{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HVN2PGCTYEELDM2M2KJEFRZO2J","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":"06cafac2c3bab76083553d0462ab2fac636a5fa941f8b97bccb97b5f3e45b009","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-21T14:47:54Z","title_canon_sha256":"a5abbd643824e6584b22ec42d2657f2a237097b92110d765cb2b8dffd37d9eb8"},"schema_version":"1.0","source":{"id":"2605.22568","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22568","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22568v1","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22568","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"HVN2PGCTYEEL","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"HVN2PGCTYEELDM2M","created_at":"2026-05-22T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"HVN2PGCT","created_at":"2026-05-22T01:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:8d52dc9a4fbc00835a56a33e5e3f69fb8e7d7ca17ee28ba87d174c1d586f21b1","target":"graph","created_at":"2026-05-22T01:04:57Z","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/2605.22568/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then outline practical directions toward building more robust and trustworthy evaluation frameworks.","authors_text":"Ahmad-Reza Sadeghi, Chris Hicks, Konrad Rieck, Sahar Abdelnabi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-21T14:47:54Z","title":"Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22568","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":"sha256:77795809bd340aebd7d02f5b5aa32b43b1a936b47d52f562fa3f6eae7520064d","target":"record","created_at":"2026-05-22T01:04:57Z","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":"06cafac2c3bab76083553d0462ab2fac636a5fa941f8b97bccb97b5f3e45b009","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-21T14:47:54Z","title_canon_sha256":"a5abbd643824e6584b22ec42d2657f2a237097b92110d765cb2b8dffd37d9eb8"},"schema_version":"1.0","source":{"id":"2605.22568","kind":"arxiv","version":1}},"canonical_sha256":"3d5ba79853c108b1b34cd29242c72ed275de49f9f01442be4cf6566095a1316c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d5ba79853c108b1b34cd29242c72ed275de49f9f01442be4cf6566095a1316c","first_computed_at":"2026-05-22T01:04:57.959473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:57.959473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/HV0eNtA7G15749qYkIhgTwilwJZ3zB5koX8B14vJuTYEDaW6UBezubK5DbcOA7NXxYX31TGtllnl3JvXfhRDg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:57.960239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22568","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77795809bd340aebd7d02f5b5aa32b43b1a936b47d52f562fa3f6eae7520064d","sha256:8d52dc9a4fbc00835a56a33e5e3f69fb8e7d7ca17ee28ba87d174c1d586f21b1"],"state_sha256":"f38df9ed074fe5f349c6941f0b7fc5bdd86ab88d38ce7457de4cb8ca2e80740c"}