SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.04237 · 2020

Randomized Overdrive Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 4 have no contract verdict; 0 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/2010.04237.json · badge: /api/ran/2010.04237.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
csteinmetz1/ronn canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
FiLM Ran
ran on a synthesized input
csteinmetz1/ronn/dev/ronn/condition.py
code served (permissive licence) · get_code("e8a61d0fde7b7205")
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 3, dtype family float, shape (2, 4, 3) 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)

# Construct arguments for FiLM function
# FiLM takes two arguments: x and y
# x: feature tensor to be modulated
# y: conditioning tensor that produces gain (g) and bias (b) parameters

# From the function body:
# - y.size() returns (bs, p), so y must be 2D
# - y is split into two equal halves: g = y[..., :p // 2] and b = y[..., p // 2:]
# - g and b are reshaped to (bs, -1, 1)
# - x is multiplied by g and added with b, so x must be compatible with these operations

# Let's use batch size = 2
bs = 2
# p must be even (it's split in half), let's use p = 8
p = 8
# x should have shape (bs, features, spatial_dims) for the multiplication to work
# Since g and b are reshaped to (bs, -1, 1), x should be (bs, p//2, some_spatial_dim)
# or (bs, p//2) to be compatible. Let's make x shape (bs, 4, 3) where 4 = p//2

x = torch.randn(bs, p // 2, 3)  # shape (2, 4, 3)
y = torch.randn(bs, p)          # shape (2, 8)

ARGS = {
    "x": x,
    "y": y
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) 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
calculate_receptive_field Ran
ran on a synthesized input
csteinmetz1/ronn/dev/ronn/utils.py
code served (permissive licence) · get_code("679bec72525ea701")
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 int, ndim 0, dtype family int, 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

# Analyze the function to understand what arguments it needs
# calculate_receptive_field(kernel_size, n_layers, stride, dilations=[])

# kernel_size: appears to be an integer (used in arithmetic)
# n_layers: appears to be an integer (used in range())
# stride: appears to be an integer (used in arithmetic)
# dilations: optional list of integers (defaults to empty list)

ARGS = {
    "kernel_size": 3,
    "n_layers": 5,
    "stride": 2,
    "dilations": [1, 1, 2, 2, 1]
}
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 int, ndim 0, dtype family int, 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
center_crop Ran
ran on a synthesized input
csteinmetz1/ronn/dev/ronn/utils.py
code served (permissive licence) · get_code("f3db0665bb913e94")
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 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 torch

torch.manual_seed(0)

# Create a small tensor with shape (batch=2, dim=8)
# The last dimension is 8, and we want to crop it to size 4
x = torch.randn(2, 8)

# Size parameter - desired output size of the last dimension
size = 4

ARGS = {
    "x": x,
    "size": size,
}
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 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
get_activation Ran
ran on a synthesized input
csteinmetz1/ronn/dev/ronn/utils.py
code served (permissive licence) · get_code("394d882b23b787d4")
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 ReLU. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'activation_type': 'ReLU'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

By processing audio signals in the time-domain with randomly weighted temporal convolutional networks (TCNs), we uncover a wide range of novel, yet controllable overdrive effects. We discover that architectural aspects, such as the depth of the network, the kernel size, the number of channels, the activation function, as well as the weight initialization, all have a clear impact on the sonic character of the resultant effect, without the need for training. In practice, these effects range from conventional overdrive and distortion, to more extreme effects, as the receptive field grows, similar to a fusion of distortion, equalization, delay, and reverb. To enable use by musicians and producers, we provide a real-time plugin implementation. This allows users to dynamically design networks, listening to the results in real-time. We provide a demonstration and code at https://csteinmetz1.github.io/ronn.

For agents

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

get_harvested_code_for_paper("2010.04237")
get_code_for_paper("2010.04237")
have("2010.04237")

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

curl https://syntology.ai/api/ran/2010.04237.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.04237.svg)](https://syntology.ai/paper/2010.04237)

Connect an agent — have() is free.