SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.02838 · 2021

KuraNet: Systems of Coupled Oscillators that Learn to Synchronize

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 6 failures of our instrument; 0 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/2105.02838.json · badge: /api/ran/2105.02838.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
serre-lab/KuraNet canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
circular_moments Ran
ran; our contract draft was wrong, not the code
serre-lab/KuraNet/utils.py
code served (permissive licence) · get_code("b385f4263cd2ec80")
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 0, dtype family float, shape () 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
import numpy as np

torch.manual_seed(0)

# Create phases tensor: T x n (time steps x dimensions)
# T=2 (time steps), n=4 (phases)
phases = torch.randn(2, 4)

# Create masks tensor: g x n (groups x dimensions)
# g=3 (number of groups), n=4 (phases)
# Binary mask indicating which phases belong to each group
masks = torch.tensor([
    [1, 1, 0, 0],
    [0, 0, 1, 1],
    [1, 0, 1, 0]
], dtype=torch.float32)

ARGS = {
    "phases": phases,
    "masks": masks
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () 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
circular_variance Ran
ran; our contract draft was wrong, not the code
serre-lab/KuraNet/utils.py
code served (permissive licence) · get_code("8e19b68b595f809b")
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 0, dtype family float, shape () 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 a tensor of shape (T, n) where T is time steps and n is number of dimensions
# Using T=2 (time steps) and n=4 (dimensions)
phases = torch.randn(2, 4)

ARGS = {
    "phases": phases,
}
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 0, dtype family float, shape () — shape () 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
cohn_loss Ran
ran; our contract draft was wrong, not the code
serre-lab/KuraNet/utils.py
code served (permissive licence) · get_code("e1633f5b16cdee38")
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 0, dtype family float, shape () 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
import numpy as np

torch.manual_seed(0)

# Construct phases: T x n tensor (time steps x dimensions)
# T=2 time steps, n=4 dimensions
phases = torch.randn(2, 4)

# Construct masks: g x n tensor (groups x dimensions)
# g=3 groups, n=4 dimensions
# Binary mask indicating which phases belong to which group
masks = torch.tensor([
    [1, 1, 0, 0],
    [0, 0, 1, 1],
    [1, 0, 1, 0]
], dtype=torch.float32)

# eps parameter
eps = 1e-5

ARGS = {
    'phases': phases,
    'masks': masks,
    'eps': eps
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () 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
get_BSDS_info Ran
ran; our contract draft was wrong, not the code
serre-lab/KuraNet/data.py
code served (permissive licence) · get_code("220a2436552bf4af")
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 dict. The image it ran in was not recorded. If your copy returns the same type 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)

# The function get_BSDS_info takes a single parameter: image_tag
# It looks up the image_tag in data_info_dict_BSDS500 and returns the corresponding value
# Valid image_tags are the keys in the dictionary

ARGS = {
    'image_tag': '90076'
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
get_dist Ran
ran; our contract draft was wrong, not the code
serre-lab/KuraNet/data.py
code served (permissive licence) · get_code("dc420f95656ab9a9")
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 Normal. The image it ran in was not recorded. If your copy returns the same type 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
import numpy as np
from torch.distributions import uniform, cauchy, normal, relaxed_bernoulli, negative_binomial
from sklearn import datasets

torch.manual_seed(0)
np.random.seed(0)

# Setup for get_dist function
ARGS = {
    'dist_name': 'normal',
    'loc': torch.tensor(0.0),
    'scale': torch.tensor(1.0),
    'high': torch.tensor(1.0),
    'low': torch.tensor(0.0),
    'num_classes': 3,
    'noise': 0.05,
    'r': torch.tensor(5.0),
    'probs': torch.tensor(0.3)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Normal — a Normal output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Normal output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
load_img_BSDS500 Ran
ran; our contract draft was wrong, not the code
serre-lab/KuraNet/data.py
code served (permissive licence) · get_code("183093af298d2a40")
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 tuple. The image it ran in was not recorded. If your copy returns the same type 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 os
import numpy as np
from scipy.io import savemat
import tempfile
from skimage.io import imsave

# Create a temporary directory structure that mimics BSDS500
tmpdir = tempfile.mkdtemp()
os.makedirs(os.path.join(tmpdir, 'images', 'train'), exist_ok=True)
os.makedirs(os.path.join(tmpdir, 'groundTruth', 'train'), exist_ok=True)

# Create a dummy image file
img_array = np.random.randint(0, 256, (64, 48, 3), dtype=np.uint8)
img_path = os.path.join(tmpdir, 'images', 'train', '12345.jpg')
imsave(img_path, img_array)

# Create a dummy groundTruth .mat file with proper structure
# The function expects: mat[seg_ind][0][0][0] to work
# This means mat should be a numpy array containing cells/arrays
seg_data = np.random.randint(0, 10, (32, 32), dtype=np.uint8)

# Create the nested structure that loadmat would return
# groundTruth is typically a cell array with 5 segmentations
groundtruth_list = [
    np.array([[np.array([[seg_data]])]]) for _ in range(5)
]
groundtruth_cell = np.array(groundtruth_list, dtype=object)

mat_data = {'groundTruth': groundtruth_cell}
mat_path = os.path.join(tmpdir, 'groundTruth', 'train', '12345.mat')
savemat(mat_path, mat_data)

ARGS = {
    'file_id': '12345',
    'mode': 'train',
    'seg_ind': 0,
    'data_dir': tmpdir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 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.

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

Networks of coupled oscillators are some of the most studied objects in the theory of dynamical systems. Two important areas of current interest are the study of synchrony in highly disordered systems and the modeling of systems with adaptive network structures. Here, we present a single approach to both of these problems in the form of "KuraNet", a deep-learning-based system of coupled oscillators that can learn to synchronize across a distribution of disordered network conditions. The key feature of the model is the replacement of the traditionally static couplings with a coupling function which can learn optimal interactions within heterogeneous oscillator populations. We apply our approach to the eponymous Kuramoto model and demonstrate how KuraNet can learn data-dependent coupling structures that promote either global or cluster synchrony. For example, we show how KuraNet can be used to empirically explore the conditions of global synchrony in analytically impenetrable models with disordered natural frequencies, external field strengths, and interaction delays. In a sequence of cluster synchrony experiments, we further show how KuraNet can function as a data classifier by synchronizing into coherent assemblies. In all cases, we show how KuraNet can generalize to both new data and new network scales, making it easy to work with small systems and form hypotheses about the thermodynamic limit. Our proposed learning-based approach is broadly applicable to arbitrary dynamical systems with wide-ranging relevance to modeling in physics and systems biology.

For agents

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

get_harvested_code_for_paper("2105.02838")
get_code_for_paper("2105.02838")
have("2105.02838")

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

curl https://syntology.ai/api/ran/2105.02838.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.02838.svg)](https://syntology.ai/paper/2105.02838)

Connect an agent — have() is free.