Microsoft Research Accurate Chemistry Collection, Total Atomization Energies 2025. Atomization energies at CCSD(T)CBS at CCSD(T)CBS level of theory
ColabFit
university
AI & ML interests
Development of data-driven interatomic potentials (DDIP/MLIP)
Recent Activity
View all activity
Datasets from "23 Single-Element DNPs" in ColabFit format
-
colabfit/23-Single-Element-DNPs_all_trajectories
Viewer • Updated • 109k • 82 -
colabfit/23-Single-Element-DNPs_RSCDD_2023-Al
Viewer • Updated • 5.1k • 185 -
colabfit/23-Single-Element-DNPs_RSCDD_2023-Ag
Viewer • Updated • 7.44k • 161 -
colabfit/23-Single-Element-DNPs_RSCDD_2023-Au
Viewer • Updated • 7.19k • 107
Datasets from Alex MP-20 in ColabFit format
Datasets from Minimatani et al., JCP 2023 (https://doi.org/10.1063/5.0159349)
Datasets from ANI-Al in ColabFit format
Datasets from CA-9 in ColabFit format
Datasets from Chignolin-Ab Initio Molecular Dynamics in ColabFit format
Datasets from COmprehensive Machine-learning Potential (COMP6) Benchmark Suite version 2.0 -- ColabFit format
Datasets from Martirossyan et al., All that structure matches does not glitter
Datasets from Liu, He & Mo, NPJ 2023 (https://doi.org/10.1038/s41524-023-01123-3) in ColabFit format
-
colabfit/discrepencies_and_error_metrics_NPJ_2023_interstitial_enhanced_training_set
Viewer • Updated • 219 • 8 -
colabfit/discrepencies_and_error_metrics_NPJ_2023_vacancy_enhanced_training_set
Viewer • Updated • 219 • 6 -
colabfit/discrepencies_and_error_metrics_NPJ_2023_interstitial_re_testing_set
Viewer • Updated • 301 • 11 -
colabfit/discrepencies_and_error_metrics_NPJ_2023_vacancy_re_testing_set
Viewer • Updated • 301 • 10
Datasets from GST GAP 22 in ColabFit format
Datasets from HME21 in ColabFit format
Datasets from JARVIS in ColabFit format
Datasets from Massive Atomic Diversity in ColabFit format
Datasets from MD-22 in ColabFit format
Datasets from Meta's OC20 -- Initial Structure to Relaxed Energy/Structure task -- in ColabFit format
Datasets from Meta's OC22 in ColabFit format
Datasets from Meta's Open Materials 2024 in ColabFit format
Datasets from Meta's Open Molecules 2025 in ColabFit format
Datasets from SAIT Semiconductors (https://github.com/SAITPublic/MLFF-Framework) in ColabFit format
-
colabfit/SAIT_semiconductors_ACS_2023_HfO_train
Viewer • Updated • 28k • 74 -
colabfit/SAIT_semiconductors_ACS_2023_HfO_test
Viewer • Updated • 3.51k • 10 -
colabfit/SAIT_semiconductors_ACS_2023_HfO_validation
Viewer • Updated • 3.51k • 17 -
colabfit/SAIT_semiconductors_ACS_2023_HfO_out-of-domain
Viewer • Updated • 7k • 17
Datasets from sGDML (www.sgdml.org) in ColabFit format
Datasets from SiH GAP (https://doi.org/10.1103/PhysRevMaterials.6.065603) in ColabFit format
Datasets from Vector-QM24 (https://doi.org/10.1038/s41597-025-05428-4) in ColabFit format
Datasets from xxMD -- Pengmei, Shu & Liu, Sci. Data 2024 (https://doi.org/10.1038/s41597-024-03019-3) in ColabFit format
Datasets from Meta/FAIRChem/in collaboration with Lawrence Livermore National Laboratory in ColabFit format.
