causal-representation-learning

This paper critiques the 'Proxy Presumption' in NLP, where geometric embedding properties are incorrectly equated with social constructs. It introduces the Construct Validity Protocol and Counterfactual Neutralization methods to ensure rigorous validation of social measures derived from semantic embeddings.

This paper introduces MOSAIC, a method for module discovery in scientific time series that combines causal representation learning with sparse additive identifiable causal learning. It aims to recover interpretable latent variables and their associated observations without post-hoc alignment, validated on domains like molecular dynamics and climate data.