Continuous SUN (stable, unique, and novel) metric for generative modeling of inorganic crystals
- 1Imperial College London
Abstract
To address pressing scientific challenges such as climate change, increasingly sophisticated generative models are being developed to efficiently sample the large chemical space of potential functional materials. The proliferation of these models has necessitated the establishment of rigorous evaluation metrics. While uniqueness (U), novelty (N), and stability (S) of samples serve as standard metrics, their current formulations show several limitations. U and N rely on binary comparisons of crystals, rendering them dependent on heuristic thresholds, incapable of quantifying the degree of similarity, sensitive to atomic coordinate perturbations, and not invariant to sample permutation. Similarly, the binary assessment of S risks a premature exclusion of marginally unstable yet potentially novel candidates. These limitations are addressed by making the aforementioned metrics continuous. Furthermore, we integrate them into a unified metric ‘continuous SUN’ (cSUN), which offers a smoother score distribution and greater tunability than the conventional binary SUN metric. Experimental results demonstrate that our continuous metrics provide granular insights into sample distributions and secondarily serve as a soft screening score for selecting samples for further analysis. Finally, the use of cSUN as a reward signal in reinforcement learning is explored, showing that its adjustable weighting scheme effectively enhances sample diversity and convergence to a better optima in a Chemeleon2 case study.
Related
- Tailoring Lead Iodide Crystals Through Organic Templating and Inorganic Heterostructuring for Optoelectronics
- Guiding generative models to uncover diverse and novel crystals via reinforcement learning
- How Metal-to-Linker Ratio and Concentration Govern the Nucleation Mechanism of MOF-5-inspired Crystals: Insights from Multiscale Modeling
- Bulk mesophases modeling of ferroelectric nematic liquid crystals
- CrystalGRW: generative modeling of crystal structures with targeted crystallographic properties via geodesic random walks
BibTeX
@article{negishi2026continuous,
title = {{Continuous SUN (stable, unique, and novel) metric for generative modeling of inorganic crystals}},
author = {Masahiro Negishi and Hyunsoo Park and Kinga O. Mastej and Aron Walsh},
journal = {Machine Learning Science and Technology},
year = {2026},
month = jun,
doi = {10.1088/2632-2153/ae7d85},
url = {https://doi.org/10.1088/2632-2153/ae7d85},
note = {CC BY},
}
RIS
TY - JOUR
TI - Continuous SUN (stable, unique, and novel) metric for generative modeling of inorganic crystals
AU - Masahiro Negishi
AU - Hyunsoo Park
AU - Kinga O. Mastej
AU - Aron Walsh
PY - 2026
DA - 2026/06/01
JO - Machine Learning Science and Technology
DO - 10.1088/2632-2153/ae7d85
UR - https://doi.org/10.1088/2632-2153/ae7d85
AB - To address pressing scientific challenges such as climate change, increasingly sophisticated generative models are being developed to efficiently sample the large chemical space of potential functional materials. The proliferation of these models has necessitated the establishment of rigorous evaluation metrics. While uniqueness (U), novelty (N), and stability (S) of samples serve as standard metrics, their current formulations show several limitations. U and N rely on binary comparisons of crystals, rendering them dependent on heuristic thresholds, incapable of quantifying the degree of similarity, sensitive to atomic coordinate perturbations, and not invariant to sample permutation. Similarly, the binary assessment of S risks a premature exclusion of marginally unstable yet potentially novel candidates. These limitations are addressed by making the aforementioned metrics continuous. Furthermore, we integrate them into a unified metric ‘continuous SUN’ (cSUN), which offers a smoother score distribution and greater tunability than the conventional binary SUN metric. Experimental results demonstrate that our continuous metrics provide granular insights into sample distributions and secondarily serve as a soft screening score for selecting samples for further analysis. Finally, the use of cSUN as a reward signal in reinforcement learning is explored, showing that its adjustable weighting scheme effectively enhances sample diversity and convergence to a better optima in a Chemeleon2 case study.
SN - 2632-2153
ER -