Diagnosing Conformal Prediction Failures Under Distribution Shift: A COVID-19 Case Study

Chorok Lee
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:3453-3476, 2026.

Abstract

Conformal prediction provides distribution-free coverage guarantees, but these degrade under distribution shift—and practitioners lack tools to anticipate which deployed models will fail before observing test data. We propose SHapley Additive exPlanations (SHAP) concentration—the fraction of feature importance concentrated in the top feature—as a pre-deployment diagnostic for conformal prediction vulnerability in gradient-boosted classifiers. Using COVID-19 as a naturalistic case study, eight supply chain tasks experience identical temporal shift yet coverage drops ranging from negligible to catastrophic. Feature-importance concentration is strongly associated with failure severity across 16 multiclass tasks in 9 domains, while standard distributional shift detectors detect shift uniformly across tasks but cannot distinguish catastrophic from robust outcomes. External validation across 9 non-supply-chain datasets shows partial transfer. We prove a formal theorem showing that Adaptive Prediction Sets conformity-score bounds worsen monotonically with concentration under explicit assumptions, verified empirically. The diagnostic identifies concentrated-dependence failures characteristic of gradient-boosted models but does not detect global-sensitivity failures observed in neural networks. A decision framework operationalizes the diagnostic as an exploratory pre-deployment rule with an uncertainty band around a concentration threshold.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-lee26g, title = {Diagnosing Conformal Prediction Failures Under Distribution Shift: A COVID-19 Case Study}, author = {Lee, Chorok}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {3453--3476}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/lee26g/lee26g.pdf}, url = {https://proceedings.mlr.press/v337/lee26g.html}, abstract = {Conformal prediction provides distribution-free coverage guarantees, but these degrade under distribution shift—and practitioners lack tools to anticipate which deployed models will fail before observing test data. We propose SHapley Additive exPlanations (SHAP) concentration—the fraction of feature importance concentrated in the top feature—as a pre-deployment diagnostic for conformal prediction vulnerability in gradient-boosted classifiers. Using COVID-19 as a naturalistic case study, eight supply chain tasks experience identical temporal shift yet coverage drops ranging from negligible to catastrophic. Feature-importance concentration is strongly associated with failure severity across 16 multiclass tasks in 9 domains, while standard distributional shift detectors detect shift uniformly across tasks but cannot distinguish catastrophic from robust outcomes. External validation across 9 non-supply-chain datasets shows partial transfer. We prove a formal theorem showing that Adaptive Prediction Sets conformity-score bounds worsen monotonically with concentration under explicit assumptions, verified empirically. The diagnostic identifies concentrated-dependence failures characteristic of gradient-boosted models but does not detect global-sensitivity failures observed in neural networks. A decision framework operationalizes the diagnostic as an exploratory pre-deployment rule with an uncertainty band around a concentration threshold.} }
Endnote
%0 Conference Paper %T Diagnosing Conformal Prediction Failures Under Distribution Shift: A COVID-19 Case Study %A Chorok Lee %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-lee26g %I PMLR %P 3453--3476 %U https://proceedings.mlr.press/v337/lee26g.html %V 337 %X Conformal prediction provides distribution-free coverage guarantees, but these degrade under distribution shift—and practitioners lack tools to anticipate which deployed models will fail before observing test data. We propose SHapley Additive exPlanations (SHAP) concentration—the fraction of feature importance concentrated in the top feature—as a pre-deployment diagnostic for conformal prediction vulnerability in gradient-boosted classifiers. Using COVID-19 as a naturalistic case study, eight supply chain tasks experience identical temporal shift yet coverage drops ranging from negligible to catastrophic. Feature-importance concentration is strongly associated with failure severity across 16 multiclass tasks in 9 domains, while standard distributional shift detectors detect shift uniformly across tasks but cannot distinguish catastrophic from robust outcomes. External validation across 9 non-supply-chain datasets shows partial transfer. We prove a formal theorem showing that Adaptive Prediction Sets conformity-score bounds worsen monotonically with concentration under explicit assumptions, verified empirically. The diagnostic identifies concentrated-dependence failures characteristic of gradient-boosted models but does not detect global-sensitivity failures observed in neural networks. A decision framework operationalizes the diagnostic as an exploratory pre-deployment rule with an uncertainty band around a concentration threshold.
APA
Lee, C.. (2026). Diagnosing Conformal Prediction Failures Under Distribution Shift: A COVID-19 Case Study. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:3453-3476 Available from https://proceedings.mlr.press/v337/lee26g.html.

Related Material