OSCR

Learning missing physics from legacy simulators with alternating neural integrators.

Code ↔ Paper

4 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

3 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.

The 4 matches · 3 of them tie a paragraph to a whole file without given lines: weak matches, whose lines are not tinted
  1. [1] § Methods › Evaluation metrics and baselines ↔ Lorenz-stenflo/sindy_chaos_metric.m, the whole file · a weak match · score 0.74 · Lyapunov exponents, correlation dimension, approximate entropy, metrics, baselines, trajectory · block oscr:b:VWNWRSTM283NG-G · Report a mismatch
  2. [2] § Results › Recovering missing coupling in a chaotic system ↔ Lorenz-stenflo/sindy_chaos_metric.m, the whole file · a weak match · score 0.69 · Lyapunov exponent, correlation dimension, approximate entropy, RK4, baselines, trajectories · block oscr:b:VWNWRSTM283NG-G · Report a mismatch
  3. [3] § Methods › Implementation and non-intrusive coupling ↔ Morris/dataset/morris_lecar_ode.m, the whole file · a weak match · score 0.59 · Morris Lecar, activations, fractional, simulation · block oscr:b:XYXCJ2NAYCTRT-3 · Report a mismatch
  4. [4] § Results › From discrepancy to closed-loop refinement ↔ Lorenz-stenflo/reproduce_symbolic_writeback.py, lines 212 to 239 · score 0.54 · closed loop, Lorenz Stenflo, refinement, distillation, frozen, predictive · block oscr:b:330SQ67AD9WSM-V · Report a mismatch

Paper

Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

MATLAB · 79 lines · 2.4 KB · MIT · 2 matches

  1. % metric_trajectories_for_chaos.m
  2. here = fileparts(mfilename('fullpath'));
  3. matfile = fullfile(here, 'trajectories_for_chaos.mat');
  4. if exist(matfile, 'file') ~= 2
  5. error('Missing %s', matfile);
  6. end
  7. S = load(matfile);
  8. dt = double(S.dt(1));
  9. fs = 1 / dt;
  10. % Order: row 1 = reference truth; rows 2–3 = models (vs your true/base/4th; no 2nd in this .mat)
  11. vars = {'truth', 'rk4_prior_plus_B_baseline', 'ani4_strang_B_ani4'};
  12. nVar = numel(vars);
  13. nTraj = size(S.truth, 1);
  14. T = size(S.truth, 2);
  15. K = 2000;
  16. K = min(K, T);
  17. if K < 500
  18. warning('metric_trajectories_for_chaos: T=%d < 500, using K=%d.', T, K);
  19. end
  20. % 1-based trajectory indices (default: all trajectories in the file)
  21. traj_indices = 1:nTraj;
  22. % Optional: use only (x,y,z) for metrics [1 2 3]; [] = all 4 states
  23. state_cols = [];
  24. get_metrics = @(d) [correlationDimension(d), ...
  25. approximateEntropy(d), ...
  26. lyapunovExponent(d, fs)];
  27. all_metrics = zeros(nVar, 3, numel(traj_indices));
  28. for idx = 1:numel(traj_indices)
  29. t_idx = traj_indices(idx);
  30. for i = 1:nVar
  31. data = squeeze(S.(vars{i})(t_idx, 1:K, :));
  32. if ~isempty(state_cols)
  33. data = data(:, state_cols);
  34. end
  35. if size(data, 1) ~= K
  36. data = reshape(data, K, []);
  37. end
  38. all_metrics(i, :, idx) = get_metrics(data);
  39. end
  40. end
  41. avg_metrics = mean(all_metrics, 3);
  42. m_true = avg_metrics(1, :);
  43. den = abs(m_true);
  44. den(den < eps) = NaN;
  45. rel_errors = abs(avg_metrics(2:end, :) - m_true) ./ den;
  46. methods = {'Baseline (RK4+SINDy)', 'ANI4 (Strang)'};
  47. metrics_names = {'Corr Dimension', 'App Entropy', 'Lyapunov Exp'};
  48. fprintf('\n%s\n', matfile);
  49. fprintf('fs = 1/dt = %.6g (dt = %.6g)\n', fs, dt);
  50. fprintf('K = %d time steps, nTraj averaged = %d\n\n', K, numel(traj_indices));
  51. fprintf('%-22s | %-12s | %-12s | %-12s\n', 'Metric', 'Ground Truth', 'Method Value', 'Rel. Error');
  52. fprintf('------------------------------------------------------------------------------\n');
  53. for m = 1:3
  54. fprintf('--- %s ---\n', metrics_names{m});
  55. for i = 1:size(rel_errors, 1)
  56. val = avg_metrics(i + 1, m);
  57. err = rel_errors(i, m) * 100;
  58. fprintf('%-22s | %-12.5f | %-12.5f | %-7.2f%%\n', ...
  59. methods{i}, m_true(m), val, err);
  60. end
  61. fprintf('------------------------------------------------------------------------------\n');
  62. end

