Researchers have created CausalProfiler, a tool that generates synthetic benchmarks for evaluating causal machine learning methods. These benchmarks are designed to be more comprehensive and transparent than existing ones, which often rely on hand-crafted or semi-synthetic datasets. The tool allows for the evaluation of causal ML methods under various conditions and assumptions, including observation, intervention, and counterfactual reasoning. --- Why it matters: This matters because it enables more rigorous and transparent evaluation of causal machine learning methods, which is crucial for high-stakes decision-making applications. Source: https://arxiv.org/abs/2511.22842