The paper introduces a unified evaluation protocol for robust counterfactual explanations (CFE), testing six robust methods and two baselines across four tabular datasets under eight types of model change. It shows that robustness scores vary by change type and that methods designed for one change family may not transfer to others, with RobX performing most consistently. The study emphasizes the need for a common protocol that defines model changes, measures their impact, and separates generation performance from robustness.
By Marcin Kostrzewa, Maciej Zi\k{e}ba
arXiv:2606. 01566v1 Announce Type: new Abstract: Small-to-medium scientific datasets place machine learning pipelines under two compounding pressures.
By Amanda S Barnard
arXiv:2607. 10420v1 Announce Type: cross Abstract: In software analytics, rerunning the same analysis twice often yields different models and conclusions.
By Amirali Rayegan, Lunxiao Li, Tim Menzies
arXiv:2608.27704v1 Announce Type: new
Abstract: When machine learning classifiers are retrained, inputs correctly classified by the previous model version may be misclassified by the updated version,...
By Madhusudan Srinivasan, Namith Nishal Raphae
arXiv:2605.30454v2 Announce Type: replace-cross
Abstract: Prompt-injection benchmarks for LLM agents typically test attacks through a single injection surface and report the resulting attack success...
By Syed Nazmus Sakib, Nafiul Haque, Shahrear Bin Amin, Shifat E. Arman
arXiv:2608. 05419v1 Announce Type: cross Abstract: Models trained by empirical risk minimization on data containing spurious correlations achieve high average accuracy while failing on subpopulations where the correlation does not hold.
By Nilesh Kumar
arXiv:2607. 26964v1 Announce Type: cross Abstract: We study feature bagging through the lens of algorithmic stability.
By Yuheng Ma, Qiang Sun
arXiv:2607. 20046v1 Announce Type: cross Abstract: With the widespread deployment of deep neural networks (DNNs) in safety-critical domains, reducing the cost of model validation under limited testing budgets has become increasingly important.
By Chunyu Liu, Mingyuan Li, Yang Li, Wenmin Li, Fei Gao, Tengfei Tu, Su-Juan Qin
The paper investigates the "edge of stability" phenomenon in deep learning, where Hessian eigenvalues remain stable above a classically predicted unstable threshold. It shows that many first‑order optimizers, including gradient descent, can violate this stability bound by up to a factor of 21.1, and that this deviation depends systematically on the optimizer used. The authors propose a new stability threshold based on the directional Hessian and gradient‑alignment score, which removes optimizer‑dependent offsets and offers consistent predictions while providing diagnostic tools to understand how optimizers balance temporal and spatial budgets.
By Jaerin Lee, Kyoung Mu Lee
arXiv:2609.13714v1 Announce Type: new
Abstract: An updated model can improve an aggregate metric while degrading a slice that matters to a downstream user. We study checkpoint selection subject to no...
By Shengwei Zhang, Tao Wu, Fei Qian
arXiv:2607. 03839v1 Announce Type: new Abstract: Sparse feature selection is critical for high-dimensional machine learning, yet traditional $\ell_1$-regularized methods are often brittle under observational noise and spurious correlations, leading to unstable feature supports and degraded generalization.
By Zhen Huang, Peicheng Xu, Junbiao Pang, Yulong Zheng
arXiv:2606. 19147v3 Announce Type: replace-cross Abstract: How can training data be used to compare local updates to the current model, choose an update, and retain valid bounds for the selected update's population-risk change?
By Mingzhi Song