Pith. sign in

REVIEW 3 cited by

Differentiable Physics: A Position Piece

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2109.07573 v1 pith:AMQKNOEG submitted 2021-09-14 cs.LG physics.chem-ph

classification cs.LGphysics.chem-ph
keywords differentiablephysicsphysicalclassicalmethodsmodelingnumericalprogramming
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Differentiable physics provides a new approach for modeling and understanding the physical systems by pairing the new technology of differentiable programming with classical numerical methods for physical simulation. We survey the rapidly growing literature of differentiable physics techniques and highlight methods for parameter estimation, learning representations, solving differential equations, and developing what we call scientific foundation models using data and inductive priors. We argue that differentiable physics offers a new paradigm for modeling physical phenomena by combining classical analytic solutions with numerical methodology using the bridge of differentiable programming.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networks

    physics.flu-dyn 2026-06 unverdicted novelty 6.0 of 10

    Differentiable physics recovers accurate wall shear stress from concentration observations across measurement scenarios where PINNs fail.

  2. What You See is Not What You Get: Neural Partial Differential Equations and The Illusion of Learning

    cs.LG 2024-11 conditional novelty 6.0 of 10

    NeuralPDEs trained on finite-difference simulation data inherit the discretization's Taylor-series truncation error, so generalization depends on matching numerical schemes between the solver and the model.

  3. Open source Differentiable ODE Solving Infrastructure

    cs.LG 2024-11 conditional novelty 3.0 of 10

    DeepChem gets differentiable ODE solvers adapted from ξ-torch, validated on four standard benchmarks, but the reported accuracy and open-source code are not yet verifiable.

Pith tools