# Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration

Source: [Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration](<https://www.sota2.com/research/paper/6a7bfdf24b236a9bba1a1797>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-13T05:00:05.217Z

Authors: Lening Zhao, Qipeng Zhan, Li Shen

Published: 2026-08-11T02:08:05.000Z

## Abstract

Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining. An ideal calibrator should correct nonlinear miscalibration, scale gracefully to large label spaces, and preserve the original predictions; existing methods typically violate at least one of these properties---temperature scaling lacks expressivity, more flexible parametric alternatives introduce parameters that grow with the number of classes $C$, and other expressive methods do not preserve the rank ordering of class scores and may alter the predicted class. We propose \\textbf{Invertible Logits Transformation (InvLT)}, which applies a learned scalar MLP $f:\\mathbb{R}\\to\\mathbb{R}$ element-wise to the pre-softmax logits. Sharing $f$ across all logit dimensions makes the parameter count independent of $C$. Monotonicity of $f$---and hence preservation of the argmax prediction---is softly encouraged via a paired inverse network rather than enforced through the numerical integration required by prior monotone calibrators; this avoids their computational overhead while empirically preserving the original classification accuracy in every setting we evaluate. Across standard image classification benchmarks and a range of architectures, InvLT consistently outperforms a broad set of post-hoc baselines on standard calibration metrics.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2608.10372>)

[PDF](<https://arxiv.org/pdf/2608.10372.pdf>)
