List your company

Misalignment Detection on Strategic deception Bloom behaviors (in-distribution)

0.817AUROC18-indicator ensemble
0.725480.749240.7730.79676Jun 23, 2026

Evaluation results

MethodLinks
18-indicator ensembleLayer=292026.060.817
18-indicator ensembleLayer=272026.060.792
RepE baselineLayer=292026.060.758
RepE baselineLayer=272026.060.729