Evidence and limits
Finding: Human-authored rules could identify useful delegation regions in the studied setting, but creating reliable rules became harder under distribution shift and explanations did not guarantee better performance.
Impact: Watch bounded conditional delegation for stable, observable regions. Strengthen distribution-shift checks before reusing a rule.
Boundary: The work uses relatively low-stakes keyword moderation and an experimental interface. Next: can delegation rules remain legible and safe in open-ended workflows with changing models?
Flags: preprint; content-moderation labels; induced distribution shift
Record State: Catalog review recorded; not a performance endorsement
What was reviewed: Structure and relevance screened; not a full evaluation