SOURCE-LINKED INTELLIGENCE

Available Guardrails: Certifying Selective Prediction across ML Systems

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

A selective predictor acts as a safety gate: it returns an output only when the prediction appears sufficiently trustworthy. Deployments increasingly require this reliability to be certified at a target precision for every reporting unit of interest, such as a tool, policy label, or patient subgroup. The main difficulty is often not whether a granted certificate is valid, but whether finite calibration data can produce one at all. As the gate becomes safer or more fine-grained, some units may receive too little evidence to certify. We make this notion of availability computable through classic

Read original source ↗ Open in workspace

recordType

paper

region

Global