SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.05352 · ICML · 2026

Smoothness Errors in Dynamics Models and How to Avoid Them

Jung Park, Robin Walters, Edward Berman, Luisa Li

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2602.05352.json · badge: /api/ran/2602.05352.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
EdwardBerman/rayleigh_analysis canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
add_skip_connections Ran
ran; our contract draft was wrong, not the code
EdwardBerman/rayleigh_analysis/model/model_factory.py
pointer only (licence: NONE) · get_code("b5acd8d032ae7901")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, EdwardBerman/rayleigh_analysis 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.

one_percent_filter Ran
ran, violated the contract we drafted
EdwardBerman/rayleigh_analysis/data_preprocessing/lrgb_small.py
pointer only (licence: NONE) · get_code("1dfc9c31460b0605")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, EdwardBerman/rayleigh_analysis 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.

rayleigh_error Ran
ran, honoured the contract we drafted
EdwardBerman/rayleigh_analysis/metrics/rayleigh.py
pointer only (licence: NONE) · get_code("493595b9093e81e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, EdwardBerman/rayleigh_analysis 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.

rayleigh_quotients Ran
ran; our contract draft was wrong, not the code
EdwardBerman/rayleigh_analysis/metrics/rayleigh.py
pointer only (licence: NONE) · get_code("74205af7add68d65")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, EdwardBerman/rayleigh_analysis 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.

rayleigh_quotients_graphlevel Ran
ran; our contract draft was wrong, not the code
EdwardBerman/rayleigh_analysis/metrics/rayleigh.py
pointer only (licence: NONE) · get_code("4107e3151ce189e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, EdwardBerman/rayleigh_analysis 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.

scatter_sum Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
EdwardBerman/rayleigh_analysis/model/complex_global_mean_pool.py
pointer only (licence: NONE) · get_code("0b6c9febe370d7f6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, EdwardBerman/rayleigh_analysis 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.

broadcast Not yet run
unverified (harvested, no recorded run)
EdwardBerman/rayleigh_analysis/model/complex_global_mean_pool.py
pointer only (licence: NONE) · get_code("5dd38da29766376b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, EdwardBerman/rayleigh_analysis 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.

scatter_mean Not yet run
unverified (harvested, no recorded run)
EdwardBerman/rayleigh_analysis/model/complex_global_mean_pool.py
pointer only (licence: NONE) · get_code("de1db25f3065b24e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, EdwardBerman/rayleigh_analysis 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

FunctionAlso present inEarliest-datedOthers named
broadcast 4 other papers
4 dated earlier
2204.10555 (2022-04)
KALA: Knowledge-Augmented Language Model Adaptation
2308.04583 (2023-08)
LATR: 3D Lane Detection from Monocular Images with Transformer
2311.16716 (2023-11)
GraphPro: Graph Pre-training and Prompt Learning for Recommendation
and 1 more not named here
scatter_sum 3 other papers
3 dated earlier
2204.10555 (2022-04)
KALA: Knowledge-Augmented Language Model Adaptation
2308.04583 (2023-08)
LATR: 3D Lane Detection from Monocular Images with Transformer
2311.16716 (2023-11)
GraphPro: Graph Pre-training and Prompt Learning for Recommendation

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

Modern neural networks have shown promise for solving partial differential equations over surfaces, often by discretizing the surface as a mesh and learning with a mesh-aware graph neural network. However, graph neural networks suffer from oversmoothing, where a node's features become increasingly similar to those of its neighbors. Unitary graph convolutions, which are mathematically constrained to preserve smoothness, have been proposed to address this issue. Despite this, in many physical systems, such as diffusion processes, smoothness naturally increases and unitarity may be overconstraining. In this paper, we systematically study the smoothing effects of different GNNs for dynamics modeling and prove that unitary convolutions hurt performance for such tasks. We propose relaxed unitary convolutions that balance smoothness preservation with the natural smoothing required for physical systems. We also generalize unitary and relaxed unitary convolutions from graphs to meshes. In experiments on PDEs such as the heat and wave equations over complex meshes and on weather forecasting, we find that our method outperforms several strong baselines, including mesh-aware transformers and equivariant neural networks.

For agents

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

get_harvested_code_for_paper("2602.05352")
get_code_for_paper("2602.05352")
have("2602.05352")

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

curl https://syntology.ai/api/ran/2602.05352.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.05352.svg)](https://syntology.ai/paper/2602.05352)

Connect an agent — have() is free.