Gate 0 verification of the kagome Weyl semimetal Co3Sn2S2: sanity card clean, Curie route agrees (137 vs 177 K), but ALIGNN's structure-only moment underestimates the measured itinerant moment fivefold.
Co₃Sn₂S₂ is the canonical magnetic Weyl semimetal: a kagome layer compound that is also a collinear ferromagnet below ~177 K, with Co moments along the c axis. It came back into focus this summer in first-principles work on broadband nonreciprocal thermal radiation (Jiang, Zhao, Zhu & Yan, arXiv:2606.14861), where the material's magnetic order is precisely what makes the thermal emission nonreciprocal. That made me curious how our own verification stack sees this structure, so I ran it through Gate 0 with the claim taken straight from the neutron literature.
Input. The neutron-refined structure from Vaqueiro & Sobany's powder neutron study (Solid State Sciences 11, 513 (2009), COD entry 1528948): shandite-type R-3m, a = 5.35739 Å, c = 13.1274 Å, Z = 3, Co on 9d, Sn on 3a/3b, S on 6c. I uploaded it here. The structure sanity card passes cleanly: R-3m is robust at every tolerance from 0.01 to 1.00 Å, minimum pair distance 2.17 Å, all 21 atoms sit exactly on their symmetry-refined ideal positions. This is a well-behaved CIF.
Claim under test. Collinear ferromagnetism with an ordered moment of roughly 0.3 μB/Co (neutron refinement gives 0.39(4) μB/Co at 15 K; bulk magnetization 0.29 to 0.32 μB/Co), and Tc = 177(10) K.
Observation 1: the moment. The ALIGNN FM-constrained moment prediction returns 0.53 μB per cell, which is 0.18 μB per formula unit. The measured value is about 0.9 μB per formula unit. That is a fivefold underestimate, and Gate 0 records the verdict as disagree (run).
Observation 2: the Curie temperature. The CHGNet-feature Curie regressor predicts 137 K against the measured 177 K, a 23% shortfall that sits comfortably inside that model's published family-level bias envelope. I would call that agreement for this class of tool (run).
What I think this means. The disagreement in Observation 1 belongs to the model, not the paper. Co₃Sn₂S₂ is an itinerant small-moment ferromagnet: the moment is set by electronic structure just above the Fermi level, not by geometry, and a structure-only regressor has no way to see it. This extends something we documented in the ALIGNN vs mCGCNN vs CHGNet benchmark
What would falsify this reading. A DFT SCF with spin-orbit coupling on this same CIF. If the DFT stack reproduces roughly 0.3 μB/Co with the c-axis easy axis, the story stands as a documented ML limitation. If DFT also collapses the moment, the interesting question moves to whether the ordered moment requires physics beyond the standard collinear treatment, such as the intermediate-temperature Weyl-state exchange physics reported by Zhang et al. (PRL 127, 117201 (2021)). That SCF run is the next gate I would run on this structure.
Receipts: the Gate 0 route records the pre-registered claim, the sanity card, and the stated limits (ALIGNN's family-dependent bias is known; a Gate 0 "agree" never certifies a ground state, and this run's "disagree" likewise does not challenge the neutron measurement). The full claim-receipt methodology is the same one behind the Mn₃GeN verification
Follow-up on this verification, since the promised spin-orbit run is done — and it came out as a two-part result.
The run that works. SOC SCF + MAE on the same neutron-refined CIF, with metal-appropriate smearing (Methfessel-Paxton, 0.01 Ry instead of the default Gaussian 0.05 Ry):
Total moment 1.02 µB/fu against ~0.85 µB/fu measured
Saturation magnetization 87 kA/m against ~74 kA/m measured
MAE 0.12 meV/fu (0.18 MJ/m³), easy axis along c (001), hard axis in-plane — the easy-axis geometry experiment reports
So the moment and the anisotropy both live in the electronic structure, and a plain PBE/DZP calculation recovers them once the settings stop fighting the physics. Caveats: experimental (unrelaxed) geometry, DZP LCAO basis, k-spacing 0.3 1/Å; the MAE magnitude is indicative, the easy axis is the robust part.
View run
The observation worth carrying. The first pass with default settings (Gaussian smearing 0.05 Ry) silently quenched the itinerant moment to 0.006 µB and returned a meaningless MAE of ~10⁻⁸ eV. Controls on the same stack (Fe, Co, FeCo, FePt, MnBi in the benchmark dataset) are all fine — the failure is specific to weak itinerant magnetism, where the exchange splitting is smaller than the smearing width. Defaults tuned on strong magnets do not transfer to itinerant ones. That observation is separate from the interpretation; if someone with more Co₃Sn₂S₂ experience reads the quenched run and sees a different cause, I want to hear it.
View quenched run
Both runs are being logged to the CIF calculated properties dataset with their smearing settings, and the leaderboard's MAE gate will use the corrected settings for itinerant candidates.