Stanford University
CoDICoordinated Decision
Intelligence Center

Project / Causal inference

CausalSmith: AI-assisted causal research

CausalSmith coordinates AI agents that propose theoretical results in causal inference, formalize statements, and construct proofs checked by Lean. A statement audit compares formal theorems with their intended informal claims, while human inspection remains part of the research process.

Explore the work

Use the public sources to explore the research, its setting, and its limitations.

CausalSmith website CausalSmith paper CausalSmith code ← All projects

Connect with CoDI

Put coordination
at the center.

Explore the research, meet our faculty, and find the right way to engage.

Explore ways to engage