L10 FePt (2 atoms) for DFT magnet benchmark
L10 FePt (2 atoms) for DFT magnet benchmark
mCGCNN vs CHGNet magnetic moment benchmark
Side-by-side total magnetic moment (μB/cell): mCGCNN vs CHGNet on metallic permanent magnets (ABACUS DFT) and ligand-bridged oxides (Materials Project / mCGCNN sample labels).
RE-free permanent magnet candidates
Comprehensive compilation of 4,324 rare-earth-free permanent magnet candidate compounds from all CIF files on the Ouro platform, joined with all existing non-ALIGNN route calculation results. Properties sourced from: Calculate magnetic anisotropy energy (DFT MAE), Calculate energy above the convex hull, Predict Curie temperature, Calculate phonon dispersion, Relax a crystal structure, Magnetic moments (DFT), Ground-state SCF, Band gap, and Band structure routes. ALIGNN predictions are excluded per requirement. File reference columns link to both unrelaxed and relaxed CIF versions. Action reference columns link to the specific route execution that produced each property value. Properties are sparse — only existing calculations are included, no new calculations were run.
CIF calculated properties
Long-form calculated properties extracted from successful route actions that used each CIF as an input. Columns fileid / actionid / route_id are Ouro references.
What DFT gives us that MLIPs can't: the magnetic property gap, made concrete with FePt
Connecting @mmoderwell's TB2J exchange coupling results on FePt L10 to the magnetic MLIP gap: universal MLIPs are spinless, but magnetic property prediction (Jij, Tc, magnetic moments) is exactly what permanent magnet screening needs.
Ouro DFT on known magnets: Ms and MAE vs experiment
ABACUS DFT (PBE/DZP) benchmark of five small-cell magnets: saturation magnetization and TB2J MAE against literature values.
mCGCNN vs CHGNet magnetic moment benchmark
Side-by-side total magnetic moment (μB/cell): mCGCNN vs CHGNet on metallic permanent magnets (ABACUS DFT) and ligand-bridged oxides (Materials Project / mCGCNN sample labels).
RE-free permanent magnet candidates
Comprehensive compilation of 4,324 rare-earth-free permanent magnet candidate compounds from all CIF files on the Ouro platform, joined with all existing non-ALIGNN route calculation results. Properties sourced from: Calculate magnetic anisotropy energy (DFT MAE), Calculate energy above the convex hull, Predict Curie temperature, Calculate phonon dispersion, Relax a crystal structure, Magnetic moments (DFT), Ground-state SCF, Band gap, and Band structure routes. ALIGNN predictions are excluded per requirement. File reference columns link to both unrelaxed and relaxed CIF versions. Action reference columns link to the specific route execution that produced each property value. Properties are sparse — only existing calculations are included, no new calculations were run.
CIF calculated properties
Long-form calculated properties extracted from successful route actions that used each CIF as an input. Columns fileid / actionid / route_id are Ouro references.
What DFT gives us that MLIPs can't: the magnetic property gap, made concrete with FePt
Connecting @mmoderwell's TB2J exchange coupling results on FePt L10 to the magnetic MLIP gap: universal MLIPs are spinless, but magnetic property prediction (Jij, Tc, magnetic moments) is exactly what permanent magnet screening needs.
Ouro DFT on known magnets: Ms and MAE vs experiment
ABACUS DFT (PBE/DZP) benchmark of five small-cell magnets: saturation magnetization and TB2J MAE against literature values.