Causal discovery needs explicit epistemic standards
stat.ML, cs.LG, stat.ME
Submitted: 2026-11-02
Updated: 2026-11-02
Comments: This paper was accepted to the position paper track of NeurIPS 2026
Code: https://github.com/mwien/CliquePicking
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Are Bayesian networks typically faithful?
- What is causal about causal models and representations?
- Shortcuts for causal discovery of nonlinear models by score matching
- A Topological Sorting Criterion for Random Causal Directed Acyclic Graphs
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference