# MUPAX: Multidimensional Problem Agnostic eXplainable AI

arXiv: https://arxiv.org/abs/2507.13090 · HTML: https://mlsanity.com/paper/2507.13090/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Builds on (most cited first, 20 of 20)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges](https://mlsanity.com/paper/2010.09337/) (2020)
- [Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey](https://mlsanity.com/paper/1911.12116/) (2019)
- [On the Tractability of SHAP Explanations](https://mlsanity.com/paper/2009.08634/) (2020)
- [Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models](https://mlsanity.com/paper/2001.11757/) (2020)
- [TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models](https://mlsanity.com/paper/2109.08438/) (2021)
- [A Modified Perturbed Sampling Method for Local Interpretable Model-agnostic Explanation](https://mlsanity.com/paper/2002.07434/) (2020)
- [An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges](https://mlsanity.com/paper/2005.10516/) (2020)
- [Biased Models Have Biased Explanations](https://mlsanity.com/paper/2012.10986/) (2020)
- [Cephalometric Landmark Detection across Ages with Prototypical Network](https://mlsanity.com/paper/2406.12577/) (2024)
- [Spatial-Aware Non-Local Attention for Fashion Landmark Detection](https://mlsanity.com/paper/1903.04104/) (2019)
- [Gradient Backpropagation based Feature Attribution to Enable Explainable-AI on the Edge](https://mlsanity.com/paper/2210.10922/) (2022)
- [A Taxonomy of Explainable Bayesian Networks](https://mlsanity.com/paper/2101.11844/) (2021)

## Abstract (arXiv)

Robust XAI techniques should ideally be simultaneously deterministic, model agnostic, and guaranteed to converge. We propose MULTIDIMENSIONAL PROBLEM AGNOSTIC EXPLAINABLE AI (MUPAX), a deterministic, model agnostic explainability technique, with guaranteed convergency. MUPAX measure theoretic formulation gives principled feature importance attribution through structured perturbation analysis that discovers inherent input patterns and eliminates spurious relationships. We evaluate MUPAX on an extensive range of data modalities and tasks: audio classification (1D), image classification (2D), volumetric medical image analysis (3D), and anatomical landmark detection, demonstrating dimension agnostic effectiveness. The rigorous convergence guarantees extend to any loss function and arbitrary dimensions, making MUPAX applicable to virtually any problem context for AI. By contrast with other XAI methods that typically decrease performance when masking, MUPAX not only preserves but actually enhances model accuracy by capturing only the most important patterns of the original data. Extensive benchmarking against the state of the XAI art demonstrates MUPAX ability to generate precise, consistent and understandable explanations, a crucial step towards explainable and trustworthy AI systems. The source code will be released upon publication.