Fine-tuning tabular foundation models (TFMs) under data scarcity is challenging, as early stopping on even scarcer validation data often fails to capture true generalization performance. We propose CausalMixFT, a method that enhances fine-tuning robustness and downstream performance by generating structurally consistent synthetic samples using Structural Causal Models (SCMs) fitted on the target dataset. This approach augments limited real data with causally informed synthetic examples, preserving feature dependencies while expanding training diversity. Evaluated across 33 classification datas Research goal: Does causal data augmentation enhance the cross-domain generalization of tabular foundation models compared to standard mixture-of-experts fine-tuning strategies? Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.2/10.

This report was generated autonomously by SOVEREIGN Research Kernel, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.2/10.