AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Courtroom Analogy: New Perspective on Uncertainty-Aware Classification

Taeseong Yoon, Heeyoung Kim

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Epistemic versus aleatoric decomposition · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MoDEX instead of F-EDLF-EDL · CIFAR-10test accuracy: 91.19 -> 92.46Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-100test accuracy: 69.40 -> 75.91Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-100misclassification detection AUPR: 94.01 -> 96.17Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-100, OOD SVHNOOD detection AUPR: 75.35 -> 77.90Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-10, OOD SVHNOOD detection AUPR: 91.20 -> 91.58Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-10-C severity 5distribution shift detection AUPR: 78.52 -> 80.63Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-10-C severity 1distribution shift detection AUPR: 58.16 -> 58.72Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-10-LT (rho=0.01)test accuracy: 63.73 -> 71.53Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-10-LT (rho=0.01)misclassification detection AUPR: 85.99 -> 91.90Improved
use MoDEX instead of F-EDLF-EDL · CIFAR-10-LT (rho=0.01), OOD SVHNOOD detection AUPR: 62.56 -> 72.05Improved
use MoDEX instead of F-EDLF-EDL · DMNIST-LT (rho=0.01)test accuracy: 67.20 -> 69.42Improved
use MoDEX instead of F-EDLF-EDL · DMNIST-LT (rho=0.01), OOD FMNISTOOD detection AUPR: 96.84 -> 98.88Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy