Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles

Excerpt

arXiv:2608.16190v1 Announce Type: cross Abstract: Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monitor at matched cost. They are built by minimising average pairwise correlation, and that paper's twelve monitors shared one base model, leaving open what supplies the diversity. We study 24 open-weight monitors spanning nine pretraining lineages and a 29x range of detection skill (pAUC at 10 percent