Unrelated, but:

> The dominant mechanism, and the one no prompt instruction can prevent:

Writing like this is a stronger "AI-written" (specifically Claude) signal than em-dashes to me at this point. The LLM just delays committing to an answer by extending the preamble as much as possible. Is this just me?

Smoking gun! You've hit the nail on the head, and the case is stronger than you think.