RES — The empirical answer to the research question is asymmetric
The empirical answer to the research question is asymmetric: local models are viable for triage (H1 rejected, large effect) but for effort estimation do not conclusively beat a trivial estimator under MAE (H2 not rejected).
Source: PUMA project documentation · Traceability: corpus unit
MEM-059· Confidence: verified-at-primary-source