CausalArena: Benchmarking Causal Discovery in the Foundation Model Era
Researchers introduce CausalArena, a unified benchmark revealing that causal discovery rankings shift substantially across structural causal model families and protocols.
The paper presents CausalArena, a unified and evolvable benchmark for causal discovery combining synthetic structural causal models, semantically grounded operational SCMs, formula-grounded scientific SCMs, and public real-world datasets. Experiments across classical, neural, and pretrained causal discovery foundation models show large ranking shifts between benchmark regimes. The authors identify pretraining-evaluation overlap and benchmark diversity as central evaluation challenges.
- Unified protocol spans synthetic, semantic, and formula-grounded SCM families
- Pretraining-evaluation overlap confounds results of causal discovery foundation models
- Strong performance in one benchmark regime does not transfer to others
- Real-world datasets add an external-validity check beyond synthetic generators
- Products
- CausalArena
- Organizations
- arXiv
From the original article
1 min read at arxiv.orgCausal discovery aims to uncover causal structures from data and is fundamental to scientific reasoning and intervention-based decision making. Its evaluation relies heavily on structural causal models (SCMs), which specify a causal graph together with the mechanisms that generate data, yet existing studies differ substantially in graph families, mechanisms, and evaluation protocols.
By Zi-Rong Li · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.