Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
CXPlain: Causal Explanations for Model Interpretation under Uncertainty
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use CXPlain (U-net) rather than CXPlain (MLP) (ablation) | CXPlain · MNIST | feature-importance estimation accuracy: p < 0.001 | Helped |
| use CXPlain rather than LIME | feature-importance estimation · ImageNet | feature-importance estimation accuracy: p < 0.01 | Helped |
| use CXPlain rather than LIME or SHAP | feature-importance estimation · MNIST and ImageNet | evaluation time | Helped |
| increase the bootstrap ensemble size from M=5 to M=100 (ablation) | CXPlain uncertainty estimates · MNIST test images | correlation of uncertainty with rank error: p < 0.001 | Helped |
| use bootstrap-derived uncertainty rather than randomly selected uncertainty estimates | CXPlain · MNIST test images | correlation of uncertainty with rank error: p < 0.001 | Helped |
Closest papers by meaning
- The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations (NeurIPS 2021 · similarity 0.89)
- Feature Importance Explanations for Temporal Black-Box Models (AAAI 2022 · similarity 0.87)
- Aggregate Models, Not Explanations: Improving Feature Importance Estimation (ICML 2026 · similarity 0.87)
- Regional Explanations: Bridging Local and Global Variable Importance (NeurIPS 2025 · similarity 0.86)
- Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration (NeurIPS 2025 · similarity 0.86)
- Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation (ICML 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.