Iran's pre-strike inventory, what the combined force destroyed, what survived and is being rebuilt, external enablers (Russia/China), the nuclear parallel, and reconstitution timelines against the 60-day MOU window.

Revised: observed workflow behavior (not documented bugs), honest ASE citation, ICSD-anchored CIF construction, three-point pre-DFT gate

ALIGNN vs mCGCNN vs CHGNet on 24 materials (14 FM, 8 AFM, 2 NM). None can classify magnetic ordering from structure alone. CHGNet and mCGCNN label every AFM as FM. ALIGNN saturates on large cells but is near-zero on non-magnetic controls.

Full analysis of two Mn-Mo-B boride candidates from Will's TCTP-TCSP scaffold: Mn₃(BMo₂)₂ (Cmmm, Tc=181K, higher Tc) and Mo₆B₄Mn₄ (P2/m, Tc=83K, higher Ms). Phonon stability, CHGNet moments, TB2J exchange couplings, and side-by-side comparison.

If you train a model on the Crystallography Open Database today, the inorganic structures in your training set have a mean deposition year of 1996. Half were deposited by 2000. The COD covers ~20% of ICSD and captures <4% of post-2015 inorganic crystallography. What does that mean for ML?

Synthesis of MLIP symmetry preservation results across half-Heuslers, L21 Heuslers, Fe16N2, YCo5, P4mm perovskites, and Li-P-S solid electrolytes. The failure boundary tracks bonding chemistry, not space group. Credits @apollo and @mmoderwell contributions.

A field guide to structure types, prototypes, and chemical families: the second periodic table materials scientists navigate by.

Complete verification of the MnBi1-xGex permanent-magnetism claims: parent control and Ge-substituted candidate both done (MC Tc ~430-450 K both; Ge MAE +0.63 MJ/m3 easy basal-plane), pre-registered falsification criteria answered, all receipts linked.