{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LF2DOOI5GWYHTRILVOYSNETQQN","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":"09fa9955fcfe95fd1390941d4d8e6f2d886eea82069d9bd633fdf3cb6529ca76","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T03:45:10Z","title_canon_sha256":"7d35204fc934013277a9c3601a371dd3def3b38301507a7fbc850b487ceccad0"},"schema_version":"1.0","source":{"id":"2607.28685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28685","created_at":"2026-08-03T00:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28685v1","created_at":"2026-08-03T00:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28685","created_at":"2026-08-03T00:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"LF2DOOI5GWYH","created_at":"2026-08-03T00:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"LF2DOOI5GWYHTRIL","created_at":"2026-08-03T00:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"LF2DOOI5","created_at":"2026-08-03T00:12:10Z"}],"graph_snapshots":[{"event_id":"sha256:a8ba3912e8ff5b8c6522deb9bb0360e66ee28eaa43e290185f37cd7c601e878a","target":"graph","created_at":"2026-08-03T00:12:10Z","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/2607.28685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm, AgentDojo) as measurements to be validated, running each under its official implementation and author-provided scorer on up to 22 models, with MMLU and GPQA measured by us under one protocol as a capability composite. The metric is the first problem. On any binary trace-judgment benchmark scored by $F_1$, an ``always positive'' policy attains $F_1 = 2\\pi/(1+\\pi)$; on R-Judge that is $0.690$, above five of the 21 models tha","authors_text":"Bowen Liu, Dingyan Shang, Xiao Han, Youting Wang, Yuan Tang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T03:45:10Z","title":"Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28685","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:ad67e999c6ba39f6086c73406ad3d9f348fca55fecefc9f69cbc59c5a354b322","target":"record","created_at":"2026-08-03T00:12:10Z","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":"09fa9955fcfe95fd1390941d4d8e6f2d886eea82069d9bd633fdf3cb6529ca76","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T03:45:10Z","title_canon_sha256":"7d35204fc934013277a9c3601a371dd3def3b38301507a7fbc850b487ceccad0"},"schema_version":"1.0","source":{"id":"2607.28685","kind":"arxiv","version":1}},"canonical_sha256":"597437391d35b079c50babb1269270836931879273532ee628e43931d5bc4f52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"597437391d35b079c50babb1269270836931879273532ee628e43931d5bc4f52","first_computed_at":"2026-08-03T00:12:10.577518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T00:12:10.577518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yaY1sG9ZCWU/IqadIchO4avkeVdeLYvlP6OOcLHZL91pk/n3sRqm5Q3Z7Jc69CyS2ChBhrqqDZUybl8A+ygACw==","signature_status":"signed_v1","signed_at":"2026-08-03T00:12:10.579711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.28685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad67e999c6ba39f6086c73406ad3d9f348fca55fecefc9f69cbc59c5a354b322","sha256:a8ba3912e8ff5b8c6522deb9bb0360e66ee28eaa43e290185f37cd7c601e878a"],"state_sha256":"7a3e0d00dd921fcc83f93f67f3f0cf1e41a17860da909623579e2f82b975306c"}