SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.08579 · 2024

Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 3 honoured the contract we drafted, 4 violated it and 0 have no contract verdict; 0 failures of our instrument; 1 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/2402.08579.json · badge: /api/ran/2402.08579.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
ClaraWanjura/neuroscatter canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
costF Ran
ran, violated the contract we drafted
ClaraWanjura/neuroscatter/fashionMNIST/fc_ANN_large.py
code served (permissive licence) · get_code("a1af7e2fbe55bd9a")
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 ArrayImpl, 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 jax
import jax.numpy as jnp
import numpy as np

# Set seed for reproducibility
np.random.seed(0)

# Create small tensors for testing
# x: input vector of dimension 4
x = jnp.array([0.1, 0.2, 0.3, 0.4])

# y: one-hot encoded label vector of dimension 3 (for softmax output)
y = jnp.array([1.0, 0.0, 0.0])

# weights: list of weight matrices
# weights[0]: maps input (dim 4) to hidden layer (dim 5)
# weights[1]: maps hidden layer (dim 5) to output (dim 3)
weights = [
    jnp.array(np.random.randn(5, 4) * 0.1),
    jnp.array(np.random.randn(3, 5) * 0.1)
]

# biases: list of bias vectors
# biases[0]: bias for hidden layer (dim 5)
# biases[1]: bias for output layer (dim 3)
biases = [
    jnp.array(np.random.randn(5) * 0.1),
    jnp.array(np.random.randn(3) * 0.1)
]

ARGS = {
    "x": x,
    "y": y,
    "weights": weights,
    "biases": biases
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, 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
costF Ran
ran, violated the contract we drafted
ClaraWanjura/neuroscatter/fashionMNIST/fc_ANN_large_linear.py
code served (permissive licence) · get_code("0c59c58f929a5bb4")
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 ArrayImpl, 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 jax.numpy as jnp
import jax
import numpy as np

# Set seed for reproducibility
np.random.seed(0)

# Define small sample data
# x: input vector, shape (4,) - 4 dimensional input
x = jnp.array([0.1, 0.2, 0.3, 0.4], dtype=jnp.float32)

# y: target output, shape (3,) - 3 classes for softmax
y = jnp.array([0.0, 1.0, 0.0], dtype=jnp.float32)

# weights: list of weight matrices
# First layer: 3x4 (maps 4-dim input to 3-dim hidden)
# Second layer: 3x3 (maps 3-dim hidden to 3-dim output)
weights = [
    jnp.array(np.random.randn(3, 4), dtype=jnp.float32),
    jnp.array(np.random.randn(3, 3), dtype=jnp.float32)
]

# biases: list of bias vectors
# First bias: shape (3,)
# Second bias: shape (3,)
biases = [
    jnp.array(np.random.randn(3), dtype=jnp.float32),
    jnp.array(np.random.randn(3), dtype=jnp.float32)
]

ARGS = {
    "x": x,
    "y": y,
    "weights": weights,
    "biases": biases
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, 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
invSuscept Ran
ran, violated the contract we drafted
ClaraWanjura/neuroscatter/fashionMNIST/conv_scatt_large.py
code served (permissive licence) · get_code("c4f7b9558d2a22ee")
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 ArrayImpl, ndim 2, dtype family float, shape (4, 4) 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 jax.numpy as jnp
import numpy as np

# gamma: array-like parameter for the function
# omega: array-like parameter for the function

gamma = jnp.array([0.1, 0.2, 0.3, 0.4])
omega = jnp.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "gamma": gamma,
    "omega": omega,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 2, dtype family float, shape (4, 4) — shape (4, 4) 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
network Ran
ran, honoured the contract we drafted
ClaraWanjura/neuroscatter/fashionMNIST/fc_ANN_large.py
code served (permissive licence) · get_code("08cb9c17df630f81")
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 ArrayImpl, ndim 1, dtype family float, shape (2,) 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 jax.numpy as jnp
import numpy as np

