ember

7Calibration

A reliability diagram plots each confidence bin's accuracy against its mean confidence; a perfectly calibrated advisor sits on the diagonal [11]. Bars above the diagonal mean ember was more often right than its confidence claimed (under-confidence); bars below it mean over-confidence, the dangerous direction for threshold-driven agents.

Reliability of noul answersAccuracy bars per confidence bin against the diagonal of perfect calibration.accuracymean confidenceperfect calibration0.00.00.20.20.40.40.60.60.80.81.01.0Top-label confidenceAccuracyn=46n=55n=58n=94n=391ECE 0.070 MCE 0.146
Figure 6 Reliability of noul answers (644 questions). Coral lines mark each bin's mean confidence; shading below a line marks over-confidence.
TypeNMean confidenceAccuracyAccuracy minus confidenceECEMCEBrier
noul6440.87280.1%-0.070 (over-confident)0.0700.1460.135