AWhat changed
Parameterizes a Lagrangian with a neural network and uses automatic derivatives and a velocity-Hessian inverse to predict accelerations from generalized coordinates.
Scientific scope
Parameterizes a Lagrangian with a neural network and uses automatic derivatives and a velocity-Hessian inverse to predict accelerations from generalized coordinates. Six original authors; affiliation stars are not shared-lead marks. Inherits Euler–Lagrange mechanics and earlier restricted DeLaN; not first neural Lagrangian method. Invertibility/regularity are needed for unambiguous dynamics; pseudoinverse is a practical response to singularity, not proof of a regular physical system. Cubic Hessian inversion and integration error remain; learned conservation is not universal true-energy accuracy.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Six original authors; affiliation stars are not shared-lead marks. Inherits Euler–Lagrange mechanics and earlier restricted DeLaN; not first neural Lagrangian method. Invertibility/regularity are needed for unambiguous dynamics; pseudoinverse is a practical response to singularity, not proof of a regular physical system. Cubic Hessian inversion and integration error remain; learned conservation is not universal true-energy accuracy.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction