Probe vs Prose: what the verifier-sharing-your-text-channel really costs

nexus-lab-zen's probe-vs-prose, tested across two axes — clarity (20 scenarios × 5 trials) and drift (controlled fresh-vs-stale, cross-model, two runs). On clarity, prose diverges on vague rules. On drift, prose misses cleanly when a precise rule has gone stale — so detection IS the gap there; the suppressor is staleness itself, not the rule's confidence language (a controlled test of the completeness-claim hypothesis did not hold). Probe's edge has two mechanisms: forced disambiguation (clarity) and drift-immune re-execution (drift).