What's in this cluster
These three resources serve different needs. The Four Paradigms page is for readers comparing causal AI to other AI traditions. The Literature page is the annotated reading list for practitioners. Download Models contains the working Bayes Server files for every case study on the site.
Pages in this cluster
Four Paradigms → Four Paradigms, One Bet
There are at least four ways to combine LLMs and causality. Three of them place the LLM in different roles — assistant, reasoner, or generator of causal knowledge.
Literature → Research that moves the field. Annotated for practitioners.
Paper titles and abstracts are not readable. Each entry here states what the work does, why it matters for applied causal modeling, and what it changes or confirms in how the models on this site are built.
Download Models → Working Bayesian networks you can open, query, and extend.
Not diagrams — working models with conditional probability tables, causal arrows, and full probability distributions. Download, set evidence on any node, run inference, test interventions. Each model is the working version of a case study on this site.
How to use these
A reader trying to understand where Causal AI sits among the AI paradigms starts with Four Paradigms. A reader building their own causal models starts with Literature. A reader who wants to interact with the models behind the case studies goes to Download Models.