{"node":{"id":19334,"uuid":"d2688b67-5b1a-4961-96d1-a7d9d581c24a","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","url":"https:\/\/xmt.pub\/index.php\/node\/19334","created":1788408024},"trust_level":"l0_aggregate","publisher":null,"source_url":"https:\/\/arxiv.org\/abs\/2609.01611","provenance":{"algorithm":"sha256(source_url|publisher_id|created)","stored":"bdf5bf3b6e74ea10782c6db46c3ba37b3f6470db444db81048976237cc95b833","expected":"bdf5bf3b6e74ea10782c6db46c3ba37b3f6470db444db81048976237cc95b833","status":"verified"}}