SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1805.00237 · 2018

Randomly weighted CNNs for (music) audio classification

arXiv · PDF · Open in the Atlas

Code that ran

2 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 2 have 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/1805.00237.json · badge: /api/ran/1805.00237.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
jordipons/elmarc canonical (classifier label)
classifier basis: census
2 ran · 4 no recorded run
FunctionStatusWhere it lives
ballroom_path2gt Ran
ran on a synthesized input
jordipons/elmarc/src/datasets.py
code served (permissive licence) · get_code("76462b61225f2f18")
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

def ballroom_path2gt(file_path):
    cut_end = file_path[:file_path.rfind('/')]
    tag = cut_end[cut_end.rfind('/') + 1:]
    print(tag)
    if tag == 'ChaChaCha':
        return 0
    elif tag == 'Jive':
        return 1
    elif tag == 'Quickstep':
        return 2
    elif tag == 'Rumba':
        return 3
    elif tag == 'Samba':
        return 4
    elif tag == 'Tango':
        return 5
    elif tag == 'VienneseWaltz':
        return 6
    elif tag == 'Waltz':
        return 7
    else:
        print('Warning: did not find the corresponding ground truth (' + str(tag) + ').')
        import ipdb
        ipdb.set_trace()

# Valid file paths that extract dance category tags
file_path_1 = "/data/ballroom/Waltz/video_001.mp4"
file_path_2 = "/dataset/ChaChaCha/sample.avi"
file_path_3 = "/path/to/Tango/frame_sequence.mov"

ARGS = {
    "file_path": file_path_1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
ipdb, 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
gtzan_path2gt Ran
ran on a synthesized input
jordipons/elmarc/src/datasets.py
code served (permissive licence) · get_code("d2cbd5f613717907")
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

def gtzan_path2gt(file_path):
    tag = file_path[file_path.rfind('/') + 1:file_path.rfind('.', 0, -4)]
    print(tag)
    if tag == 'blues':
        return 0
    elif tag == 'classical':
        return 1
    elif tag == 'country':
        return 2
    elif tag == 'disco':
        return 3
    elif tag == 'hiphop':
        return 4
    elif tag == 'jazz':
        return 5
    elif tag == 'metal':
        return 6
    elif tag == 'pop':
        return 7
    elif tag == 'reggae':
        return 8
    elif tag == 'rock':
        return 9
    else:
        print('Warning: did not find the corresponding ground truth (' + str(tag) + ').')
        import ipdb
        ipdb.set_trace()

ARGS = {
    'file_path': '/path/to/blues.00000.au'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
ipdb, 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
build Not yet run
unverified (harvested, no recorded run)
jordipons/elmarc/src/dl_models.py
code served (permissive licence) · get_code("09f096ee2270341e")
How it ran

no invocation recorded.

cnn_single Not yet run
unverified (harvested, no recorded run)
jordipons/elmarc/src/dl_models.py
code served (permissive licence) · get_code("f7616517ba167ac3")
How it ran

no invocation recorded.

cnn_small_filters Not yet run
unverified (harvested, no recorded run)
jordipons/elmarc/src/dl_models.py
code served (permissive licence) · get_code("b46d6101918d9c80")
How it ran

no invocation recorded.

path2gt Not yet run
unverified (harvested, no recorded run)
jordipons/elmarc/src/datasets.py
code served (permissive licence) · get_code("6e49a9fff662661f")
How it ran

no invocation recorded.

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

The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional neural networks perform as feature extractors for (music) audio classification tasks. We use features extracted from the embeddings of deep architectures as input to a classifier - with the goal to compare classification accuracies when using different randomly weighted architectures. By following this methodology, we run a comprehensive evaluation of the current deep architectures for audio classification, and provide evidence that the architectures alone are an important piece for resolving (music) audio problems using deep neural networks.

For agents

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

get_harvested_code_for_paper("1805.00237")
get_code_for_paper("1805.00237")
have("1805.00237")

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

curl https://syntology.ai/api/ran/1805.00237.json

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

[![Syntology run record](https://syntology.ai/api/ran/1805.00237.svg)](https://syntology.ai/paper/1805.00237)

Connect an agent — have() is free.