mlsanityData to 14 Oct 2026

Space Explanations of Neural Network Classification

arXiv 2511.22498 ↗First posted 27 Nov 2025cs.LG cs.LOcited by 5

Not on the map. Why?

Abstract (arXiv)

We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas of the input feature space. To automatically generate space explanations, we leverage a range of flexible Craig interpolation algorithms and unsatisfiable core generation. Based on real-life case studies, ranging from small to medium to large size, we demonstrate that the generated explanations are more meaningful than those computed by state-of-the-art.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 11 of its 45 references that are in the map. First posted on arXiv 27 Nov 2025.

Builds on

11 of 45 references.

References · 11

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  4. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  5. 2018Abduction-Based Explanations for Machine Learning Modelscited by 160
  6. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 131
  7. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  8. 2022Logic-Based Explainability in Machine Learningcited by 48
  9. 2016Towards Verified Artificial Intelligencecited by 36
  10. 2022VeriX: Towards Verified Explainability of Deep Neural Networkscited by 30
  11. 2023Delivering Inflated Explanationscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guaranteescited by 11
  2. 2026Provably Explaining Neural Additive Modelscited by 1
  3. 2026Towards Rigorous Explainability by Feature Attributioncited by 0
  4. 2026Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networkscited by 0
  5. 2026Neuron Activation-based Computation of Logical Explanations for Deep Neural Networkscited by 0