Dataset
Massive_Atomic_Diversity_MAD-1.5_PBE
Species content of dataset
Name :
Massive_Atomic_Diversity_MAD-1.5_PBE
Authors :
Cesare Malosso, Filippo Bigi, Paolo Pegolo, Joseph W. Abbott, Philip Loche, Mariana Rossi, Michele Ceriotti, Arslan Mazitov
Description :
A subset of the MAD-1.5 (Massive Atomic Diversity version 1.5) structures recomputed with the PBE GGA functional, covering the MAD-1 subsets (MC3D, MC3D-rattled, MC3D-random, MC3D-surface, MC3D-cluster, MC2D, SHIFTML-molcrys, SHIFTML-molfrags) plus monomers and MC3D-random-extended from the new MAD-1.5 subsets. All DFT settings are consistent with the r2SCAN calculations: FHI-aims (version 250806) all-electron code with tight NAO basis sets (species defaults 2020), 8 Angstrom^-1 k-point density for periodic systems, Gaussian smearing of 0.05 eV, and SCF convergence thresholds of 1e-6 eV (energy), 1e-4 eV/Angstrom (forces), and 1e-5 e*a0^-3 (electron density). Cross-validation splits are consistent with the r2SCAN train/val/test splits; this file contains all three splits combined. PBE targets were used in PET-MAD-1.5 model training with separate prediction heads alongside r2SCAN targets, improving force accuracy by approximately 25% relative to r2SCAN-only training. As a lower level of theory, this dataset is less carefully curated than the primary r2SCAN dataset; PBE heads are discarded from the final released models.
Cite As :
Malosso, C., Bigi, F., Pegolo, P., Abbott, J. W., Loche, P., Rossi, M., Ceriotti, M., and Mazitov, A. "Massive Atomic Diversity MAD-1.5 PBE." ColabFit, 2026. https://doi.org/None.
ColabFit ID :
Extended ID :
Date Added :
2026-05-21
License :
CC-BY-4.0
Downloads :
0
Num. Configurations :
101,493
Num. Atoms :
2,620,250
Calculated Property Types :
atomic_forces
atomization_energy
cauchy_stress
energy
Elements :
Ac (0.03%)
Ag (0.45%)
Al (0.86%)
Am (0.03%)
Ar (0.04%)
As (0.67%)
At (0.03%)
Au (0.29%)
B (0.93%)
Ba (0.41%)
Be (0.28%)
Bi (0.48%)
Bk (0.03%)
Br (0.87%)
C (13.3%)
Ca (0.76%)
Cd (0.42%)
Ce (0.04%)
Cf (0.03%)
Cl (2.43%)
Cm (0.03%)
Co (0.62%)
Cr (0.4%)
Cs (0.7%)
Cu (0.81%)
Dy (0.03%)
Er (0.04%)
Es (0.03%)
Eu (0.03%)
F (3.49%)
Fe (0.69%)
Fm (0.03%)
Fr (0.03%)
Ga (0.61%)
Gd (0.03%)
Ge (0.81%)
H (18.19%)
He (0.04%)
Hf (0.42%)
Hg (0.33%)
Ho (0.03%)
I (0.85%)
In (0.46%)
Ir (0.27%)
K (1.09%)
Kr (0.04%)
La (0.04%)
Li (0.86%)
Lu (0.04%)
Md (0.03%)
Mg (0.51%)
Mn (0.52%)
Mo (0.54%)
N (5.72%)
Na (1.0%)
Nb (0.61%)
Nd (0.04%)
Ne (0.04%)
Ni (0.82%)
No (0.03%)
Np (0.03%)
O (18.48%)
Os (0.13%)
P (1.6%)
Pa (0.03%)
Pb (0.49%)
Pd (0.47%)
Pm (0.03%)
Po (0.05%)
Pr (0.04%)
Pt (0.36%)
Pu (0.03%)
Ra (0.03%)
Rb (0.58%)
Re (0.24%)
Rh (0.31%)
Rn (0.04%)
Ru (0.22%)
S (3.14%)
Sb (0.62%)
Sc (0.41%)
Se (1.49%)
Si (1.16%)
Sm (0.03%)
Sn (0.58%)
Sr (0.71%)
Ta (0.41%)
Tb (0.03%)
Tc (0.09%)
Te (0.79%)
Th (0.03%)
Ti (0.62%)
Tl (0.42%)
Tm (0.04%)
U (0.03%)
V (0.56%)
W (0.32%)
Xe (0.06%)
Y (0.67%)
Yb (0.04%)
Zn (0.63%)
Zr (0.69%)
Methods :
DFT-PBE
Software :
FHI-aims v250806
Publication Link :
Data Source Link :
Spec File :
