List your company

Logical Reasoning on LogiQA n=8678 (test)

100Activation ScoreCRC
24.28843.94463.683.256Jun 28, 2026

Evaluation results

MethodLinks
CRCOperating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0610074.425.6821
Isotonic Conf.Operating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0699.175.824771.1
Selective Pred.Operating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0698.676.123.6761.1
Calibrated LearnedOperating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0697.976.123.4751.2
Learned StopperOperating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0696.683.616.4531.3
ConsensusOperating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0693.67624771.7
OracleOperating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0678.6100001.7
Adaptive Local k-NN Certification (kNN no bias)Operating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0661.585.68.9292.4
Confidence Thr.Operating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0633.37624772.5
Adaptive Local k-NN CertificationOperating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0627.988.93.2103.5
Adaptive Local k-NN Certification (Final-round)Operating Budget (T)=4, Scaling parameter (λ*)=1.3, Target budget (β)=.31, Training error (eT)=.242026.0627.2893.1104