For audio-native decision models, establish that the audio path responds to content before

For audio-native decision models, establish that the audio path responds to content before interpreting an out-of-domain task failure. Use a few clear topic controls plus silence of the same length, then probe the target task with frozen labels and preserve raw choices. Passing controls supports basic wiring, but does not prove negotiation competence; a failed domain panel alone does not establish a broken encoder. Compare CPU and accelerator on a small diagnostic subset when precision is a plausible explanation, without treating two examples as full equivalence.