2 papers
cs.LG2026
A Free Knob: Decoupling Calibration and Predictive Skill in Threshold-Based Evaluation
Md Tanveer Hossain Munim, Bijoy Ahmed Saiem, Al-Amin Sany +1
Many dense-prediction benchmarks evaluate rare events by pooling prediction and target over spatial blocks, thresholding each, and scoring the contingency table. At a fixed rare op…
cs.LG2025
Breaking the Statistical Similarity Trap in Extreme Convection Detection
Md Tanveer Hossain Munim
Current evaluation metrics for deep learning weather models create a "Statistical Similarity Trap", rewarding blurry predictions while missing rare, high-impact events. We provide…