Demographic Parity in TabPFN Predictions Across Causal Structures and Quantification via Counterfactual Fairness Metrics

Machine learning systems are becoming increasingly ubiquitous. These systems's adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning that algorithmically informed decisions have greater potential for significant social impact. However, most of these accurate decision support systems remain complex black boxes, meaning their internal logic and inner workings are hidden to the user and even experts cannot fully understand the rationale behind their predictions. Moreover, new regulations and highly regulated domains have made the audit and verifiability o

Research goal: How does the demographic parity of TabPFN's downstream predictions vary when trained on SCMs with different causal structures, and can a causal fairness metric like counterfactual fairness be used to quantify this effect?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.3/10.