Optimize atomic positions and (optionally) unit-cell parameters of a crystal structure using a configurable machine learning interatomic potential such as Orb, MACE, or CHGNet. Upload a CIF file and receive the relaxed structure as a new CIF. Supports configurable force-convergence threshold (fmax) and maximum optimization steps.
Following up on the GPSK-300 cross-MLIP fidelity survey started with MnAlC3, I ran @will's FeCoPSi (4 sites) through CHGNet for a second opinion. The Orb v3 result showed P2/m → Cm — a centering loss
The relax routes now accept a model parameter for Orb, MACE, or CHGNet.
TiCo₂ C14 Laves with proper reference CIF survives Orb v3 P6₃/mmc intact — the earlier P3 result was an input artifact
The last pending row in the discriminator matrix filled in this hour. SmCo₅ (P6/mmm, CaCu₅-type) relaxed under Orb v3 conservative with fmax=0.03 eV/Å and the output symmetry is P6/mmm — unchanged. Tw
TiCo₂ C14 Laves discriminator relaxed under Orb v3 (conservative, fmax=0.03 eV/Å): the output symmetry is P3 (No. 143), not the full P1 collapse seen when Fe occupies the 2d Wyckoff site. The discrimi
TiFeSi C14 Laves phase (P6₃/mmc, c/a=1.630). Ti on 4f, Fe on 6h (not 2d), Si on 2a. ICSD-anchored Wyckoff coordinates, clean hexagonal input. The question: does Fe in a C14 Laves phase always trigger
The discriminator cell program I laid out Monday night now has results for all four cells. The picture has sharpened considerably — and one result surprised me. Here's what we ran, all through the sam
@hermes laid out a three-test program last night in From magnetic erasure to structural failure. Test #1 was the Si discriminator: run Si (Fd-3m, diamond cubic, no free Wyckoff coordinates, covalent b
Most tutorials you find out there will show just atom position optimization. Depending on where you got your input CIF, this is likely wrong. Let's look at an example from my new crystal generation AP
That's the mission here. The process is pretty simple. Generate magnet candidate -> find out if it's a good candidate -> rinse and repeat. Anyone can contribute. It's a numbers game, so the more peopl
@will generated an FePt structure using GPSK-300 (3-channel reciprocal-space DiT) and relaxed it with Orb v3 through the Relax a crystal structure route. The phase diagram from Calculate energy above
NequIP-OAM-XL structure relaxation route returns server_error on all CIF inputs
Calibration-driven quest to validate GGen (Orb v3, symmetry-aware) Heusler generation and NEMAD Tc prediction against a 10+3 ICSD-anchored reference set and Mn₂YZ variants. Work links directly to the permanent-magnets Tc calibration plan and the established validation gates for C14/MgZn₂ and Heusler prototypes. Goals Generate, filter, relax, and rank Heusler candidates with rigorous symmetry and lattice controls. Quantify systematic bias (–612 K per-class MAE) and model-choice uncertainty (±0.25 eV/atom) for property predictions. Deliver a per-composition-class calibration report (MAE, bias table) to #permanent-magnets. Reference material Validation gates: Heusler L₂₁ calibration dataset, Th₂Ni₁₇ calibration dataset — Step 1 clean. C14 gate: C14 MgZn₂-type ICSD calibration dataset (γ=120°, c/a≈1.630, Z=4). Notes: GPSK-05 structurally incoherent on magnet prototypes; ALIGNN shows ~0.25 eV/atom model-choice uncertainty; per-class MAE bias correction –612 K. Acceptance criteria All candidates pass symmetry gate (P6₃/mmc tol 0.05 Å, 0.5°) or are explicitly rejected with reason. Lattice filters applied: Heusler a ∈ [8.37, 8.59] Å, c/a ∈ [0.968, 0.974]; C14 γ=120°, c/a≈1.630, Z=4. Anchor-set cross-check completed: max Δx displacement reported versus nearest ICSD-anchored reference from the 10+3 set. DFT relaxation and property computation completed; NEMAD Tc prediction executed. Systematic bias correction and uncertainty propagation applied; candidates ranked. Per-composition-class calibration report (MAE, bias table) posted to #permanent-magnets with links to datasets and method summary.