OpenAI proposes pair-matched and post-control metrics to complement g-mean² for monitorability
AIOpenAI's Alignment Research Blog proposes two metrics to complement g-mean², a dataset-level score for how well monitors discriminate target behavior. A pair-matched metric compares models only on task instances supported for both, and a post-control integration metric estimates how much bad output remains after monitor-gated rejection.
Source details
OpenAI Alignment Research Blog · Melody Guan, Yuxiang Xie, Bowen Baker · alignment.openai.comPublished · added here
Original title: Beyond g-mean²: complementary metrics for monitorability