Introduces the RealMat-BaG benchmark showing fundamental generalization limits of ML models when predicting experimental bandgaps from DFT-trained data.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cond-mat.mtrl-sci 3years
2026 3representative citing papers
Three foundation MLIPs succeed on scalar breathing order, fail the symmetry of vector Jahn–Teller order, and cannot access on-site multiplet crossovers in d4/d6/d7 perovskites.
A hierarchical ALIGNN + ALIGNN-FF + DFT pipeline recovers experimental average voltages within 0.3 V on four commercial Li-ion cathodes and ranks large materials databases into surrogate-level shortlists.
citing papers explorer
-
Benchmarking bandgap prediction in semiconductors under experimental and realistic evaluation settings
Introduces the RealMat-BaG benchmark showing fundamental generalization limits of ML models when predicting experimental bandgaps from DFT-trained data.
-
Bond, orbital and spin order in d4/d6/d7 perovskite oxides: successes and limitations of foundation interatomic potentials
Three foundation MLIPs succeed on scalar breathing order, fail the symmetry of vector Jahn–Teller order, and cannot access on-site multiplet crossovers in d4/d6/d7 perovskites.
-
BatteryMat: a hierarchical machine-learning and DFT framework for average-voltage screening of lithium-ion cathode materials
A hierarchical ALIGNN + ALIGNN-FF + DFT pipeline recovers experimental average voltages within 0.3 V on four commercial Li-ion cathodes and ranks large materials databases into surrogate-level shortlists.