Evidence and limits
Finding: Simpler transparent models improved simulation of predictions but did not increase beneficial following and reduced detection of large model mistakes in one condition.
Impact: Strengthen behavioral interpretability tests. Reject transparency or simulability as automatic error-correction evidence.
Boundary: Synthetic prediction tasks do not cover all explanation goals. Next: which explanation improves a named decision behavior without information overload?
Flags: synthetic prediction tasks; interpretability manipulation
Record State: Catalog review recorded; not a performance endorsement
What was reviewed: Structure and relevance screened; not a full evaluation