# Multi-Dimensional Model Integrity and Responsibility Assessment Index and Scoring Framework

arXiv: https://arxiv.org/abs/2605.14550 · HTML: https://mlsanity.com/paper/2605.14550/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 27 of 27)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Fairness in Criminal Justice Risk Assessments: The State of the Art](https://mlsanity.com/paper/1703.09207/) (2017)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [When Do Neural Nets Outperform Boosted Trees on Tabular Data?](https://mlsanity.com/paper/2305.02997/) (2023)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [When Explanations Lie: Why Many Modified BP Attributions Fail](https://mlsanity.com/paper/1912.09818/) (2019)
- [Fairlearn: Assessing and Improving Fairness of AI Systems](https://mlsanity.com/paper/2303.16626/) (2023)
- [Framework for Evaluating Faithfulness of Local Explanations](https://mlsanity.com/paper/2202.00734/) (2022)
- [On Adversarial Bias and the Robustness of Fair Machine Learning](https://mlsanity.com/paper/2006.08669/) (2020)
- [LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks](https://mlsanity.com/paper/2402.12525/) (2024)
- [SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning](https://mlsanity.com/paper/2112.02230/) (2021)
- [XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach](https://mlsanity.com/paper/2407.11771/) (2024)
- [Motion2Meaning: A Clinician-Centered Framework for Contestable LLM in Parkinson's Disease Gait Interpretation](https://mlsanity.com/paper/2512.08934/) (2025)
- [Guideline for Trustworthy Artificial Intelligence -- AI Assessment Catalog](https://mlsanity.com/paper/2307.03681/) (2023)
- [ODExAI: A Comprehensive Object Detection Explainable AI Evaluation](https://mlsanity.com/paper/2504.19249/) (2025)
- [Navigating the EU AI Act: A Methodological Approach to Compliance for Safety-critical Products](https://mlsanity.com/paper/2403.16808/) (2024)
- [MACeIP: A Multimodal Ambient Context-enriched Intelligence Platform in Smart Cities](https://mlsanity.com/paper/2409.15243/) (2024)
- [RAISE: A Unified Framework for Responsible AI Scoring and Evaluation](https://mlsanity.com/paper/2510.18559/) (2025)

## Abstract (arXiv)

Artificial intelligence in high-stakes tabular domains cannot be evaluated by predictive performance alone, yet current practice still assesses explainability, fairness, robustness, privacy, and sustainability mostly in isolation. We propose the Model Integrity and Responsibility Assessment Index (MIRAI), a unified evaluation framework that measures tabular models across these five dimensions under a controlled comparison setting and aggregates them into a single score. MIRAI combines established metrics through normalized and direction-aligned dimension scores, which enables direct comparison across models with different architectural and computational profiles. Experiments on healthcare, financial, and socioeconomic datasets show that higher predictive performance does not necessarily imply better overall integrity and responsibility. In several cases, simpler models achieve a stronger cross-dimensional balance than more complex deep tabular architectures. MIRAI provides a compact and practical basis for responsible model selection in regulated settings.