# Set seed for reproducibility
np.random.seed(0)

# Create small input vector (dimension 4)
x = jnp.array([0.1, 0.2, 0.3, 0.4])

# Create weights for the two-layer network
# First layer: input dim 4 -> hidden dim 3
# Second layer: hidden dim 3 -> output dim 2
weights = [
    jnp.array(np.random.randn(3, 4)),  # 3x4 matrix for first layer
    jnp.array(np.random.randn(2, 3))   # 2x3 matrix for second layer
]

# Create biases
# First layer bias: dimension 3
# Second layer bias: dimension 2
biases = [
    jnp.array(np.random.randn(3)),  # bias for hidden layer
    jnp.array(np.random.randn(2))   # bias for output layer
]

ARGS = {
    "x": x,
    "weights": weights,
    "biases": biases
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 1, dtype family float, shape (2,) — shape (2,) 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
randomVector Ran
ran, honoured the contract we drafted
ClaraWanjura/neuroscatter/fashionMNIST/conv_scatt_large.py
code served (permissive licence) · get_code("be6786347fb10612")
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 ndarray, ndim 1, dtype family float, shape (5,) 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 numpy as np

ARGS = {
    "Nj": 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (5,) — shape (5,) 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
sigmoid Ran
ran, honoured the contract we drafted
ClaraWanjura/neuroscatter/fashionMNIST/conv_ANN_small.py
code served (permissive licence) · get_code("231f6788694b28f8")
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 ArrayImpl, ndim 2, dtype family float, shape (2, 4) 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 jax.numpy as jnp

# The sigmoid function takes a single parameter 'z' which should be a numeric input
# (scalar, array, or JAX array). We'll create a small JAX array to pass to it.

z_input = jnp.array([[-2.0, -1.0, 0.0, 1.0],
                      [2.0, 0.5, -0.5, 1.5]])

ARGS = {
    "z": z_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
suscept Ran
ran, violated the contract we drafted
ClaraWanjura/neuroscatter/fashionMNIST/conv_scatt_large.py
code served (permissive licence) · get_code("fc146430c2189dc6")
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 ArrayImpl, ndim 2, dtype family float, shape (4, 4) 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 jax.numpy as jnp
import numpy as np

# gamma and omega are used in arithmetic operations within jnp.diag(1 / (gamma / 2 - 1j * omega))
# They appear to be array-like objects that support:
# - Division by scalar (gamma / 2)
# - Subtraction with complex numbers (- 1j * omega)
# - Division (1 / ...)
# - Passing to jnp.diag

# Create small sample arrays
gamma = jnp.array([2.0, 4.0, 6.0, 8.0])
omega = jnp.array([0.5, 1.0, 1.5, 2.0])

ARGS = {
    "gamma": gamma,
    "omega": omega,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 2, dtype family float, shape (4, 4) — shape (4, 4) 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
network Not yet run
unverified (harvested, no recorded run)
ClaraWanjura/neuroscatter/fashionMNIST/fc_ANN_large_linear.py
code served (permissive licence) · get_code("ff527f8ce8bec718")
How it ran

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 7 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 7 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

Given the rapidly growing scale and resource requirements of machine learning applications, the idea of building more efficient learning machines much closer to the laws of physics is an attractive proposition. One central question for identifying promising candidates for such neuromorphic platforms is whether not only inference but also training can exploit the physical dynamics. In this work, we show that it is possible to successfully train a system of coupled phase oscillators - one of the most widely investigated nonlinear dynamical systems with a multitude of physical implementations, comprising laser arrays, coupled mechanical limit cycles, superfluids, and exciton-polaritons. To this end, we apply the approach of equilibrium propagation, which permits to extract training gradients via a physical realization of backpropagation, based only on local interactions. The complex energy landscape of the XY/ Kuramoto model leads to multistability, and we show how to address this challenge. Our study identifies coupled phase oscillators as a new general-purpose neuromorphic platform and opens the door towards future experimental implementations.

For agents

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

get_harvested_code_for_paper("2402.08579")
get_code_for_paper("2402.08579")
have("2402.08579")

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

curl https://syntology.ai/api/ran/2402.08579.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.08579.svg)](https://syntology.ai/paper/2402.08579)

Connect an agent — have() is free.