Researchers have developed a new benchmark for evaluating how policies affect complex systems over time. Their method, called second-order policy-effect prediction, takes into account the ways in which institutions and actors adapt to new policies. The benchmark includes 96 real-world case studies of public policies across various domains, such as healthcare and education. These cases are used to test a simulator that estimates the effects of policies on things like capture, gaming, and compliance costs. According to the authors' results, their method outperforms other approaches in predicting side effects and transition scores. --- Why it matters: This work matters because it provides a more realistic way for researchers and policymakers to evaluate how policies will affect complex systems over time. By considering the ways in which institutions and actors adapt to new policies, this approach can help identify potential problems and areas where policies may have unintended consequences. Source: https://arxiv.org/abs/2608.15101