3 papers
cs.DB2026
CSQL: Mapping Documents into Causal Databases
Sridhar Mahadevan
We describe a novel system, CSQL, which automatically converts a collection of unstructured text documents into an SQL-queryable causal database (CDB). A CDB differs from a traditi…
cs.AI2026
Categorical Belief Propagation: Sheaf-Theoretic Inference via Descent and Holonomy
Enrique ter Horst, Sridhar Mahadevan, Juan Diego Zambrano
We develop a categorical foundation for belief propagation on factor graphs. We construct the free hypergraph category \(\Syn_Σ\) on a typed signature and prove its universal prop…
cs.AI2025
Large Causal Models from Large Language Models
Sridhar Mahadevan
We introduce a new paradigm for building large causal models (LCMs) that exploits the enormous potential latent in today's large language models (LLMs). We describe our ongoing exp…