sindy_chaos_metric.m at commit 6b23f21, under MIT · at the source

Overview

  1. School of Mathematical Sciences, Zhejiang University,Hangzhou, China
  2. Department of Mathematics, Southern University of Science and Technology,Shenzhen, China
  3. Shenzhen International Center for Mathematics, Southern University of Science and Technology,Shenzhen, China
  4. Guangdong Provincial Key Laboratory of Computational Science and Material Design, Southern University of Science and Technology,Shenzhen, China
Journal: Nature communications, volume 17, issue 1, article 7877
Dates: received 17 November 2025; accepted 26 May 2026; published online 23 June 2026
Type: Research article · Language: English
License: CC BY-NC-ND
Identifiers: DOI 10.1038/s41467-026-74002-2 · PMID 42337241 · PMCID PMC13444323 · OpenAlex W7165570580
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Methods: Complexity, Statistics, Machine learning
Keywords: Applied mathematics, Computational science
Topic: Model Reduction and Neural Networks (Statistical and Nonlinear Physics, Physics and Astronomy), according to OpenAlex
Funding: National Natural Science Foundation of China (92370108); Science, Technology and Innovation Commission of Shenzhen Municipality (JCYJ20250604144300001, RCJC20221008092757098); Science Challenge Project (No. TZ2025007)
Citations: not cited yet (Europe PMC); 24 references in the paper

Abstract

The abstract is not reproduced here: the paper's license (CC BY-NC-ND) does not allow it. Read it in the paper, at the publisher or on Europe PMC.

Repository

Its files are read in the Code ↔ Paper reader above, with 4 matches between paragraphs and lines of code.

shanxue-w/ANI

License: MIT
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 6b23f2183cd89ec9779d2a51a81b99b0bdfe5d16, 21 June 2026
Languages: Python (183), MATLAB (24), Shell (8), Jupyter (3), C (2), C++ (2), C/C++ (1)
Size: 911 files, 223 scripts
Software Heritage: not checked
Found in: “Code availability”
Holds: README, license file, environment (requirements.txt, setup.py), tests, 3 notebooks
Not found: CITATION.cff, continuous integration, documentation
Tools: NumPy (168 files), Matplotlib (140 files), PyTorch (127 files), seaborn (43 files), SciPy (23 files), pandas (16 files), SymPy (2 files), scikit-learn (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
225 files

Code availability statement

The paper has a code availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1038/s41467-026-74002-2.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 223 scripts, each with its path and the digest of its content;
  • 4 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

Datasets cited

Data availability statement

The paper has a data availability statement. Its license (CC BY-NC-ND) does not allow reproducing it here; in short, from what the harvester recognized in it:

Read it in the paper: doi.org/10.1038/s41467-026-74002-2.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 2 keywords, 3 funders, 19 references.

Cite

This paper

Wang, H., Wang, Q., Yuan, C., & Wu, K. (2026). Learning missing physics from legacy simulators with alternating neural integrators. Nature communications, 17(1), 7877. https://doi.org/10.1038/s41467-026-74002-2

BibTeX

@article{wang2026learning,
author = {Wang, Hao and Wang, Qinghe and Yuan, Caiyou and Wu, Kailiang},
title = {{Learning missing physics from legacy simulators with alternating neural integrators}},
journal = {Nature communications},
year = {2026},
month = jun,
volume = {17},
number = {1},
pages = {7877},
publisher = {Nature Publishing Group},
issn = {2041-1723},
doi = {10.1038/s41467-026-74002-2},
url = {https://doi.org/10.1038/s41467-026-74002-2},
pmid = {42337241},
pmcid = {PMC13444323}
}