Configuration Sets by Name :
Configuration Sets by ID :
Name: Massive_Atomic_Diversity_MAD-1.5_PBE
Extended ID: Massive_Atomic_Diversity_MAD-1.5_PBE__Malosso-Bigi-Pegolo-Abbott-Loche-Rossi-Ceriotti-Mazitov__DS_zs8bsrqnmyn0_0
Description: A subset of the MAD-1.5 (Massive Atomic Diversity version 1.5) structures recomputed with the PBE GGA functional, covering the MAD-1 subsets (MC3D, MC3D-rattled, MC3D-random, MC3D-surface, MC3D-cluster, MC2D, SHIFTML-molcrys, SHIFTML-molfrags) plus monomers and MC3D-random-extended from the new MAD-1.5 subsets. All DFT settings are consistent with the r2SCAN calculations: FHI-aims (version 250806) all-electron code with tight NAO basis sets (species defaults 2020), 8 Angstrom^-1 k-point density for periodic systems, Gaussian smearing of 0.05 eV, and SCF convergence thresholds of 1e-6 eV (energy), 1e-4 eV/Angstrom (forces), and 1e-5 e*a0^-3 (electron density). Cross-validation splits are consistent with the r2SCAN train/val/test splits; this file contains all three splits combined. PBE targets were used in PET-MAD-1.5 model training with separate prediction heads alongside r2SCAN targets, improving force accuracy by approximately 25% relative to r2SCAN-only training. As a lower level of theory, this dataset is less carefully curated than the primary r2SCAN dataset; PBE heads are discarded from the final released models.
Authors:
Cesare Malosso
Filippo Bigi
Paolo Pegolo
Joseph W. Abbott
Philip Loche
Mariana Rossi
Michele Ceriotti
Arslan Mazitov
DOI: None
Calculated Property Types:
atomic_forces
atomization_energy
cauchy_stress
energy
Elements:
Ac (0.03%)
Ag (0.45%)
Al (0.86%)
Am (0.03%)
Ar (0.04%)
As (0.67%)
At (0.03%)
Au (0.29%)
B (0.93%)
Ba (0.41%)
Be (0.28%)
Bi (0.48%)
Bk (0.03%)
Br (0.87%)
C (13.3%)
Ca (0.76%)
Cd (0.42%)
Ce (0.04%)
Cf (0.03%)
Cl (2.43%)
Cm (0.03%)
Co (0.62%)
Cr (0.4%)
Cs (0.7%)
Cu (0.81%)
Dy (0.03%)
Er (0.04%)
Es (0.03%)
Eu (0.03%)
F (3.49%)
Fe (0.69%)
Fm (0.03%)
Fr (0.03%)
Ga (0.61%)
Gd (0.03%)
Ge (0.81%)
H (18.19%)
He (0.04%)
Hf (0.42%)
Hg (0.33%)
Ho (0.03%)
I (0.85%)
In (0.46%)
Ir (0.27%)
K (1.09%)
Kr (0.04%)
La (0.04%)
Li (0.86%)
Lu (0.04%)
Md (0.03%)
Mg (0.51%)
Mn (0.52%)
Mo (0.54%)
N (5.72%)
Na (1.0%)
Nb (0.61%)
Nd (0.04%)
Ne (0.04%)
Ni (0.82%)
No (0.03%)
Np (0.03%)
O (18.48%)
Os (0.13%)
P (1.6%)
Pa (0.03%)
Pb (0.49%)
Pd (0.47%)
Pm (0.03%)
Po (0.05%)
Pr (0.04%)
Pt (0.36%)
Pu (0.03%)
Ra (0.03%)
Rb (0.58%)
Re (0.24%)
Rh (0.31%)
Rn (0.04%)
Ru (0.22%)
S (3.14%)
Sb (0.62%)
Sc (0.41%)
Se (1.49%)
Si (1.16%)
Sm (0.03%)
Sn (0.58%)
Sr (0.71%)
Ta (0.41%)
Tb (0.03%)
Tc (0.09%)
Te (0.79%)
Th (0.03%)
Ti (0.62%)
Tl (0.42%)
Tm (0.04%)
U (0.03%)
V (0.56%)
W (0.32%)
Xe (0.06%)
Y (0.67%)
Yb (0.04%)
Zn (0.63%)
Zr (0.69%)
Methods:
DFT-PBE
Software:
FHI-aims v250806
Number of Configurations: 101,493
Number of Atoms: 2,620,250
Publication Link: https://doi.org/10.48550/arXiv.2603.02089
Data Source Link: https://doi.org/10.24435/materialscloud:jc-9f
Dataset viewer powered by Hugging Face
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.