SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.02247 · 2022

Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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 13 have no contract verdict; 0 failures of our instrument; 1 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/2211.02247.json · badge: /api/ran/2211.02247.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
jhtonykoo/music_mixing_style_transfer canonical (classifier label)
classifier basis not recorded on the link
13 ran · 1 no recorded run
FunctionStatusWhere it lives
dis_hinge Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/modules/loss.py
code served (permissive licence) · get_code("1c9b83928c254d42")
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 0, dtype family float, 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

torch.manual_seed(0)

# dis_hinge expects two tensors: dis_fake and dis_real
# The function applies relu and mean operations on them
# They should be discriminator outputs (typically 1D or can be any shape that supports relu and mean)

dis_fake = torch.randn(2, 4)
dis_real = torch.randn(2, 4)

ARGS = {
    "dis_fake": dis_fake,
    "dis_real": dis_real,
}
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 0, dtype family float, 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
find_best_epoch Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/modules/training_utils.py
code served (permissive licence) · get_code("403bb700e3a588f7")
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 os
import tempfile
from glob import glob

# Create a temporary directory with mock epoch folders
temp_dir = tempfile.mkdtemp()

# Create some mock epoch directories with numeric names
epoch_names = ['0', '5', '10', '3']
for epoch_name in epoch_names:
    epoch_path = os.path.join(temp_dir, epoch_name)
    os.makedirs(epoch_path, exist_ok=True)

# The input_dir should be the temp directory with a trailing separator
# so that glob('{}*'.format(input_dir)) matches the epoch subdirectories
input_dir = temp_dir + os.sep

ARGS = {
    'input_dir': input_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 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
find_by_name Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/modules/training_utils.py
code served (permissive licence) · get_code("ee59fdc91bab20e3")
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 os
import tempfile

# Create a temporary directory structure with epoch folders
temp_dir = tempfile.mkdtemp()
epoch_dirs = []
for epoch_num in [5, 10, 3, 15, 8]:
    epoch_path = os.path.join(temp_dir, str(epoch_num))
    os.makedirs(epoch_path, exist_ok=True)
    epoch_dirs.append(epoch_path)

ARGS = {
    "epochs": epoch_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 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
frames_to_time Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/data_loader/loader_utils.py
code served (permissive licence) · get_code("0b24f944e9b2a2f1")
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 str. 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 numpy as np

torch.manual_seed(0)

# Analyze the function:
# - total_length: numeric value (int or float) representing frames
# - sr: sample rate (default 44100), numeric value
# The function divides total_length by sr to get time in seconds,
# then converts to hours:minutes:seconds format

# Create valid arguments
ARGS = {
    'total_length': 353400,  # Example: 353400 frames at 44100 Hz = ~8 seconds (2 hours, 18 minutes, 20 seconds in this case let's use 441000 for 10 seconds)
    'sr': 44100
}

# Adjust for meaningful output
ARGS['total_length'] = 441000  # 10 seconds at 44100 Hz = 0:00:10
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
gen_hinge Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/modules/loss.py
code served (permissive licence) · get_code("31c0864198dface2")
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 0, dtype family float, 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

torch.manual_seed(0)

# Create tiny discriminator output tensors
# dis_fake: tensor of fake discriminator scores
dis_fake = torch.randn(2, 4)

# dis_real: optional, not used in the function body but is a parameter
dis_real = torch.randn(2, 4)

ARGS = {
    "dis_fake": dis_fake,
    "dis_real": dis_real,
}
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 0, dtype family float, 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
hard_clip Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/mixing_manipulator/common_audioeffects.py
code served (permissive licence) · get_code("ea654d205db37b82")
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 (16,) 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

# Create small audio signal
x = np.random.randn(16).astype(np.float32)

# Define threshold in dB
threshold_dB = -20.0

# Define drive in dB
drive = 6.0

ARGS = {
    "x": x,
    "threshold_dB": threshold_dB,
    "drive": drive,
}
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 (16,) — shape (16,) 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
infoNCE Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/modules/loss.py
code served (permissive licence) · get_code("3d4969385373faf6")
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 0, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import torch.nn as nn

torch.manual_seed(0)

# Mock the gather_from_all function since it's not defined
def gather_from_all(tensor):
    return tensor

# Monkey-patch it into the module namespace
import sys
current_module = sys.modules[__name__]
current_module.gather_from_all = gather_from_all

# Create small tensors: batch_size=2, embedding_dim=4
nn_tensor = torch.randn(2, 4)  # Shape: (batch_size, embedding_dim)
p_tensor = torch.randn(2, 4)   # Shape: (batch_size, embedding_dim)

ARGS = {
    "nn": nn_tensor,
    "p": p_tensor,
    "temperature": 0.1
}
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 0, dtype family float — no output shape is stated: observe_signature.py could not observe it (fixture:KeyError)
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
load_files_lists Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/mixing_manipulator/common_dataprocessing.py
code served (permissive licence) · get_code("62b7418046b2021c")
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 some subdirectories to simulate a database structure
temp_dir = tempfile.mkdtemp()

# Create some sample subdirectories (representing songs/mixtures)
os.makedirs(os.path.join(temp_dir, "song_1"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "song_2"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "song_3"), exist_ok=True)

# Also create a file to test that os.listdir includes files too
with open(os.path.join(temp_dir, "readme.txt"), "w") as f:
    f.write("test")

