# Prevalence calibration as shortcut mitigation

arXiv: https://arxiv.org/abs/2609.07922 · HTML: https://mlsanity.com/paper/2609.07922/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging](https://mlsanity.com/paper/1909.12475/) (2019)
- [Reading Race: AI Recognises Patient's Racial Identity In Medical Images](https://mlsanity.com/paper/2107.10356/) (2021)
- [Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests](https://mlsanity.com/paper/2106.00545/) (2021)
- [Omnipredictors](https://mlsanity.com/paper/2109.05389/) (2021)
- [MEDFAIR: Benchmarking Fairness for Medical Imaging](https://mlsanity.com/paper/2210.01725/) (2022)
- [Causally motivated Shortcut Removal Using Auxiliary Labels](https://mlsanity.com/paper/2105.06422/) (2021)
- [Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing](https://mlsanity.com/paper/2207.10384/) (2022)
- [MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging](https://mlsanity.com/paper/2410.06542/) (2024)
- [Detecting Shortcuts in Medical Images -- A Case Study in Chest X-rays](https://mlsanity.com/paper/2211.04279/) (2022)
- [Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness](https://mlsanity.com/paper/2310.19691/) (2023)
- [Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods](https://mlsanity.com/paper/2406.12142/) (2024)
- [Are Sex-based Physiological Differences the Cause of Gender Bias for Chest X-ray Diagnosis?](https://mlsanity.com/paper/2308.05129/) (2023)

## Built on by (most cited first, 1 of 1)

- [Is invariance all you need for algorithmic fairness? Removing demographic information can create new bias](https://mlsanity.com/paper/2609.32004/) (2026)

## Abstract (arXiv)

Shortcut learning denotes the widespread situation in which a classifier exploits spurious correlations rather than diagnostic features. Existing mitigation strategies mostly aim to learn shortcut-invariant representations; their empirical success is limited and they cannot be applied to classifiers using frozen foundation model encoders. We propose to reframe shortcut learning as fundamentally a calibration problem: unconstrained learning implicitly calibrates each shortcut group to its training set disease prevalence, rendering the resulting classifier necessarily over-confident in one group and under-confident in the other. Building on this insight, we prevalence-equalize calibration between shortcut groups through two encoder-agnostic methods, an in-processing regularizer and a post-hoc prevalence-equalized recalibration step. Across chest-drain-pneumothorax benchmarks on CheXpert and SIIM-ACR, spanning fine-tuned CNNs and frozen foundation-model backbones, both methods substantially outperform all baselines. Post-hoc recalibration of a standard ERM-trained DenseNet raises misaligned-group AUROC from 0.23 to 0.73, indicating that shortcut reliance degrades the classification head rather than the underlying representation. Besides two new state-of-the-art shortcut mitigation approaches, our findings more fundamentally connect shortcut learning to calibration theory and algorithmic fairness.