SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.08561 · 2024

Data efficiency and long term prediction capabilities for neural operator surrogate models of core and edge plasma codes

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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, 0 violated it and 0 have no contract verdict; 5 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/2402.08561.json · badge: /api/ran/2402.08561.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
microsoft/pdearena canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
batchmul1d Ran
ran; our contract draft was wrong, not the code
microsoft/pdearena/pdearena/modules/fourier.py
pointer only (licence: MIT); the stored copy get_code serves, from pengwei07/PAPM, is pointer only (licence: NONE) · get_code("be31a0618c98c1b9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pengwei07/PAPM, and GitHub detected no licence in that repository 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.

batchmul2d Ran
ran; our contract draft was wrong, not the code
microsoft/pdearena/pdearena/modules/fourier.py
pointer only (licence: MIT); the stored copy get_code serves, from pengwei07/papm, is pointer only (licence: NONE) · get_code("4c0fb383786dadb3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from pengwei07/papm, and GitHub detected no licence in that repository 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.

custommse_loss Ran
ran; our contract draft was wrong, not the code
microsoft/pdearena/pdearena/modules/loss.py
pointer only (licence: MIT); the stored copy get_code serves, from anthonyzhou-1/temporal_pdes, is pointer only (licence: NONE) · get_code("86d0930a8092c898")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from anthonyzhou-1/temporal_pdes, and GitHub detected no licence in that repository 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.

pearson_correlation Ran
ran; our contract draft was wrong, not the code
microsoft/pdearena/pdearena/modules/loss.py
code served (permissive licence) · get_code("d83235be62a2525b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create input tensor: shape (B, T, feature_dim) = (2, 3, 4)
input_tensor = torch.randn(2, 3, 4)

# Create target tensor: same shape as input
target_tensor = torch.randn(2, 3, 4)

# reduce_batch parameter
reduce_batch_flag = False

ARGS = {
    "input": input_tensor,
    "target": target_tensor,
    "reduce_batch": reduce_batch_flag,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
scaledlp_loss Ran
ran; our contract draft was wrong, not the code
microsoft/pdearena/pdearena/modules/loss.py
pointer only (licence: MIT); the stored copy get_code serves, from anthonyzhou-1/temporal_pdes, is pointer only (licence: NONE) · get_code("85fc41048fade072")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from anthonyzhou-1/temporal_pdes, and GitHub detected no licence in that repository 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.

batchmul3d Not yet run
unverified (harvested, no recorded run)
microsoft/pdearena/pdearena/modules/fourier.py
code served (permissive licence) · get_code("6c3ea29ff7061656")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
microsoft/pdearena/pdearena/models/pderefiner.py
code served (permissive licence) · get_code("e363d96b6681e2f0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 7 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 7 later) and 0 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
batchmul1d 2 other papers
2 later
2407.05232 (2024-07)
PAPM: A Physics-aware Proxy Model for Process Systems
2503.18731 (2025-03)
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
batchmul2d 2 other papers
2 later
2407.05232 (2024-07)
PAPM: A Physics-aware Proxy Model for Process Systems
2503.18731 (2025-03)
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
custommse_loss 2 other papers
2 later
2412.13074 (2024-12)
Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogates
2503.18731 (2025-03)
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
scaledlp_loss 2 other papers
2 later
2412.13074 (2024-12)
Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogates
2503.18731 (2025-03)
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
batchmul3d 1 other paper
1 later
2503.18731 (2025-03)
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
get_model 1 other paper
1 later
2503.18731 (2025-03)
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
pearson_correlation 1 other paper
1 later
2503.18731 (2025-03)
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos

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

Simulation-based plasma scenario development, optimization and control are crucial elements towards the successful deployment of next-generation experimental tokamaks and Fusion power plants. Current simulation codes require extremely intensive use of HPC resources that make them unsuitable for iterative or real time applications. Neural network based surrogate models of expensive simulators have been proposed to speed up such costly workflows. Current efforts in this direction in the Fusion community are mostly limited to point estimates of quantities of interest or simple 1D PDE models, with a few notable exceptions. While the AI literature on methods for neural PDE surrogate models is rich, performance benchmarks for Fusion-relevant 2D fields has so far remained flimited. In this work neural PDE surrogates are trained for the JOREK MHD code and the STORM scrape-off layer code using the PDEArena library (https://github.com/microsoft/pdearena). The performance of these surrogate models is investigated as a function of training set size as well as for long-term predictions. The performance of surrogate models that are trained on either one variable or multiple variables at once is also considered. It is found that surrogates that are trained on more data perform best for both long- and short-term predictions. Additionally, surrogate models trained on multiple variables achieve higher accuracy and more stable performance. Downsampling the training set in time may provide stability in the long term at the expense of the short term predictive capability, but visual inspection of the resulting fields suggests that multiple metrics should be used to evaluate performance.

For agents

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

get_harvested_code_for_paper("2402.08561")
get_code_for_paper("2402.08561")
have("2402.08561")

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

curl https://syntology.ai/api/ran/2402.08561.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.08561.svg)](https://syntology.ai/paper/2402.08561)

Connect an agent — have() is free.