d77b33f518802ade3c85be0d37b2861d632","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e873ad47d375d0572c86cf81f4f47d77b33f518802ade3c85be0d37b2861d632","first_computed_at":"2026-07-17T01:22:17.454759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:17.454759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/yUuiTqFfMvuzLo9YEAwBVhPTpOiHhhwWQPkPcpjM+zep4ZIxAGDq/ljVS0Ctu+rnNE5Ctmr+ymBVgarElxnBw==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:17.455584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94fd07643139eea732b61a35cac8a18bd3837066e7036d10c34e4beeebdf1404","sha256:16557a1787c096c3cb3a736b9c37b68c4265cea7cabb96189bbfd0486a2894f5"],"state_sha256":"55047a30654f8a24328cf45eaebdffa10bbd77afafe478226878fef597e0554c"}