RIS

TY - JOUR
AU - Wang, Hao
AU - Wang, Qinghe
AU - Yuan, Caiyou
AU - Wu, Kailiang
TI - Learning missing physics from legacy simulators with alternating neural integrators
T2 - Nature communications
J2 - Nat Commun
PY - 2026
DA - 2026/06/23
VL - 17
IS - 1
SP - 7877
SN - 2041-1723
PB - Nature Publishing Group
DO - 10.1038/s41467-026-74002-2
UR - https://doi.org/10.1038/s41467-026-74002-2
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41467-026-74002-2",
"type": "article-journal",
"title": "Learning missing physics from legacy simulators with alternating neural integrators",
"container-title": "Nature communications",
"author": [
{
"family": "Wang",
"given": "Hao"
},
{
"family": "Wang",
"given": "Qinghe"
},
{
"family": "Yuan",
"given": "Caiyou"
},
{
"family": "Wu",
"given": "Kailiang"
}
],
"container-title-short": "Nat Commun",
"volume": "17",
"issue": "1",
"page": "7877",
"DOI": "10.1038/s41467-026-74002-2",
"PMID": "42337241",
"PMCID": "PMC13444323",
"ISSN": "2041-1723",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41467-026-74002-2",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
23
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41467-024-48024-7 [code]
Task-oriented machine learning surrogates for tipping points of agent-based models.
Journal: Nature communications
In common: seaborn, scikit-learn, pandas, 3 other tools, 3 references
[2] doi:10.7554/elife.95607 [code]
Generation of biophysical neuron model parameters from recorded electrophysiological responses.
Journal: eLife
In common: PyTorch, seaborn, scikit-learn, 4 other tools, 2 references
[3] doi:10.1098/rspa.2021.0883 [code]
Discovery of nonlinear dynamical systems using a Runge-Kutta inspired dictionary-based sparse regression approach.
Journal: Proceedings. Mathematical, physical, and engineering sciences
In common: PyTorch, scikit-learn, SciPy, 2 other tools, 3 references
[4] doi:10.1038/s41467-024-50378-x [code]
Learning interpretable dynamics of stochastic complex systems from experimental data.
Journal: Nature communications
In common: PyTorch, seaborn, scikit-learn, 4 other tools, 2 references
[5] doi:10.1038/s41467-024-51709-8 [code]
Highly efficient modeling and optimization of neural fiber responses to electrical stimulation.
Journal: Nature communications
In common: SymPy, PyTorch, seaborn, 4 other tools, 1 reference
[6] doi:10.1093/nsr/nwaf457 [code]
Artificial intelligence as a surrogate brain: bridging neural dynamical models and data.
Journal: National science review
In common: SymPy, PyTorch, scikit-learn, 4 other tools, 1 reference
[7] doi:10.1038/s41467-022-30628-6 [code]
Learning emergent partial differential equations in a learned emergent space.
Journal: Nature communications
In common: SymPy, PyTorch, scikit-learn, 4 other tools, 1 reference
[8] doi:10.1073/pnas.2306275120 [code]
Machine-guided discovery of a real-world rogue wave model.
Journal: Proceedings of the National Academy of Sciences of the United States of America
In common: SymPy, seaborn, scikit-learn, 4 other tools, 1 reference
[9] doi:10.1162/imag.a.1227 [code]
Large language models reveal the neural tracking of linguistic context in attended and unattended multi-talker speech.
Journal: Imaging neuroscience (Cambridge, Mass.)
In common: SymPy, PyTorch, seaborn, 5 other tools
[10] doi:10.1038/s43856-026-01606-6 [code]
Validation of remote multimodal AI screening for Parkinson disease across diverse settings.
Journal: Communications medicine
In common: SymPy, PyTorch, seaborn, 5 other tools

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Add the badge to the code's README

OSCR: the badge of this paper

If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.

Markdown
<!-- oscr-badge:start -->
[![OSCR](https://openscicode.org/badge/doi/10.1038/s41467-026-74002-2.svg)](https://openscicode.org/badge/doi/10.1038/s41467-026-74002-2)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.1038/s41467-026-74002-2.svg
   :target: https://openscicode.org/badge/doi/10.1038/s41467-026-74002-2
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1038/s41467-026-74002-2"><img src="https://openscicode.org/badge/doi/10.1038/s41467-026-74002-2.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->

On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".

If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Report a mismatch between the code and the paper · Report a code error (signed in)

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Report a reproduction failure (signed in)

Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.