- Score 83
- Official
An Operationalization of Opaque Serial Depth
arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverbalized serial cognition a model can perform, as a specific instantiation of the notion of opaque serial depth: roughly, th
So what
What this event means by reading role—not a longer recap.
- BuilderIf you ship latent-reasoning or full-bandwidth architectures, expect scrutiny of CoT monitorability and consider reporting NLS depth alongside it.
- ResearcherOffers a concrete, architecture-level metric for opaque serial depth that is insensitive to post-training and can be computed before training.
Score dimensions
Higher total means read first. Each bar is one factor we use to rank the system pool. How we score