Evidence and limits
Finding: A more accurate model update can reduce team performance when its new errors violate the human participant's learned expectations.
Impact: Strengthen version-change compatibility and revalidation. Reject higher model accuracy as sufficient evidence that an established workflow improved.
Boundary: The experiments use structured classification decisions. Next: which model, prompt, tool, and policy changes should invalidate prior delegation and reliance evidence?
Flags: structured advice tasks; author-family overlap
Record State: Catalog review recorded; not a performance endorsement
What was reviewed: Structure and relevance screened; not a full evaluation