{"schemaVersion":1,"target":{"type":"reading","id":"db48a40c0ec33d8e5ee2673cb8b21698f2e896a0d9ea079cb593ee2c94c892f5","revision":"4789de76-1119-46a4-8717-667cc7487964","revisionKind":"publication-id","title":"arXiv cs.AI: Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks","url":"https://escapemeridian.com/readings/arxiv-cs-ai-safety-or-just-capability-a-validity-audit-of-agent-db48a40c"},"source":{"type":"source","id":"https://arxiv.org/abs/2607.28685","revision":"93bc4e005ccdd82ee9b648e741e3f64031663742167445897b61167c3650aacf","revisionKind":"sha256-source-text","title":"Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks","url":"https://arxiv.org/abs/2607.28685"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}