SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.09058 · 2022

BEATs: Audio Pre-Training with Acoustic Tokenizers

arXiv · PDF · Open in the Atlas

Code that ran

16 of 18 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 12 have no contract verdict; 4 failures 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/2212.09058.json · badge: /api/ran/2212.09058.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
phuriches/genrepasd community (classifier label)
classifier basis not recorded on the link
16 ran · 2 no recorded run
FunctionStatusWhere it lives
calc_dist_matrix Ran
ran on a synthesized input
phuriches/genrepasd/run_genrep_dcase2020.py
code served (permissive licence) · get_code("3d14ae419c0d7642")
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 (5, 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)

# Create small tensors with distinct dimensions
# x: (num_points_x, feature_dim) = (5, 4)
# y: (num_points_y, feature_dim) = (3, 4)
x = torch.randn(5, 4)
y = torch.randn(3, 4)

# Batch size
bs = 2

ARGS = {
    "x": x,
    "y": y,
    "bs": bs,
}
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 (5, 3) — shape (5, 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
calc_dist_matrix Ran
ran on a synthesized input
phuriches/genrepasd/run_genrep_dcase2023.py
code served (permissive licence) · get_code("4ca327b55579e45c")
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, 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)

# Create two small tensors for x and y
# x: shape (2, 4) - 2 points in 4D space
# y: shape (3, 4) - 3 points in 4D space
x = torch.randn(2, 4)
y = torch.randn(3, 4)

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 2, dtype family float, shape (2, 3) — shape (2, 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
csv_text_to_list Ran
ran on a synthesized input
phuriches/genrepasd/dcase2023_task2_evaluator/dcase2023_task2_evaluator.py
code served (permissive licence) · get_code("a7f6845c12992bc0")
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 list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 csv
from io import StringIO

# The function csv_text_to_list takes a single parameter: csv_text
# It expects a string containing CSV-formatted data
# The function uses StringIO to create a file-like object from the string
# and csv.reader to parse it with comma delimiter

csv_text = """name,age,city
Alice,30,New York
Bob,25,Los Angeles
Charlie,35,Chicago"""

ARGS = {
    "csv_text": csv_text
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
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
eval_score Ran
ran on a synthesized input
phuriches/genrepasd/run_genrep_dcase2020.py
code served (permissive licence) · get_code("e0640949f9aea446")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

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

# Create ground truth labels (binary classification)
# Using 0s and 1s for binary labels
gt_list = [0, 1, 1, 0, 1, 0, 1, 1]

# Create anomaly scores (floating point values between 0 and 1)
# These represent model confidence/anomaly scores
scores = np.array([0.1, 0.9, 0.8, 0.2, 0.7, 0.3, 0.85, 0.95])

ARGS = {
    "gt_list": gt_list,
    "scores": scores,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
gelu Ran
ran; our contract draft was wrong, not the code
phuriches/genrepasd/beats/modules.py
code served (permissive licence) · get_code("f30ebf4e48b7e2d7")
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 (2, 4)
x = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    "x": x
}
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
gelu_accurate Ran
ran; our contract draft was wrong, not the code
phuriches/genrepasd/beats/modules.py
pointer only (licence: MIT); the stored copy get_code serves, from BytedanceSpeech/seed-tts-eval, is pointer only (licence: NONE) · get_code("4aa7333ffd7e18c6")
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 BytedanceSpeech/seed-tts-eval, 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.

get_data_list Ran
ran on a synthesized input
phuriches/genrepasd/src/datasets/prepare_dcase2020.py
code served (permissive licence) · get_code("3054478e3ed187fa")
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 tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory structure with test files
temp_dir = tempfile.mkdtemp()

# Create subdirectories with test .wav files
normal_dir = os.path.join(temp_dir, 'normal_sounds')
abnormal_dir = os.path.join(temp_dir, 'abnormal_sounds')

os.makedirs(normal_dir, exist_ok=True)
os.makedirs(abnormal_dir, exist_ok=True)

# Create dummy .wav files
open(os.path.join(normal_dir, 'normal_sample1.wav'), 'w').close()
open(os.path.join(normal_dir, 'normal_sample2.wav'), 'w').close()
open(os.path.join(abnormal_dir, 'abnormal_sample1.wav'), 'w').close()
open(os.path.join(abnormal_dir, 'defect_sample2.wav'), 'w').close()

# Define ARGS with the required parameter
ARGS = {
    'file_dirs': [normal_dir, abnormal_dir]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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_data_list Ran
ran on a synthesized input
phuriches/genrepasd/src/datasets/prepare_dcase2023.py
code served (permissive licence) · get_code("f87d24572787fc14")
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 tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory structure with test files
temp_dir = tempfile.mkdtemp()

# Create subdirectories with test files
subdir1 = os.path.join(temp_dir, 'subdir1')
subdir2 = os.path.join(temp_dir, 'subdir2')
os.makedirs(subdir1, exist_ok=True)
os.makedirs(subdir2, exist_ok=True)

