Clean Sheets and Checkpoints: Evidence Complexity for Certifying Sequential Agent Risk
arXiv:2610.39124v1 Announce Type: cross Abstract: Dangerous-capability evaluations often test an AI agent from prepared states at ordered milestones. A clean sheet records no successes. What it certifies about a campaign of $B$ attempts depends on what a failed attempt erases. We model the task as a chain of $k$ milestones divided into checkpoint segments and ask how many zero audit responses certify, at level $\alpha$, a completion probability of at most $\epsilon$. For segments chosen before…