SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.00530 · 2022

Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations

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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure 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/2209.00530.json · badge: /api/ran/2209.00530.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
Laborieux-Axel/holomorphic_eqprop canonical (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
FunctionStatusWhere it lives
identity Ran
ran, honoured the contract we drafted
Laborieux-Axel/holomorphic_eqprop/utils/functions.py
pointer only (licence: MIT); the stored copy get_code serves, from dholzmueller/universal_double_descent, is pointer only (licence: NONE) · get_code("9910e2fc297f8665")
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 dholzmueller/universal_double_descent, 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.

my_sigmoid Ran
ran on a synthesized input
Laborieux-Axel/holomorphic_eqprop/utils/functions.py
code served (permissive licence) · get_code("9249643e87c169c9")
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 function. 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 jax.numpy as jnp

# my_sigmoid takes two parameters: a and b
# These are used in the function f as: a * x + b
# So they should be scalar values (floats or arrays that broadcast with x)

a = 2.0
b = -1.5

ARGS = {
    "a": a,
    "b": b,
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
one_hot Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Laborieux-Axel/holomorphic_eqprop/utils/data.py
code served (permissive licence) · get_code("38f2f3d1795ca431")
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, 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 jax.numpy as jnp

# Construct arguments for the one_hot function
# The function takes:
# - x: an array of indices (shape: [batch_size])
# - k: number of classes (int)
# - dtype: data type (default jnp.float32)

# Create a small batch of class indices
x = jnp.array([0, 2, 1, 3])  # batch size 4, indices ranging from 0 to 3

# Number of classes
k = 5

# Data type
dtype = jnp.float32

ARGS = {
    "x": x,
    "k": k,
    "dtype": dtype
}
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 (4, 5) — shape (4, 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
sfm_pool Ran
ran on a synthesized input
Laborieux-Axel/holomorphic_eqprop/utils/custom.py
code served (permissive licence) · get_code("c1c975a446032f3b")
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 4, dtype family float, shape (2, 4, 3, 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
import jax.numpy as jnp
from jax import random

# Set seed for reproducibility
key = random.PRNGKey(0)

# Create a small test input tensor
# Shape: (batch=2, height=4, width=3, channels=2)
value = jnp.ones((2, 4, 3, 2), dtype=jnp.float32)

# Window shape for pooling (height, width)
window_shape = 2

# Strides for pooling (height, width)
strides = 1

# Padding mode
padding = "SAME"

# Channel axis (default is -1, the last dimension)
channel_axis = -1

# Temperature parameter for softmax
T = 1.0

ARGS = {
    "value": value,
    "window_shape": window_shape,
    "strides": strides,
    "padding": padding,
    "channel_axis": channel_axis,
    "T": T,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
haiku, jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 4, dtype family float, shape (2, 4, 3, 2) — shape (2, 4, 3, 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
silu Ran
ran on a synthesized input
Laborieux-Axel/holomorphic_eqprop/utils/functions.py
code served (permissive licence) · get_code("b438bb89cb4b14aa")
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 silu function takes a single parameter z which is used in a mathematical operation
# It should be a numeric array/tensor

# Create a small JAX array as input
z = jnp.array([[-1.0, 0.0, 1.0, 2.0],
               [0.5, -0.5, 1.5, -1.5]])

ARGS = {
    "z": z
}
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
make_result_dir Not yet run
unverified (harvested, no recorded run)
Laborieux-Axel/holomorphic_eqprop/utils/data.py
code served (permissive licence) · get_code("840f7736c00503d1")
How it ran

no invocation recorded.

window_wise_max Not yet run
unverified (harvested, no recorded run)
Laborieux-Axel/holomorphic_eqprop/utils/custom.py
code served (permissive licence) · get_code("ccf0c136a71a1e23")
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, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 2 later) and 5 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
identity 69 other papers
30 dated earlier, 1 the same month, 38 later · 5 only as an assembly brick
1706.07296 (2017-06)
A Minimal Developmental Model Can Increase Evolvability in Soft Robots
1802.09419 (2018-02)
Stochastic Hyperparameter Optimization through Hypernetworks
1804.06055 (2018-04)
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation
and 66 more not named here
one_hot 2 other papers
2 later
2402.16077 (2024-02)
Equivariant Frames and the Impossibility of Continuous Canonicalization
2605.07886 (2026-05)
Characterizing and Correcting Effective Target Shift in Online Learning

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

Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the training of deep neural networks with local learning rules. It thus provides a compelling framework for training neuromorphic systems and understanding learning in neurobiology. However, EP requires infinitesimal teaching signals, thereby limiting its applicability in noisy physical systems. Moreover, the algorithm requires separate temporal phases and has not been applied to large-scale problems. Here we address these issues by extending EP to holomorphic networks. We show analytically that this extension naturally leads to exact gradients even for finite-amplitude teaching signals. Importantly, the gradient can be computed as the first Fourier coefficient from finite neuronal activity oscillations in continuous time without requiring separate phases. Further, we demonstrate in numerical simulations that our approach permits robust estimation of gradients in the presence of noise and that deeper models benefit from the finite teaching signals. Finally, we establish the first benchmark for EP on the ImageNet 32x32 dataset and show that it matches the performance of an equivalent network trained with BP. Our work provides analytical insights that enable scaling EP to large-scale problems and establishes a formal framework for how oscillations could support learning in biological and neuromorphic systems.

For agents

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

get_harvested_code_for_paper("2209.00530")
get_code_for_paper("2209.00530")
have("2209.00530")

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

curl https://syntology.ai/api/ran/2209.00530.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.00530.svg)](https://syntology.ai/paper/2209.00530)

Connect an agent — have() is free.