{"schemaVersion":1,"target":{"type":"reading","id":"fa0c566c6206fca8c654f0872881a2eb6757e6be8e9072433b1c2ad2b93c1b29","revision":"92f093e1-5edc-4d9e-8b84-7f3923c250de","revisionKind":"publication-id","title":"Megan Li and coauthors argue safety benchmarks must connect to deployment","url":"https://escapemeridian.com/readings/megan-li-and-coauthors-argue-safety-benchmarks-must-connect-to-fa0c566c"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.18930","revision":"c6d34ae633780e1126cceaddfe1e532e43f79b4dbfe6f7ce1775afbe1adcd087","revisionKind":"sha256-source-text","title":"Between Rigor and Reality: How AI Safety Benchmark Developers Understand Benchmark Use and Maintenance","url":"https://arxiv.org/abs/2611.18930"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings to this reading. Shared topics are not citations. Other record types need an explicit reference adapter."}