Papers
1–3 of 3Research Paper·Feb 18, 2026
Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning
Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GN...
7.0 viability
Research Paper·Mar 5, 2026
Warm Starting State-Space Models with Automata Learning
We prove that Moore machines can be exactly realized as state-space models (SSMs), establishing a formal correspondence between symbolic automata and these continuous machine learning architectures. T...
7.0 viability
Research Paper·Mar 5, 2026
On Multi-Step Theorem Prediction via Non-Parametric Structural Priors
Multi-step theorem prediction is a central challenge in automated reasoning. Existing neural-symbolic approaches rely heavily on supervised parametric models, which exhibit limited generalization to e...
6.0 viability