collision entropy

Why similarity-based AI text detection has a hard accuracy limit

A collision-entropy floor for watermark and retrieval detection sounds abstract, but the math is refreshingly direct. The core claim is that any similarity-based detector, no matter how clever, cannot escape a false-positive floor set by the raw text's own collision entropy. That is a powerful, clean result. The bridge to Silva's work is the boldest move here. If the matching-game formalization holds, it unifies two frameworks that were previously separate. That is worth scrutiny.