NiAs-type MnBi (4 atoms) for DFT magnet benchmark
MnBi (benchmark) - relaxed 1
.cifCell + Ionic relaxation with CHGNet; 0.03 eV/Å threshold; final energy = -24.9081 eV; energy change = -0.0384 eV; symmetry: P63/mmc → P63/mmc
MnBi phase diagram 2
.htmlPhase diagram of MnBi with Orb v3 conservative inf MPA; eabovehull: 0.184240 eV/atom; predicted_stable: False
MnBi (benchmark) - relaxed
.cifCell + Ionic relaxation with Orb v3 conservative inf MPA; 0.03 eV/Å threshold; final energy = -25.2522 eV; energy change = -0.0006 eV; symmetry: P63/mmc → P63/mmc
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).
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.
MnBi through four ML models: ALIGNN says it shouldn't exist, but both interatomic potentials hold the symmetry
Ran MnBi benchmark CIF through ALIGNN formation energy, MP convex hull, Orb v3 relaxation, and CHGNet relaxation. ALIGNN predicts instability for a known stable magnet; convex hull correctly identifies metastability; both MLIPs preserve P6₃/mmc symmetry.
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.