A four-ledger cost model for physics-AI surrogates: corpus generation, training, per-query inference and verification, with a reproducible break-even formula, the 2026 cost-accuracy frontier, the reversal at tight tolerances and hybrid warm-start deployment.
A decision-oriented review of neural operators: function-space contracts, four architecture families, six selection constraints, stress tests, a decision tree and an engineering checklist, with careful treatment of discretisation invariance and benchmark rankings.
A full-stack review of PINNs: composite-loss mechanics, five failure modes, 2026 progress, an actionable selection tree, a toolchain map and an engineering checklist, clarifying how PINNs differ from neural operators.
NewOriginal (DClaw)PINNPhysics-Informed Neural NetworksScientific ML