# Create test files with naming patterns that include 'normal'/'anomaly' and 'source'/'target'
test_files = [
    os.path.join(subdir1, 'normal_source_001.wav'),
    os.path.join(subdir1, 'normal_target_002.wav'),
    os.path.join(subdir1, 'anomaly_source_003.wav'),
    os.path.join(subdir2, 'anomaly_target_004.wav'),
    os.path.join(subdir2, 'normal_source_005.wav'),
]

for file_path in test_files:
    with open(file_path, 'w') as f:
        f.write('')

# Define file_dirs parameter
file_dirs = [subdir1, subdir2]

ARGS = {
    'file_dirs': file_dirs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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_filename_list Ran
ran on a synthesized input
phuriches/genrepasd/src/datasets/prepare_dcase2020.py
code served (permissive licence) · get_code("8a194b39e1e24723")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()

# Create some subdirectories and files
os.makedirs(os.path.join(temp_dir, "subdir1"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "subdir2"), exist_ok=True)

# Create some test files
open(os.path.join(temp_dir, "file1.wav"), 'w').close()
open(os.path.join(temp_dir, "file2.wav"), 'w').close()
open(os.path.join(temp_dir, "subdir1", "file3.wav"), 'w').close()
open(os.path.join(temp_dir, "subdir2", "file4.png"), 'w').close()
open(os.path.join(temp_dir, "other.txt"), 'w').close()

ARGS = {
    'dir_path': temp_dir,
    'pattern': '*',
    'ext': 'wav'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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_machines Ran
ran on a synthesized input
phuriches/genrepasd/dcase2023_task2_evaluator/dcase2023_task2_evaluator.py
code served (permissive licence) · get_code("8550a8f6ab58c11d")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory with mock CSV files
temp_dir = tempfile.mkdtemp()

# Create some ground truth CSV files with different machine IDs
machine_ids = ['machine_001', 'machine_002', 'machine_003']
for machine_id in machine_ids:
    filename = os.path.join(temp_dir, f'ground_truth_{machine_id}.csv')
    with open(filename, 'w') as f:
        f.write('dummy,data\n1,2\n')

# Also create a file with duplicate machine ID to test deduplication
filename_dup = os.path.join(temp_dir, 'ground_truth_machine_002.csv')
with open(filename_dup, 'w') as f:
    f.write('dummy,data\n1,2\n')

ARGS = {
    'load_dir': temp_dir,
    'ext': '.csv'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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_meta_list Ran
ran on a synthesized input
phuriches/genrepasd/src/datasets/prepare_dcase2020.py
code served (permissive licence) · get_code("81118c228b7322b3")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# The function get_meta_list takes a file_list parameter
# It iterates through files and checks if 'normal' is in the filename
# If 'normal' is in the filename, it appends 0, otherwise 1

file_list = [
    'patient_001_normal.txt',
    'patient_002_abnormal.txt',
    'patient_003_normal.txt',
    'patient_004_disease.txt'
]

ARGS = {
    'file_list': file_list
}
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 list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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_meta_list Ran
ran on a synthesized input
phuriches/genrepasd/src/datasets/prepare_dcase2023.py
code served (permissive licence) · get_code("ed2f071daa13388b")
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 tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# The function expects a list of file paths/names
# It checks for 'normal' substring to determine label (0 if normal, 1 otherwise)
# It checks for 'source' substring to determine source (source or target)

file_list = [
    'data_normal_source.txt',
    'data_abnormal_target.txt',
    'sample_normal_target.csv',
    'sample_abnormal_source.npy'
]

ARGS = {
    'file_list': file_list
}
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 tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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_section_ids Ran
ran on a synthesized input
phuriches/genrepasd/dcase2023_task2_evaluator/dcase2023_task2_evaluator.py
code served (permissive licence) · get_code("7ff1101f9d23c903")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory structure with mock ground truth files
temp_dir = tempfile.mkdtemp()

# Create some dummy ground truth files with section IDs in their names
os.makedirs(temp_dir, exist_ok=True)
open(os.path.join(temp_dir, 'ground_truth_section_01_data.csv'), 'w').close()
open(os.path.join(temp_dir, 'ground_truth_section_02_data.csv'), 'w').close()
open(os.path.join(temp_dir, 'ground_truth_section_03_data.csv'), 'w').close()

ARGS = {
    'target_dir': temp_dir,
    'ext': '.csv'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
l2norm Ran
ran; our contract draft was wrong, not the code
phuriches/genrepasd/beats/quantizer.py
pointer only (licence: MIT); the stored copy get_code serves, from jy0205/LaVIT, is pointer only (licence: NOASSERTION) · get_code("eca6cdf05972a95e")
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 jy0205/LaVIT, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

sample_vectors Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phuriches/genrepasd/beats/quantizer.py
pointer only (licence: MIT); the stored copy get_code serves, from yangling0818/vqgraph, is pointer only (licence: NONE) · get_code("ada1d74afbd92171")
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 yangling0818/vqgraph, 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.

trainDataPct Ran
ran on a synthesized input
phuriches/genrepasd/src/datasets/utils.py
code served (permissive licence) · get_code("f975a9de7c08ff36")
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 dict. 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 numpy as np

# Create a minimal dataset dict that matches the expected structure
np.random.seed(42)

# Create sample data
num_samples = 10
file_list = [f"audio_{i}.wav" for i in range(num_samples)]
label_list = [f"label_{i}.txt" for i in range(num_samples)]
file_attrs = [f"attr_{i}" for i in range(num_samples)]
source_list = [f"source_{i}" for i in range(num_samples)]
machine_names_array = np.array(["machine_A"] * 5 + ["machine_B"] * 5)

dataset = {
    'file_list': file_list,
    'label_list': label_list,
    'file_attrs': file_attrs,
    'source_list': source_list,
    'machine_names': machine_names_array
}

ARGS = {
    'dataset': dataset,
    'pct': 0.8,
    'num_samples': None,
    'machine_names': None,
    'seed': 42
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_activation_fn Not yet run
unverified (harvested, no recorded run)
phuriches/genrepasd/beats/modules.py
pointer only (licence: MIT); the stored copy get_code serves, from BytedanceSpeech/seed-tts-eval, is pointer only (licence: NONE) · get_code("01233f4856456c5f")
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 BytedanceSpeech/seed-tts-eval, 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. No invocation recorded.

kmeans Not yet run
unverified (harvested, no recorded run)
phuriches/genrepasd/beats/quantizer.py
code served (permissive licence) · get_code("b865ae3ee66b52d3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 7 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 6 later) and 11 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
l2norm 24 other papers
24 later · 6 only as an assembly brick
2303.04341 (2023-03)
Neural Vector Fields: Implicit Representation by Explicit Learning
2303.04743 (2023-03)
Vector Quantized Time Series Generation with a Bidirectional Prior Model
2305.02541 (2023-05)
Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder
and 21 more not named here
sample_vectors 15 other papers
15 later · 5 only as an assembly brick
2305.13050 (2023-05)
AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation
2308.02117 (2023-08)
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
2309.16429 (2023-09)
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
and 12 more not named here
gelu 11 other papers
3 dated earlier, 8 later
2204.02152 (2022-04)
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
2204.03339 (2022-04)
Boosting Self-Supervised Embeddings for Speech Enhancement
2210.17016 (2022-10)
Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit
and 8 more not named here
gelu_accurate 11 other papers
3 dated earlier, 8 later
2204.02152 (2022-04)
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
2204.03339 (2022-04)
Boosting Self-Supervised Embeddings for Speech Enhancement
2210.17016 (2022-10)
Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit
and 8 more not named here
get_activation_fn 11 other papers
3 dated earlier, 8 later
2204.02152 (2022-04)
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
2204.03339 (2022-04)
Boosting Self-Supervised Embeddings for Speech Enhancement
2210.17016 (2022-10)
Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit
and 8 more not named here
kmeans 9 other papers
9 later
2305.13050 (2023-05)
AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation
2309.16429 (2023-09)
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
2405.18765 (2024-05)
Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI
and 6 more not named here
get_filename_list 1 other paper
1 dated earlier
2005.09234 (2020-05)
Anomalous sound detection based on interpolation deep neural network

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 massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art audio SSL models still employ reconstruction loss for pre-training. Compared with reconstruction loss, semantic-rich discrete label prediction encourages the SSL model to abstract the high-level audio semantics and discard the redundant details as in human perception. However, a semantic-rich acoustic tokenizer for general audio pre-training is usually not straightforward to obtain, due to the continuous property of audio and unavailable phoneme sequences like speech. To tackle this challenge, we propose BEATs, an iterative audio pre-training framework to learn Bidirectional Encoder representation from Audio Transformers, where an acoustic tokenizer and an audio SSL model are optimized by iterations. In the first iteration, we use random projection as the acoustic tokenizer to train an audio SSL model in a mask and label prediction manner. Then, we train an acoustic tokenizer for the next iteration by distilling the semantic knowledge from the pre-trained or fine-tuned audio SSL model. The iteration is repeated with the hope of mutual promotion of the acoustic tokenizer and audio SSL model. The experimental results demonstrate our acoustic tokenizers can generate discrete labels with rich audio semantics and our audio SSL models achieve state-of-the-art results across various audio classification benchmarks, even outperforming previous models that use more training data and model parameters significantly. Specifically, we set a new state-of-the-art mAP 50.6% on AudioSet-2M for audio-only models without using any external data, and 98.1% accuracy on ESC-50. The code and pre-trained models are available at https://aka.ms/beats.

For agents

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

get_harvested_code_for_paper("2212.09058")
get_code_for_paper("2212.09058")
have("2212.09058")

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

curl https://syntology.ai/api/ran/2212.09058.json

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

[![Syntology run record](https://syntology.ai/api/ran/2212.09058.svg)](https://syntology.ai/paper/2212.09058)

Connect an agent — have() is free.