SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.13412 · ICLR · 2024

Scaling physics-informed hard constraints with mixture-of-experts

Aditi Krishnapriyan, Yiheng Du, Nithin Chalapathi

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.13412.json · badge: /api/ran/2402.13412.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ask-berkeley/physics-nns-hard-constraints canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
convert_dict_to_tuples Ran
ran; our contract draft was wrong, not the code
ask-berkeley/physics-nns-hard-constraints/resume.py
pointer only (licence: NONE) · get_code("49fb4d19879a0a90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

double_vmap Ran
ran; our contract draft was wrong, not the code
ask-berkeley/physics-nns-hard-constraints/neptune/models/fno2d.py
pointer only (licence: NONE) · get_code("b525083279ecffac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

lp_norm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ask-berkeley/physics-nns-hard-constraints/neptune/losses/mse.py
pointer only (licence: NONE) · get_code("0708e0c2961b937e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reweight_matrix Ran
ran, violated the contract we drafted
ask-berkeley/physics-nns-hard-constraints/neptune/models/constraints/hard_constraint.py
pointer only (licence: NONE) · get_code("448357e9dda4fede")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

run_conv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ask-berkeley/physics-nns-hard-constraints/neptune/models/fno3d.py
pointer only (licence: NONE) · get_code("6957e51bf9fb6be1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

split_prng_key Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ask-berkeley/physics-nns-hard-constraints/neptune/models/model_utils.py
pointer only (licence: NONE) · get_code("a6a01f81f216d47c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

triple_vmap Ran
ran; our contract draft was wrong, not the code
ask-berkeley/physics-nns-hard-constraints/neptune/models/fno3d.py
pointer only (licence: NONE) · get_code("0acc1636c3fa1a80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dict_to_model_config Not yet run
unverified (harvested, no recorded run)
ask-berkeley/physics-nns-hard-constraints/neptune/models/model_builder.py
pointer only (licence: NONE) · get_code("0839759e88bf2562")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_model_config Not yet run
unverified (harvested, no recorded run)
ask-berkeley/physics-nns-hard-constraints/neptune/models/model_builder.py
pointer only (licence: NONE) · get_code("6ec0dd5d77d8e238")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ask-berkeley/physics-nns-hard-constraints when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Imposing known physical constraints, such as conservation laws, during neural network training introduces an inductive bias that can improve accuracy, reliability, convergence, and data efficiency for modeling physical dynamics. While such constraints can be softly imposed via loss function penalties, recent advancements in differentiable physics and optimization improve performance by incorporating PDE-constrained optimization as individual layers in neural networks. This enables a stricter adherence to physical constraints. However, imposing hard constraints significantly increases computational and memory costs, especially for complex dynamical systems. This is because it requires solving an optimization problem over a large number of points in a mesh, representing spatial and temporal discretizations, which greatly increases the complexity of the constraint. To address this challenge, we develop a scalable approach to enforce hard physical constraints using Mixture-of-Experts (MoE), which can be used with any neural network architecture. Our approach imposes the constraint over smaller decomposed domains, each of which is solved by an "expert" through differentiable optimization. During training, each expert independently performs a localized backpropagation step by leveraging the implicit function theorem; the independence of each expert allows for parallelization across multiple GPUs. Compared to standard differentiable optimization, our scalable approach achieves greater accuracy in the neural PDE solver setting for predicting the dynamics of challenging non-linear systems. We also improve training stability and require significantly less computation time during both training and inference stages.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.13412")
get_code_for_paper("2402.13412")
have("2402.13412")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.13412.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.13412.svg)](https://syntology.ai/paper/2402.13412)

Connect an agent — have() is free.