Evidence and limits
Finding: A prior consistent deferral formulation was not calibrated for expert correctness; the proposed one-vs-all method produced calibrated probabilities in tested tasks.
Impact: Strengthen calibration testing for deferral estimates. Reject consistency or accuracy alone as calibrated routing evidence.
Boundary: Classification benchmarks do not validate open-ended delegation. Next: what calibration target is meaningful when correctness is delayed or multidimensional?
Flags: classification benchmarks; delayed outcomes absent
Record State: Catalog review recorded; not a performance endorsement
What was reviewed: Structure and relevance screened; not a full evaluation