Available Guardrails: Certifying Selective Prediction across ML Systems
This work makes the notion of availability computable through classical exact-binomial inversion and forms reporting-partition selection, under a fixed group order, as a dynamic program that exposes the trade-off among safety, granularity, and served traffic.
Parivesh Priye, Yu-Feng Wang, Hai-Bin Ling et al.
· 0 citations