3BPA datasets in ColabFit format
MD trajectory datasets from Alexandria in ColabFit format
Datasets from the ANI-2x collection in ColabFit format
Datasets from BOTnet in ColabFit format
New selections and splits from the Carbon-24 dataset as described in Martirossyan et al. (https://arxiv.org/abs/2509.12178)
Datasets from COLL in ColabFit format
Datasets from CGM-MLP in ColabFit format
Datasets from DFT-Polymorphs in ColabFit format
-
colabfit/DFT_polymorphs_PNAS_2022_PBE0_MBD_benzene_train
Viewer • Updated • 1.8k • 9 -
colabfit/DFT_polymorphs_PNAS_2022_PBE0_MBD_benzene_test
Viewer • Updated • 201 • 7 -
colabfit/DFT_polymorphs_PNAS_2022_PBE0_MBD_benzene_validation
Viewer • Updated • 201 • 8 -
colabfit/DFT_polymorphs_PNAS_2022_PBE0_MBD_glycine_train
Viewer • Updated • 3.6k • 14
Datasets from Eremin et al., CMS 2024 (https://doi.org/10.1016/j.commatsci.2023.112672) in ColabFit format
Datasets in the High Entropy Alloys family in ColabFit format
Datasets from HO LiMoNiTi (https://doi.org/10.1038/s41524-020-0323-8) in ColabFit format
-
colabfit/HO_LiMoNiTi_NPJCM_2020_LiMoNiTi_train
Viewer • Updated • 825 • 18 -
colabfit/HO_LiMoNiTi_NPJCM_2020_LiMoNiTi_validation
Viewer • Updated • 1.79k • 9 -
colabfit/HO_LiMoNiTi_NPJCM_2020_water_clusters
Viewer • Updated • 1.85k • 6 -
colabfit/HO_LiMoNiTi_NPJCM_2020_bulk_water_train_test
Viewer • Updated • 701 • 49
Related datasets containing either LiSiPS or LiGePS structures, calculated either using PBE or PBEsol DFT methods -- ColabFit format
Versions 1 and 2 of the MatPES_2025 dataset. Potential energy surface datasets with near-complete coverage of the periodic table
Datasets from mlearn -- Zuo et al., JPCA 2020 (https://doi.org/10.1021/acs.jpca.9b08723) in ColabFit format
Datasets from Meta's OC20 -- Structure to Energy/Forces task -- ColabFit format
Open Direct Air Capture 2025 datasets from Meta/FAIR Chemistry/LLNL. The largest high-quality DFT dataset for Direct Air Capture.
Datasets from Meta's OMC25 in ColabFit format
Datasets from QM-22 in ColabFit format
Datasets from sAlex, the fine-tuning dataset for Meta's OMAT24, subsampled from Alexandria, in ColabFit format
Datasets from <https://doi.org/10.1103/PhysRevB.99.214108> in ColabFit format
Datasets from Transition1x in ColabFit format
Datasets from WS22 (https://doi.org/10.5281/zenodo.7032333) in ColabFit format
Microsoft Research Accurate Chemistry Collection, Total Atomization Energies 2025. Atomization energies at CCSD(T)CBS at CCSD(T)CBS level of theory
Datasets from Meta/FAIRChem/in collaboration with Lawrence Livermore National Laboratory in ColabFit format.
Datasets from "23 Single-Element DNPs" in ColabFit format
-
colabfit/23-Single-Element-DNPs_all_trajectories
Viewer • Updated • 109k • 82 -
colabfit/23-Single-Element-DNPs_RSCDD_2023-Al
Viewer • Updated • 5.1k • 185 -
colabfit/23-Single-Element-DNPs_RSCDD_2023-Ag
Viewer • Updated • 7.44k • 161 -
colabfit/23-Single-Element-DNPs_RSCDD_2023-Au
Viewer • Updated • 7.19k • 107
3BPA datasets in ColabFit format
Datasets from Alex MP-20 in ColabFit format
MD trajectory datasets from Alexandria in ColabFit format
Datasets from Minimatani et al., JCP 2023 (https://doi.org/10.1063/5.0159349)
Datasets from the ANI-2x collection in ColabFit format
Datasets from ANI-Al in ColabFit format
Datasets from BOTnet in ColabFit format
Datasets from CA-9 in ColabFit format
New selections and splits from the Carbon-24 dataset as described in Martirossyan et al. (https://arxiv.org/abs/2509.12178)
Datasets from Chignolin-Ab Initio Molecular Dynamics in ColabFit format
Datasets from COLL in ColabFit format
Datasets from COmprehensive Machine-learning Potential (COMP6) Benchmark Suite version 2.0 -- ColabFit format
Datasets from CGM-MLP in ColabFit format
Datasets from Martirossyan et al., All that structure matches does not glitter
