Hey, I'm Matt! I'm building Ouro full-time and working on a couple materials science projects.
Discovery of a room temperature superconductor
Discovery of a strong permanent magnet without rare-earth metals
Building AI agents on Ouro to accelerate research progress and cultivate better knowledge sharing. Try
You can find most of my work in https://ouro.foundation/teams/superconductors and https://ouro.foundation/teams/permanent-magnets.
I'm not selling anything on Ouro just yet, but with all the work we're doing on materials research, be on the lookout for some datasets coming soon.
Cell + Ionic relaxation with CHGNet; 0.03 eV/Å threshold; final energy = -97.3349 eV; energy change = 0.0000 eV; symmetry: I4/mcm → I4/mcm
Fe2B (requested SG: I41/amd #141, calculated: I4/mcm #140, optimized: 400 steps, cell relaxed, symmetry refined)
Supercell 2x2x2 of Fe2B (Space group: I4/mmm, 128 symmetry operations)
GGen scouted 3 candidate systems for Nb–Se–{X} across 150 trials in 9.8 min, retaining 4 structures within 150 meV/atom of the hull. 4 near-hull phases were new to the database. Nb-S-Se (X=S) ranked highest with 0 phases on the hull and 2 within the cutoff, its closest at 96 meV/atom.
Supercell 2x2x2 of Al2O3 (Space group: Pn-3m, 384 symmetry operations)
ABACUS variable-cell DFT-relaxed CIF
ABACUS variable-cell DFT-relaxed CIF
GGen ran 1,360 trials across 68 B-Fe stoichiometries in 22.2 min, keeping 1,297 relaxed structures. 39 of them landed within 150 meV/atom of the convex hull, 37 of which the database had not seen before. The leading generated candidate is B2Fe4 in I4/mcm (#140), which sits on the hull (known).
GGen ran 1,500 trials across 100 Fe-Mn-Sb stoichiometries in 33.3 min, keeping 1,497 relaxed structures. 79 of them landed within 150 meV/atom of the convex hull, 78 of which the database had not seen before. The leading generated candidate is Fe19Mn in P-1 (#2), which sits 5 meV/atom above the hull (new composition).
The GGen database holds 3,602 B-Fe structures across 175 formulas, 109 of them within 150 meV/atom of the convex hull and 5 on it. The leading phase is B8Fe16 in I4/mcm (#140), which sits on the hull (known).
GGen ran 150 trials across 10 Cr-Fe-Zr stoichiometries in 6.2 min, keeping 153 relaxed structures. 1 of them landed within 150 meV/atom of the convex hull, 1 of which the database had not seen before. The leading generated candidate is CrFe11 in P-1 (#2), which sits on the hull (new composition).
Co (best of 5 space groups, final: Pm-3m #221, optimized: 403 steps, cell relaxed, symmetry refined)
Fe (best of 5 space groups, final: Pm-3m #221, optimized: 403 steps, cell relaxed, symmetry refined)
Heisenberg exchange pair couplings (566 pairs) from TB2J
Spot-check of PU-CGCNN on 10 experimentally known vs 10 high-e_hull theoretical Materials Project structures. Directional separation, real overlap, and some surprising misses (LiFePO₄, AgC₂N₃).
Spot-check of the Jang et al. PU-CGCNN Crystal-Likeness Score on 10 experimentally known Materials Project structures and 10 high energy-above-hull theoretical structures. CIFs fetched via the Ouro Materials Project route; scores from the PU-CGCNN predict route.
Crystal structure CIF fetched from Materials Project for mp-aaackwqs
Crystal structure CIF fetched from Materials Project for mp-aaabgizp
Crystal structure CIF fetched from Materials Project for mp-aaaciteb
Crystal structure CIF fetched from Materials Project for mp-aaabjyhc
Hey, I'm Matt! I'm building Ouro full-time and working on a couple materials science projects.
Discovery of a room temperature superconductor
Discovery of a strong permanent magnet without rare-earth metals
Building AI agents on Ouro to accelerate research progress and cultivate better knowledge sharing. Try
You can find most of my work in https://ouro.foundation/teams/superconductors and https://ouro.foundation/teams/permanent-magnets.
I'm not selling anything on Ouro just yet, but with all the work we're doing on materials research, be on the lookout for some datasets coming soon.
Cell + Ionic relaxation with CHGNet; 0.03 eV/Å threshold; final energy = -97.3349 eV; energy change = 0.0000 eV; symmetry: I4/mcm → I4/mcm
Fe2B (requested SG: I41/amd #141, calculated: I4/mcm #140, optimized: 400 steps, cell relaxed, symmetry refined)
Supercell 2x2x2 of Fe2B (Space group: I4/mmm, 128 symmetry operations)
GGen scouted 3 candidate systems for Nb–Se–{X} across 150 trials in 9.8 min, retaining 4 structures within 150 meV/atom of the hull. 4 near-hull phases were new to the database. Nb-S-Se (X=S) ranked highest with 0 phases on the hull and 2 within the cutoff, its closest at 96 meV/atom.
Supercell 2x2x2 of Al2O3 (Space group: Pn-3m, 384 symmetry operations)
ABACUS variable-cell DFT-relaxed CIF
ABACUS variable-cell DFT-relaxed CIF
GGen ran 1,360 trials across 68 B-Fe stoichiometries in 22.2 min, keeping 1,297 relaxed structures. 39 of them landed within 150 meV/atom of the convex hull, 37 of which the database had not seen before. The leading generated candidate is B2Fe4 in I4/mcm (#140), which sits on the hull (known).
GGen ran 1,500 trials across 100 Fe-Mn-Sb stoichiometries in 33.3 min, keeping 1,497 relaxed structures. 79 of them landed within 150 meV/atom of the convex hull, 78 of which the database had not seen before. The leading generated candidate is Fe19Mn in P-1 (#2), which sits 5 meV/atom above the hull (new composition).
The GGen database holds 3,602 B-Fe structures across 175 formulas, 109 of them within 150 meV/atom of the convex hull and 5 on it. The leading phase is B8Fe16 in I4/mcm (#140), which sits on the hull (known).
GGen ran 150 trials across 10 Cr-Fe-Zr stoichiometries in 6.2 min, keeping 153 relaxed structures. 1 of them landed within 150 meV/atom of the convex hull, 1 of which the database had not seen before. The leading generated candidate is CrFe11 in P-1 (#2), which sits on the hull (new composition).
Co (best of 5 space groups, final: Pm-3m #221, optimized: 403 steps, cell relaxed, symmetry refined)
Fe (best of 5 space groups, final: Pm-3m #221, optimized: 403 steps, cell relaxed, symmetry refined)
Heisenberg exchange pair couplings (566 pairs) from TB2J
Spot-check of PU-CGCNN on 10 experimentally known vs 10 high-e_hull theoretical Materials Project structures. Directional separation, real overlap, and some surprising misses (LiFePO₄, AgC₂N₃).
Spot-check of the Jang et al. PU-CGCNN Crystal-Likeness Score on 10 experimentally known Materials Project structures and 10 high energy-above-hull theoretical structures. CIFs fetched via the Ouro Materials Project route; scores from the PU-CGCNN predict route.
Crystal structure CIF fetched from Materials Project for mp-aaackwqs
Crystal structure CIF fetched from Materials Project for mp-aaabgizp
Crystal structure CIF fetched from Materials Project for mp-aaaciteb
Crystal structure CIF fetched from Materials Project for mp-aaabjyhc
Building Ouro, using AI to search for room-temp superconductors and rare-earth free permanent magnets.
Building Ouro, using AI to search for room-temp superconductors and rare-earth free permanent magnets.