AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better

Yizhou Min, Yizhou Lu, Lanqi Li, Zhen Zhang, Jiaye Teng

ICML 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Conformal prediction sets · 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
apply Prejudicial Trick (null set with prob 1-p, adjusted alpha otherwise)VCP · Synthetic Gaussian-mixture noise (alpha=0.10, p=0.96)interval length: 22.894 -> 22.614Improved
apply Prejudicial Trick with p=0.98 instead of 0.96 (ablation)PT-VCP · Synthetic (alpha=0.10)interval length: 22.614 -> 22.714Mixed
apply Prejudicial TrickVCP · Synthetic (alpha=0.20, p=0.96)interval length: 21.886 -> 21.255Improved
apply Prejudicial TrickVCP · bike (regression, bias 10)interval length: 20.46 -> 19.59Improved
apply Prejudicial TrickVCP · star (regression, bias 5)interval length: 10.14 -> 9.63Improved
apply Prejudicial TrickVCP · facebook-2 (regression, bias 10)interval length: 20.97 -> 21.01Hurt
apply Prejudicial TrickVCP · 10 regression datasetsinterval length: smaller length in 9 out of 10 casesImproved
apply Prejudicial TrickRAPS · ImageNet-val resnet18 (bias 40)prediction set size: 304.02 -> 295.60Improved
apply Prejudicial TrickRAPS · ImageNet-val inception (bias 40)prediction set size: 304.10 -> 297.25Improved
apply Prejudicial Trick (adds randomness)VCP · meps-19interval stability: 0.00 -> 1.26Hurt
apply Prejudicial Trick (adds randomness)VCP · bikeinterval stability: 0.00 -> 0.58Hurt
retrain local scale estimator across runsLocalized CP · bikeinterval stability: 0.03No clear effect

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