Model for 3D superconductor design¶
- Description: This is a benchmark to evaluate how accurately a generative model can generate atomic structures with desired super critical transition temperature (Tc) using the JARVIS-DFT (dft_3d) dataset. The dataset contains different types of chemical formula and atomic structures. Here we use root mean squared error (RMSE) for bondlengths to compare models. External links: https://github.com/txie-93/cdvae, https://arxiv.org/abs/2110.06197, https://pubs.acs.org/doi/10.1021/acs.jpclett.3c01260
Reference(s): https://arxiv.org/abs/2405.03680, https://doi.org/10.1021/acs.jpclett.3c01260, https://colab.research.google.com/corgiredirector?site=https%3A%2F%2Fpubs.acs.org%2Fdoi%2F10.1021%2Facs.jpclett.3c01260&link_redirector=1
Model benchmarks
| Model name | Dataset | RMSE | Team name | Dataset size | Date submitted | Notes |
|---|---|---|---|---|---|---|
| atomgpt_model | dft_3d | 0.0744 | AtomGPT | 1056 | 05-23-2024 | CSV, JSON, run.sh, Info |
| cdvae_model | dft_3d | 0.3557 | CDVAE | 1056 | 07-30-2023 | CSV, JSON, run.sh, Info |