Automated Synthesis and Adversarial Validation of Executable Causal Research Pipelines

תקציר מקורי באנגליתarXiv:2607.21173v1 Announce Type: new Abstract: While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes successfully yet relies on invalid causal assumptions. We present the Artificial Intelligence (AI)-based Epidemiology Research Assistant (ARA), a framework that makes these failures visible by explicitly encoding causal design principles, study-specific assumptions, and methodological constraints. ARA integrates protocol construction, synthetic data generation, and adversarial validation into a unified pipeline. The framework translates natural language research questions into structured causal protocols and executable analysis code by first constructing a protocol and then generating syntheti