Prior-fitted networks for time-series causal inference and longitudinal counterfactual outcome prediction.

A research-grade, 6-week masterclass in Causal Inference and Causal ML from first principles. Rebuilds d-separation oracles, propensity score IRLS engines, doubly-robust AIPW estimators, Cross-Fitting Double Machine Learning (DML), and honest causal forests from scratch in pure NumPy. Fully verified against causal truth

Models causals estructurals i resultats potencials (Treball de Final de Grau)

A new kind of world model: the PSD coupling kernel K(T,T') of admissible possible worlds. Diagonal = prediction, off-diagonal = counterfactual coupling. Built in public.