List your company

Question Answering on MuSR n=756 (test)

98.8Activation ScoreLearned Stopper
-3.95222.72449.476.076Jun 28, 2026

Evaluation results

MethodLinks
Learned Stopperbeta=0.15, T=42026.0698.863.536.5
Consensusbeta=0.15, T=42026.0691.965.734.3
Oraclebeta=0.15, T=42026.0668.91000
Selective Predictionbeta=0.15, T=42026.0643.467.214.2
CRCbeta=0.15, T=42026.0643.367.214.2
Confidence Thresholdbeta=0.15, T=42026.0632.96634
Calibrated Learnedbeta=0.15, T=42026.0618.946.86
Isotonic Confidencebeta=0.15, T=42026.067.6303
Adaptive Local k-NN Certification (Ours)beta=0.15, T=42026.060—0
kNN no biasbeta=0.15, T=42026.060—0
Final-roundbeta=0.15, T=42026.060—0