Prior revPBE-D3 DFT simulations of liquid water showed >20% variation in diffusion and 10% in density; new ML-potential-enabled benchmarks resolve these to consistent values across six codes, attributing prior errors to basis-set and sampling issues.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.chem-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How reproducible are first-principles simulations of liquid water?
Prior revPBE-D3 DFT simulations of liquid water showed >20% variation in diffusion and 10% in density; new ML-potential-enabled benchmarks resolve these to consistent values across six codes, attributing prior errors to basis-set and sampling issues.