SATE: Transferable Spin-Adapted Neural Wavefunctions
physics.chem-ph
Submitted: 2026-11-09
Updated: 2026-11-13
Comments: 20 pages, 4 figures
Code: https://github.com/microsoft/oneqmc
License: http://creativecommons.org/licenses/by/4.0/
The gist: Accurate prediction of molecular reactivity requires both accurate and computationally efficient description of electron correlation and spin across various molecular geometries and electronic states.
Terminology
Abstract
Accurate prediction of molecular reactivity requires both accurate and computationally efficient description of electron correlation and spin across various molecular geometries and electronic states. We introduce SATE, a spin-adapted transferable neural wavefunction architecture with effective core potentials. SATE combines a transferable neural wavefunction, the spin-adapted antisymmetrization method, and effective core potentials into a single foundation model architecture pretrained on compositions containing selected elements from hydrogen to bromine. After pretraining and adaptation, our model is able to predict 3d transition-metal spin-state gaps, bond dissociation energies, and reaction energies by addressing two key issues. First, including the core potentials into the model allows us to reduce the number of explicitly treated electrons. Second, using spin-adapted antisymmetrization enforces the prescribed total spin by construction. By testing our model with 3d transition metal chemistry, we evaluate our model's description of strong electron correlation and competing electronic states in such compounds. We find that pretraining improves most tested component energies at matched adaptation budgets, while improvements in spin-state gaps, dissociation energies, and reaction energies remain system dependent. Ultimately, our work lays the foundation for more accurate and transferable modeling of molecular systems by combining the computational efficiency of effective core potentials with explicit control over total spin.
Sources
- A Self-Attention Ansatz for Ab-initio Quantum Chemistry
- Spin-Adapted Neural Network Wavefunctions in Real Space
Related papers
- A System-Independent Metadynamics Strategy for Reactive Training Data: Application to Gas-Phase Organic Reactions
- A Machine Learning Model for the Chemistry of a Solvated Electron
- Compression of virtual spaces in transcorrelated methods via singular value decomposition: application to the G2 set
- Charge Transfer with a Spin. II: A Framework for Diabatization which Localizes Charge and Spin
- Diabatic Seam Space Sampling for Hydrogen Tunneling Systems with Nuclear-Electronic Orbital Theory
- Augmented Roothaan-Hall Hessian Applied to Spin-Restricted Open-Shell Density-Functional Theory