WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testing

arXiv:2610.00713 · cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/gmum/wombat

Terminology

• Benchmarking — 1× in this paper · explained in 4 episodes

Sources

• True to the Model or True to the Data?
• Strategies for Pre-training Graph Neural Networks
• Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs
• Investigating Saturation Effects in Integrated Gradients
• B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
• A Survey on Oversmoothing in Graph Neural Networks

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks