Skip to content
Research

CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification and Estimation.

arXiv:2602.20571v3 Announce Type: replace Abstract: Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflates two distinct steps in caus

arXiv cs.AIResearch source·