What is causal about causal models and representations?

arXiv:2501.19335 · stat.ML, cs.AI, cs.LG, math.ST, stat.TH · Submitted 2025-01-31 · Read on arXiv

stat.ML, cs.AI, cs.LG, math.ST, stat.TH

Submitted: 2025-01-31

Updated: 2026-10-16

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Abstraction — 1× in this paper · explained in 1 episode
• Causal Discovery — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 3 episodes

Sources

• Efficient adjustment for complex covariates: Gaining efficiency with DOPE
• Towards a Grounded Theory of Causation for Embodied AI
• Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
• All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Scalable Posterior Uncertainty for Flexible Density-Based Clustering
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing