mlsanityData to 14 Oct 2026

φ-Table: A Statistical Explanation for Global SHAP

arXiv 2512.07578 ↗First posted 8 Dec 2025stat.ML cs.LG stat.MEcited by 0

Not on the map. Why?

Abstract (arXiv)

Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but do not indicate whether their effects admit clear directional summaries, how uncertain those summaries are, or how faithfully they represent the fitted response. This paper proposes the φ-table, a SHAP-based statistical explanation table for tabular black-box regression models. The procedure selects features by SHAP importance and fits a standardized linear surrogate to the fitted model response f(X), reporting SHAP importance together with model-response coefficients, uncertainty summaries, surrogate fidelity, and bootstrap coefficient stability. The resulting coefficients are interpreted as projections of the fitted model response onto the SHAP-selected feature set. Across synthetic, semi-synthetic, and real-data experiments, the φ-table extends ranking-only SHAP into a statistical global explanation by exposing direction, uncertainty, fidelity, and stability as distinct components of fitted model behavior.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 50 of its 80 references that are in the map. First posted on arXiv 8 Dec 2025.

Builds on

50 of 80 references.

References · 50

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  9. 2018Sanity Checks for Saliency Mapscited by 1,156
  10. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  11. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  12. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
38 more
  1. 2017Interpretation of Neural Networks is Fragilecited by 444
  2. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 373
  3. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  4. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  5. 2019Explanations can be manipulated and geometry is to blamecited by 216
  6. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  7. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 154
  8. 2019The Shapley Taylor Interaction Indexcited by 143
  9. 2015Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction modelcited by 140
  10. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 126
  11. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  12. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 125
  13. 2019Optimal Sparse Decision Treescited by 105
  14. 2020Benchmarking Deep Learning Interpretability in Time Series Predictionscited by 102
  15. 2020Generalized and Scalable Optimal Sparse Decision Treescited by 100
  16. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  17. 2013Exact post-selection inference, with application to the lassocited by 91
  18. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 88
  19. 2018Boolean Decision Rules via Column Generationcited by 80
  20. 2015Supersparse Linear Integer Models for Optimized Medical Scoring Systemscited by 76
  21. 2022Faith-Shap: The Faithful Shapley Interaction Indexcited by 69
  22. 2016Scalable Bayesian Rule Listscited by 64
  23. 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
  24. 2014Falling Rule Listscited by 59
  25. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
  26. 2021Do Input Gradients Highlight Discriminative Features?cited by 52
  27. 2020Shapley Flow: A Graph-based Approach to Interpreting Model Predictionscited by 51
  28. 2016Learning Optimized Risk Scorescited by 47
  29. 2020A general framework for inference on algorithm-agnostic variable importancecited by 45
  30. 2023The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantuscited by 37
  31. 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Valuescited by 36
  32. 2021Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retrainingcited by 31
  33. 2022Robust Explanation Constraints for Neural Networkscited by 24
  34. 2016Selective Inference for Group-Sparse Linear Modelscited by 21
  35. 2013A significance test for the lassocited by 20
  36. 2023Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariancecited by 14
  37. 2021Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Setcited by 12
  38. 2023Faithfulness Measurable Masked Language Modelscited by 5

Built on by

Not cited yet.