Identity Is Not the Decision: Certifying Repairs for Frozen Communication Interfaces

Frozen communication interfaces can change task meaning without changing message width. Public probes may leave multiple consistent interfaces that permit the same repair, making full identity recovery spend queries on action-irrelevant distinctions. We show how to certify a repair from the shared acceptable-action set across probe-consistent interfaces. We characterize exact nonadaptive query cost by the smallest probe set separating every minimal interface group lacking a common repair, and give a noisy stopping rule with a finite-sample bound on unsafe certification. Across $225$ learned-agent pairs, anchor-consistent messages induce a common receiver action on $95.7$ percent of held-out states; uniform selection among them has a $2.2$ percent empirical upper bound on mismatch with the frozen receiver. On calibrated noisy channels, stopping uses fewer probes than target-symbol or full-interface identification and abstains when probes are uninformative. A complete automata catalog shows query savings against standard and advice-enhanced learning. On a message-dependent task, repair restores reference-level return, and released-protocol audits evaluate held-out workflows.