ARGS = {
    "path": temp_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 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
load_wav Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/mixing_manipulator/common_dataprocessing.py
code served (permissive licence) · get_code("33adcbbabb3932c9")
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. 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
import scipy.io.wavfile as wav
import tempfile
import os

# Create a temporary WAV file for testing
temp_dir = tempfile.mkdtemp()
temp_wav_path = os.path.join(temp_dir, "test_audio.wav")

# Create a simple 16-bit PCM audio file
sample_rate = 16000
duration_seconds = 1
num_samples = sample_rate * duration_seconds
num_channels = 2

# Generate stereo audio data (16-bit PCM)
audio_data = np.random.randint(-32768, 32767, size=(num_samples, num_channels), dtype=np.int16)

# Write the WAV file
wav.write(temp_wav_path, sample_rate, audio_data)

ARGS = {
    "file_path": temp_wav_path,
    "mmap": False,
    "convert_float": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
new_repr Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/mixing_manipulator/common_audioeffects.py
code served (permissive licence) · get_code("e1abc4e8a6bbbb0d")
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 str. 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

class Processor:
    def __init__(self, name, parameters):
        self.name = name
        self.parameters = parameters
    
    def new_repr(self):
        """
        Create human-readable representation.

        Args:
            self: Reference to object.

        Returns:
            string representation of object.
        """
        return f'Processor(name={self.name!r}, parameters={self.parameters!r}'

torch.manual_seed(0)

processor_instance = Processor(
    name="test_processor",
    parameters={"learning_rate": 0.001, "batch_size": 32, "hidden_dim": 128}
)

ARGS = {
    "self": processor_instance
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
recursive_getattr Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/mixing_manipulator/common_miscellaneous.py
code served (permissive licence) · get_code("97b236cd195f653f")
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 Parameter, 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
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 3)
        self.fc2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.fc2(self.fc1(x))

model = SimpleModel()

# Test with nested attribute access like "fc1.weight"
obj = model
attr = "fc1.weight"

ARGS = {
    "obj": obj,
    "attr": attr,
}
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 Parameter, ndim 2, dtype family float — no output shape is stated: observe_signature.py recorded Tensor ndim 2, which disagrees with the fixture run
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
sec_to_time Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/data_loader/loader_utils.py
code served (permissive licence) · get_code("d1fb6948a5e1be93")
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 str. 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 numpy as np

def frames_to_time(total_length, sr=44100):
    in_time = total_length / sr
    hour = int(in_time / 3600)
    minute = int((in_time - hour * 3600) / 60)
    second = int(in_time - hour * 3600 - minute * 60)
    return f'{hour:02d}:{minute:02d}:{second:02d}'

def sec_to_time(input_time):
    return frames_to_time(input_time, sr=1)

# Setup code for sec_to_time function
# The function takes input_time and converts it using frames_to_time with sr=1
# input_time represents seconds when sr=1

# Create a valid input_time value (in seconds)
# Using a value that gives meaningful hour:minute:second output
input_time_value = 3661  # 1 hour, 1 minute, 1 second

ARGS = {
    "input_time": input_time_value
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
time_to_frames Ran
ran on a synthesized input
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/data_loader/loader_utils.py
code served (permissive licence) · get_code("ffd131ee34912820")
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

torch.manual_seed(0)

ARGS = {
    'input_time': '01:30:45',
    'to_frames': True,
    'sr': 44100
}
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
reload_ckpt Not yet run
unverified (harvested, no recorded run)
jhtonykoo/music_mixing_style_transfer/mixing_style_transfer/modules/training_utils.py
code served (permissive licence) · get_code("5eb59bb5ee1d9d9e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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
hard_clip 1 other paper
1 dated earlier
2208.11428 (2022-08)
Automatic music mixing with deep learning and out-of-domain data
load_files_lists 1 other paper
1 dated earlier
2208.11428 (2022-08)
Automatic music mixing with deep learning and out-of-domain data
load_wav 1 other paper
1 dated earlier
2208.11428 (2022-08)
Automatic music mixing with deep learning and out-of-domain data
new_repr 1 other paper
1 dated earlier
2208.11428 (2022-08)
Automatic music mixing with deep learning and out-of-domain data
recursive_getattr 1 other paper
1 dated earlier
2208.11428 (2022-08)
Automatic music mixing with deep learning and out-of-domain data

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

We propose an end-to-end music mixing style transfer system that converts the mixing style of an input multitrack to that of a reference song. This is achieved with an encoder pre-trained with a contrastive objective to extract only audio effects related information from a reference music recording. All our models are trained in a self-supervised manner from an already-processed wet multitrack dataset with an effective data preprocessing method that alleviates the data scarcity of obtaining unprocessed dry data. We analyze the proposed encoder for the disentanglement capability of audio effects and also validate its performance for mixing style transfer through both objective and subjective evaluations. From the results, we show the proposed system not only converts the mixing style of multitrack audio close to a reference but is also robust with mixture-wise style transfer upon using a music source separation model.

For agents

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

get_harvested_code_for_paper("2211.02247")
get_code_for_paper("2211.02247")
have("2211.02247")

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

curl https://syntology.ai/api/ran/2211.02247.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.02247.svg)](https://syntology.ai/paper/2211.02247)

Connect an agent — have() is free.