Conditional Validity for Adaptive Modality Acquisition: When the Policy Chooses Its Own Calibration Group

תקציר מקורי באנגליתarXiv:2608.15520v2 Announce Type: replace Abstract: A multimodal system may begin inference while holding only some of its inputs and may acquire the rest at a cost. With adaptive acquisition, the policy determines which inputs are ultimately observed, so we state risk control conditional on that terminal input pattern. Conditional calibration typically assumes that the grouping map is fixed independently of the calibration sample, a condition that policy-induced grouping does not satisfy. We characterize when pattern-conditional risk control remains valid and give two finite-sample constructions: threshold-free routing with calibration applied at the terminal pattern, and simultaneous validation of complete policy-pattern pairs, which lets calibration data select the deployed policy. A co