# Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)

arXiv: https://arxiv.org/abs/2510.00475 · HTML: https://mlsanity.com/paper/2510.00475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [Training Networks in Null Space of Feature Covariance for Continual Learning](https://mlsanity.com/paper/2103.07113/) (2021)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)
- [Balancing Stability and Plasticity through Advanced Null Space in Continual Learning](https://mlsanity.com/paper/2207.12061/) (2022)
- [Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization](https://mlsanity.com/paper/2202.00232/) (2022)
- [Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation](https://mlsanity.com/paper/2412.05152/) (2024)
- [When does Bias Transfer in Transfer Learning?](https://mlsanity.com/paper/2207.02842/) (2022)
- [A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems](https://mlsanity.com/paper/2301.07799/) (2023)
- [Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics](https://mlsanity.com/paper/2302.09344/) (2023)
- [Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?](https://mlsanity.com/paper/2305.09275/) (2023)
- [Monitoring Shortcut Learning using Mutual Information](https://mlsanity.com/paper/2206.13034/) (2022)
- [How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning](https://mlsanity.com/paper/2306.00044/) (2023)
- [Does the Adam Optimizer Exacerbate Catastrophic Forgetting?](https://mlsanity.com/paper/2102.07686/) (2021)

## Abstract (arXiv)

Deep neural networks frequently exploit shortcut features, defined as incidental correlations between inputs and labels without causal meaning. Shortcut features undermine robustness and reduce reliability under distribution shifts. In continual learning (CL), the consequences of shortcut exploitation can persist and intensify: weights inherited from earlier tasks bias representation reuse toward whatever features most easily satisfied prior labels, mirroring the cognitive Einstellung effect, a phenomenon where past habits block optimal solutions. Whereas catastrophic forgetting erodes past skills, shortcut-induced rigidity throttles the acquisition of new ones. We introduce the Einstellung Rigidity Index (ERI), a compact diagnostic that disentangles genuine transfer from cue-inflated performance using three interpretable facets: (i) Adaptation Delay (AD), (ii) Performance Deficit (PD), and (iii) Relative Suboptimal Feature Reliance (SFR_rel). On a two-phase CIFAR-100 CL benchmark with a deliberately spurious magenta patch in Phase 2, we evaluate Naive fine-tuning (SGD), online Elastic Weight Consolidation (EWC_on), Dark Experience Replay (DER++), Gradient Projection Memory (GPM), and Deep Generative Replay (DGR). Across these continual learning methods, we observe that CL methods reach accuracy thresholds earlier than a Scratch-T2 baseline (negative AD) but achieve slightly lower final accuracy on patched shortcut classes (positive PD). Masking the patch improves accuracy for CL methods while slightly reducing Scratch-T2, yielding negative SFR_rel. This pattern indicates the patch acted as a distractor for CL models in this setting rather than a helpful shortcut.