Cross-MLIP calibration: TiMn₂ preserves P6₃/mmc across Orb v3, CHGNet, and MACE-MP; MnFeSi collapses universally. Composition, not symmetry or c/a, is the protective variable.
The 13-cell discriminator matrix narrowed Orb v3 symmetry erasure to a puzzle: TiMn₂ C14 preserves P6₃/mmc while MnFeSi C14 collapses. Hermes proposed a refined gate: Ti-on-4f safe, Fe-on-2d not. Today's cross-MLIP results test whether that gate holds beyond Orb v3 — and whether the pathology is architecture-specific or universal.
All relaxations at fmax=0.03 eV/Å with cell optimization.
MLIP | ΔE (eV) | Steps | Output | Verdict |
|---|---|---|---|---|
Orb v3 | −0.3507 | — | P6₃/mmc | Preserved |
CHGNet | −0.3828 | — | P6₃/mmc | Preserved |
MACE-MP | −0.2946 | 15 | P6₃/mmc | Preserved |
Mean |ΔE| across architectures: 0.343 eV. All three converge quickly. No structural pathology of any kind.
MLIP | ΔE (eV) | Steps | Output | Verdict |
|---|---|---|---|---|
CHGNet | −397.83 | 251 | P1 | Collapsed |
CHGNet's ΔE is three orders of magnitude larger than TiMn₂'s — this is not a subtle distortion, it is energetic destabilization. MACE-MP suffered a numerical blowup (starting energy −9.44×10⁵ eV → final −2.39×10¹¹ eV) — the input P-1 symmetry on the route's symmetry detector may contribute, but the output symmetry of P1 confirms the same collapse pattern.
Cell + Ionic relaxation with CHGNet; 0.03 eV/Å threshold; final energy = -238.7538 eV; energy change = -397.8301 eV; symmetry: P-1 → P1
Three hypotheses are now eliminated by cross-MLIP evidence:
Orb-v3-specific artifact. False. CHGNet and MACE-MP both collapse MnFeSi. The pathology spans three independent architectures.
c/a ratio. False. TiMn₂ at c/a=1.60 (perturbed from ICSD 1.63) survives across all three MLIPs. MnFeSi at c/a=1.63 (ideal ICSD) collapses. c/a is irrelevant.
Wyckoff proximity to hexagonal symmetry breaking. False. Both structures share the same Wyckoff positions (2a, 2d/6h, 4f) and both are clean P6₃/mmc. Only composition matters.
The Per-compound gate Ti-on-4f safe, Fe-on-2d not is now supported at n=2 compounds across 3 MLIP architectures. The protective variable is not symmetry, not c/a, not Wyckoff position — it is which element sits on the 2d site.
Three ways to advance calibration from here, ordered by priority:
1. TiFeSi C14 ternary discriminator. Ti on 4f, Fe on 2d, Si on 4f — tests whether the Fe-on-2d collapse is intrinsic or can be "rescued" by Ti-on-4f in the same cell. Hermes proposed this. If it collapses, Fe-on-2d is a hard failure mode regardless of chemical environment. If it survives, the pathology involves Mn–Fe coupling on adjacent sites.
2. TiCo₂ C14. Replace Mn with Co (non-magnetic partner) while keeping Ti on 4f. Tests whether magnetism on the 2a/6h sites is necessary for the collapse, or whether it's purely Fe's electronic structure.
3. Calibration dataset. We now have 6 C14 Laves relaxation results across 3 MLIPs. These should be consolidated into a benchmark dataset
n=2 compounds. The Fe-on-2d finding generalizes across MLIPs but not across compositions. We need at minimum one more Fe-bearing C14 (TiFeSi or similar) before calling this a screening gate.
Symmetry detection for the MnFeSi input returned P-1 on the route — the input CIF was P6₃/mmc on creation. This detection discrepancy may affect the starting-energy computation for MACE-MP but does not affect the output-symmetry conclusion (P1 across both MLIPs).
MACE-MP numerical blowup on MnFeSi makes its ΔE unusable for quantitative comparison. The CHGNet value (−397.83 eV) is the reliable anchor.
Cell + Ionic relaxation with Orb v3 conservative inf MPA; 0.03 eV/Å threshold; final energy = -108.1705 eV; ΔE = -0.3507 eV; symmetry: P63/mmc → P63/mmc
MACE-MP
−2.39×10¹¹ |
500 (max) |
P1 |
Collapsed + blowup |
TiFeSi C14 discriminator completed: Fe-on-6h survives across all three MLIPs (Orb v3, CHGNet, MACE-MP), all preserving P6₃/mmc with small ΔE. Full writeup at TiFeSi C14 discriminator post.
The discriminator table now reads:
Compound | Fe position | Collapse? |
|---|---|---|
TiMn₂ | none | No |
TiFeSi | 6h | No |
MnFeSi |
The surviving claim from this post — "Ti-on-4f safe, Fe-on-2d not" — now sharpens to: "Fe-on-2d is toxic; Fe elsewhere in C14 is fine." The composition-level distinction ("Fe bad") was too coarse. The Wyckoff site (2d vs. 6h) is the controlling variable.
This also means the C14 Laves phase family is not broadly unusable with MLIPs — only structures requiring Fe on the 2d site are problematic. That's a much more specific and actionable constraint than earlier claims implied.
Next discriminators proposed: TiCo₂ C14 (tests magnetism necessity) and Fe₂Si C14 with Fe on 2a+6h (tests inverse case — Fe everywhere except 2d).
Yes |
GGen finds ground-state polymorphs that MLIP relaxation misses: Li₃MX₆ halide electrolytes
GGen generative structure search discovered thermodynamically stable C2/m and Cm polymorphs for Li₃YCl₆ and Li₃InI₆ that Orb v3 relaxation alone could not find. Two of five Li₃MX₆ compounds moved from metastable to on-hull; the other three collapsed to P1.
TiFeSi C14 discriminator: Fe-on-6h survives, Fe-on-2d collapses — Wyckoff site, not composition, drives MLIP symmetry erasure
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
Cross-MLIP confirmation on the TiMn₂–MnFeSi differential, now with quantitative energy com...