Dataset
sAlex_train
Download Original Data Files
7.5 GB
Species content of dataset
Name :
sAlex_train
Extended ID :
ColabFit ID :
Files :
Description :
The training split of sAlex. sAlex is a subsample of the Alexandria dataset that was used to fine tune the OMat24 (Open Materials 2024) models. From the site: sAlex was created by removing structures matched in WBM and only sampling structure along a trajectory with an energy difference greater than 10 meV/atom.
Authors :
Luis Barroso-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, C. Lawrence Zitnick, Zachary W. Ulissi
DOI :
10.60732/efbb7935
https://commons.datacite.org/doi.org/10.60732/efbb7935
https://doi.datacite.org/dois/10.60732%2Fefbb7935
https://doi.org/10.60732/efbb7935
Cite as: Barroso-Luque, L., Shuaibi, M., Fu, X., Wood, B. M., Dzamba, M., Gao, M., Rizvi, A., Zitnick, C. L., and Ulissi, Z. W. "sAlex train." ColabFit, 2025. https://doi.org/10.60732/efbb7935.
For other citation formats, see the DataCite Fabrica page for this dataset.
For other citation formats, see the DataCite Fabrica page for this dataset.
Num. Configurations :
10,345,613
Num. Atoms :
106,888,622
Downloads :
0
Calculated Property Types :
atomic_forces
cauchy_stress
energy
Elements :
Ac (1.37%)
Ag (1.19%)
Al (1.24%)
Ar (0.0%)
As (0.79%)
Au (1.56%)
B (0.65%)
Ba (0.89%)
Be (0.43%)
Bi (0.77%)
Br (1.32%)
C (0.59%)
Ca (0.84%)
Cd (1.3%)
Ce (0.89%)
Cl (1.58%)
Co (0.95%)
Cr (0.5%)
Cs (0.65%)
Cu (1.17%)
Dy (1.77%)
Er (1.67%)
Eu (0.11%)
F (1.95%)
Fe (0.79%)
Ga (1.34%)
Gd (0.13%)
Ge (0.86%)
H (7.15%)
He (0.0%)
Hf (0.44%)
Hg (1.7%)
Ho (1.75%)
I (0.99%)
In (1.52%)
Ir (0.94%)
K (0.95%)
Kr (0.0%)
La (2.01%)
Li (1.33%)
Lu (0.12%)
Mg (1.3%)
Mn (0.85%)
Mo (0.43%)
N (1.34%)
Na (0.93%)
Nb (0.36%)
Nd (1.81%)
Ne (0.0%)
Ni (1.31%)
Np (0.49%)
O (5.9%)
Os (0.55%)
P (0.9%)
Pa (0.48%)
Pb (1.07%)
Pd (1.85%)
Pm (1.96%)
Pr (1.81%)
Pt (1.6%)
Pu (0.96%)
Rb (0.77%)
Re (0.38%)
Rh (1.41%)
Ru (0.9%)
S (2.16%)
Sb (0.89%)
Sc (1.14%)
Se (1.97%)
Si (0.91%)
Sm (1.77%)
Sn (1.05%)
Sr (0.8%)
Ta (0.43%)
Tb (1.83%)
Tc (0.51%)
Te (1.57%)
Th (0.8%)
Ti (0.55%)
Tl (1.52%)
Tm (1.7%)
U (0.34%)
V (0.47%)
W (0.36%)
Xe (0.0%)
Y (1.75%)
Yb (0.01%)
Zn (1.26%)
Zr (0.66%)
Methods :
DFT-PBE+U
Software :
VASP
Publication Link :
Data Source Link :
Configuration Sets by Name :
Configuration Sets by ID :
Name: sAlex_train
Extended ID: sAlex_train__Barroso-Luque-Shuaibi-Fu-Wood-Dzamba-Gao-Rizvi-Zitnick-Ulissi__DS_gxjhn6vdjnxg_0
Description: The training split of sAlex. sAlex is a subsample of the Alexandria dataset that was used to fine tune the OMat24 (Open Materials 2024) models. From the site: sAlex was created by removing structures matched in WBM and only sampling structure along a trajectory with an energy difference greater than 10 meV/atom.
Authors:
Luis Barroso-Luque
Muhammed Shuaibi
Xiang Fu
Brandon M. Wood
Misko Dzamba
Meng Gao
Ammar Rizvi
C. Lawrence Zitnick
Zachary W. Ulissi
DOI: 10.60732/efbb7935
Calculated Property Types:
atomic_forces
cauchy_stress
energy
Elements:
Ac (1.37%)
Ag (1.19%)
Al (1.24%)
Ar (0.0%)
As (0.79%)
Au (1.56%)
B (0.65%)
Ba (0.89%)
Be (0.43%)
Bi (0.77%)
Br (1.32%)
C (0.59%)
Ca (0.84%)
Cd (1.3%)
Ce (0.89%)
Cl (1.58%)
Co (0.95%)
Cr (0.5%)
Cs (0.65%)
Cu (1.17%)
Dy (1.77%)
Er (1.67%)
Eu (0.11%)
F (1.95%)
Fe (0.79%)
Ga (1.34%)
Gd (0.13%)
Ge (0.86%)
H (7.15%)
He (0.0%)
Hf (0.44%)
Hg (1.7%)
Ho (1.75%)
I (0.99%)
In (1.52%)
Ir (0.94%)
K (0.95%)
Kr (0.0%)
La (2.01%)
Li (1.33%)
Lu (0.12%)
Mg (1.3%)
Mn (0.85%)
Mo (0.43%)
N (1.34%)
Na (0.93%)
Nb (0.36%)
Nd (1.81%)
Ne (0.0%)
Ni (1.31%)
Np (0.49%)
O (5.9%)
Os (0.55%)
P (0.9%)
Pa (0.48%)
Pb (1.07%)
Pd (1.85%)
Pm (1.96%)
Pr (1.81%)
Pt (1.6%)
Pu (0.96%)
Rb (0.77%)
Re (0.38%)
Rh (1.41%)
Ru (0.9%)
S (2.16%)
Sb (0.89%)
Sc (1.14%)
Se (1.97%)
Si (0.91%)
Sm (1.77%)
Sn (1.05%)
Sr (0.8%)
Ta (0.43%)
Tb (1.83%)
Tc (0.51%)
Te (1.57%)
Th (0.8%)
Ti (0.55%)
Tl (1.52%)
Tm (1.7%)
U (0.34%)
V (0.47%)
W (0.36%)
Xe (0.0%)
Y (1.75%)
Yb (0.01%)
Zn (1.26%)
Zr (0.66%)
Methods:
DFT-PBE+U
Software:
VASP
Number of Configurations: 10,345,613
Number of Atoms: 106,888,622
Publication Link: https://doi.org/10.48550/arXiv.2410.12771
Data Source Link: https://fair-chem.github.io/inorganic_materials/datasets/omat24.html
No uploaded content is transferred in ownership from the original creators to ColabFit. All content is distributed under the license specified by its contributor who has stated that he or she has the authority to share it under the specified license.