Datasets from DFT-Polymorphs in ColabFit format
-
colabfit/DFT_polymorphs_PNAS_2022_PBE0_MBD_benzene_train
Viewer • Updated • 1.8k • 9 -
colabfit/DFT_polymorphs_PNAS_2022_PBE0_MBD_benzene_test
Viewer • Updated • 201 • 7 -
colabfit/DFT_polymorphs_PNAS_2022_PBE0_MBD_benzene_validation
Viewer • Updated • 201 • 8 -
colabfit/DFT_polymorphs_PNAS_2022_PBE0_MBD_glycine_train
Viewer • Updated • 3.6k • 14
Datasets from Liu, He & Mo, NPJ 2023 (https://doi.org/10.1038/s41524-023-01123-3) in ColabFit format
-
colabfit/discrepencies_and_error_metrics_NPJ_2023_interstitial_enhanced_training_set
Viewer • Updated • 219 • 8 -
colabfit/discrepencies_and_error_metrics_NPJ_2023_vacancy_enhanced_training_set
Viewer • Updated • 219 • 6 -
colabfit/discrepencies_and_error_metrics_NPJ_2023_interstitial_re_testing_set
Viewer • Updated • 301 • 11 -
colabfit/discrepencies_and_error_metrics_NPJ_2023_vacancy_re_testing_set
Viewer • Updated • 301 • 10
Datasets from Eremin et al., CMS 2024 (https://doi.org/10.1016/j.commatsci.2023.112672) in ColabFit format
Datasets from GST GAP 22 in ColabFit format
Datasets in the High Entropy Alloys family in ColabFit format
Datasets from HME21 in ColabFit format
Datasets from HO LiMoNiTi (https://doi.org/10.1038/s41524-020-0323-8) in ColabFit format
-
colabfit/HO_LiMoNiTi_NPJCM_2020_LiMoNiTi_train
Viewer • Updated • 825 • 18 -
colabfit/HO_LiMoNiTi_NPJCM_2020_LiMoNiTi_validation
Viewer • Updated • 1.79k • 9 -
colabfit/HO_LiMoNiTi_NPJCM_2020_water_clusters
Viewer • Updated • 1.85k • 6 -
colabfit/HO_LiMoNiTi_NPJCM_2020_bulk_water_train_test
Viewer • Updated • 701 • 49
Datasets from JARVIS in ColabFit format
Related datasets containing either LiSiPS or LiGePS structures, calculated either using PBE or PBEsol DFT methods -- ColabFit format
Datasets from Massive Atomic Diversity in ColabFit format
Versions 1 and 2 of the MatPES_2025 dataset. Potential energy surface datasets with near-complete coverage of the periodic table
Datasets from MD-22 in ColabFit format
Datasets from mlearn -- Zuo et al., JPCA 2020 (https://doi.org/10.1021/acs.jpca.9b08723) in ColabFit format
Datasets from Meta's OC20 -- Initial Structure to Relaxed Energy/Structure task -- in ColabFit format
Datasets from Meta's OC20 -- Structure to Energy/Forces task -- ColabFit format
Datasets from Meta's OC22 in ColabFit format
Open Direct Air Capture 2025 datasets from Meta/FAIR Chemistry/LLNL. The largest high-quality DFT dataset for Direct Air Capture.
Datasets from Meta's Open Materials 2024 in ColabFit format
Datasets from Meta's OMC25 in ColabFit format
Datasets from Meta's Open Molecules 2025 in ColabFit format
Datasets from QM-22 in ColabFit format
Datasets from SAIT Semiconductors (https://github.com/SAITPublic/MLFF-Framework) in ColabFit format
-
colabfit/SAIT_semiconductors_ACS_2023_HfO_train
Viewer • Updated • 28k • 74 -
colabfit/SAIT_semiconductors_ACS_2023_HfO_test
Viewer • Updated • 3.51k • 10 -
colabfit/SAIT_semiconductors_ACS_2023_HfO_validation
Viewer • Updated • 3.51k • 17 -
colabfit/SAIT_semiconductors_ACS_2023_HfO_out-of-domain
Viewer • Updated • 7k • 17
Datasets from sAlex, the fine-tuning dataset for Meta's OMAT24, subsampled from Alexandria, in ColabFit format
Datasets from sGDML (www.sgdml.org) in ColabFit format
Datasets from <https://doi.org/10.1103/PhysRevB.99.214108> in ColabFit format
Datasets from SiH GAP (https://doi.org/10.1103/PhysRevMaterials.6.065603) in ColabFit format
Datasets from Transition1x in ColabFit format
Datasets from Vector-QM24 (https://doi.org/10.1038/s41597-025-05428-4) in ColabFit format
Datasets from WS22 (https://doi.org/10.5281/zenodo.7032333) in ColabFit format
Datasets from xxMD -- Pengmei, Shu & Liu, Sci. Data 2024 (https://doi.org/10.1038/s41597-024-03019-3) in ColabFit format