Reliable decision-making in complex multi-agent systems requires calibrated predictions and interpretable uncertainty. We introduce SphUnc, a unified framework combining hyperspherical representation learning with structural causal modeling. The model maps features to unit hypersphere latents using von Mises-Fisher distributions, decomposing uncertainty into epistemic and aleatoric components through information-geometric fusion. A structural causal model on spherical latents enables directed influence identification and interventional reasoning via sample-based simulation. Empirical evaluations on social and affective benchmarks demonstrate improved accuracy, better calibration, and interpretable causal signals, establishing a geometric-causal foundation for uncertainty-aware reasoning in multi-agent settings with higher-order interactions.
@article{arxiv.2603.01168,
title = {SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry},
author = {Rong Fu and Chunlei Meng and Jinshuo Liu and Dianyu Zhao and Yongtai Liu and Yibo Meng and Xiaowen Ma and Wangyu Wu and Yangchen Zeng and Shuaishuai Cao and Simon Fong},
journal= {arXiv preprint arXiv:2603.01168},
year = {2026}
}