ConformaDecompose: Explaining Uncertainty via Calibration Localization
Abstract
Conformal Prediction provides distribution-free prediction intervals with guaranteed coverage, but its reliance on a single global calibration threshold obscures the sources of uncertainty at the instance level. In particular, it conflates irreducible noise with uncertainty induced by heterogeneous training data (aleatoric), model limitations, or calibration mismatch (epistemic), offering little insight into why an interval is wide or whether it could be reduced. We introduce an uncertainty-aware explainability framework that analyses the reducibility of calibration-induced epistemic conformal uncertainty via progressive calibration localisation for regression tasks. The approach is diagnostic rather than causal: it does not estimate true aleatoric or epistemic uncertainty, but explains how conformal intervals contract and stabilise as calibration support is localised around a test instance. Across benchmarks and real-world data, absolute reducible uncertainty aligns with epistemic proxies, while its relative contribution varies by task, revealing regimes hidden by interval width. This instance-level view complements conformal uncertainty, enhancing interpretability without altering the predictor or coverage.
Cite
@article{arxiv.2604.27149,
title = {ConformaDecompose: Explaining Uncertainty via Calibration Localization},
author = {Fatima Rabia Yapicioglu and Meltem Aksoy and Alberto Rigenti and Tuwe Löfström-Cavallin and Helena Löfström-Cavallin and Seyda Yoncaci and Luca Longo},
journal= {arXiv preprint arXiv:2604.27149},
year = {2026}
}
Comments
This is the accepted author version of a paper to appear in the proceedings of the World Explainable AI Conference (Springer). The final version will be available via Springer. This manuscript introduces ConformaDecompose, a framework for instance-wise uncertainty explainability via calibration localisation