SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.10504 · 2018

A rotation-equivariant convolutional neural network model of primary visual cortex

arXiv · PDF · Open in the Atlas

Code that ran

1 of 5 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 1 has no contract verdict; 0 failures of our instrument; 4 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/1809.10504.json · badge: /api/ran/1809.10504.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
aecker/cnn-sys-ident canonical (classifier label)
classifier basis: census
1 ran · 4 no recorded run
FunctionStatusWhere it lives
inv_soft_threshold Ran
ran on a synthesized input
aecker/cnn-sys-ident/cnn_sys_ident/architectures/utils.py
code served (permissive licence) · get_code("06ad978a0cceb3dc")
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 (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 numpy as np

def inv_soft_threshold(x):
    return np.log(np.exp(x) - 1)

# Create a small numpy array as input
# The function applies np.log(np.exp(x) - 1) element-wise
# For numerical stability, x should be positive values where exp(x) - 1 > 0
# This means x > 0 effectively
x_input = np.array([1.0, 2.0, 0.5, 1.5])

ARGS = {
    "x": x_input
}
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 (4,) — shape (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
group_sparsity_regularizer_2d Not yet run
unverified (harvested, no recorded run)
aecker/cnn-sys-ident/cnn_sys_ident/architectures/cores.py
code served (permissive licence) · get_code("22c4f698dd765ddc")
How it ran

no invocation recorded.

poisson Not yet run
unverified (harvested, no recorded run)
aecker/cnn-sys-ident/cnn_sys_ident/architectures/utils.py
code served (permissive licence) · get_code("eb7a8e72798de314")
How it ran

no invocation recorded.

smoothness_regularizer_2d Not yet run
unverified (harvested, no recorded run)
aecker/cnn-sys-ident/cnn_sys_ident/architectures/cores.py
code served (permissive licence) · get_code("df746bc2001c5bcf")
How it ran

no invocation recorded.

soft_threshold Not yet run
unverified (harvested, no recorded run)
aecker/cnn-sys-ident/cnn_sys_ident/architectures/utils.py
code served (permissive licence) · get_code("20c6abdd07d0cabe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 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.

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

Classical models describe primary visual cortex (V1) as a filter bank of orientation-selective linear-nonlinear (LN) or energy models, but these models fail to predict neural responses to natural stimuli accurately. Recent work shows that models based on convolutional neural networks (CNNs) lead to much more accurate predictions, but it remains unclear which features are extracted by V1 neurons beyond orientation selectivity and phase invariance. Here we work towards systematically studying V1 computations by categorizing neurons into groups that perform similar computations. We present a framework to identify common features independent of individual neurons' orientation selectivity by using a rotation-equivariant convolutional neural network, which automatically extracts every feature at multiple different orientations. We fit this model to responses of a population of 6000 neurons to natural images recorded in mouse primary visual cortex using two-photon imaging. We show that our rotation-equivariant network not only outperforms a regular CNN with the same number of feature maps, but also reveals a number of common features shared by many V1 neurons, which deviate from the typical textbook idea of V1 as a bank of Gabor filters. Our findings are a first step towards a powerful new tool to study the nonlinear computations in V1.

For agents

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

get_harvested_code_for_paper("1809.10504")
get_code_for_paper("1809.10504")
have("1809.10504")

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

curl https://syntology.ai/api/ran/1809.10504.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.10504.svg)](https://syntology.ai/paper/1809.10504)

Connect an agent — have() is free.