SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.06190 · 2024

Multi-Source Music Generation with Latent Diffusion

arXiv · PDF · Open in the Atlas

Code that ran

6 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 0 have no contract verdict; 6 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/2409.06190.json · badge: /api/ran/2409.06190.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
xzwy/msldm canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
get_logger Ran
ran; our contract draft was wrong, not the code
xzwy/msldm/msldm/main/utils.py
code served (permissive licence) · get_code("ab52a777f7ea129a")
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 Logger. 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 logging
from pytorch_lightning.utilities import rank_zero_only

ARGS = {
    "name": "test_logger"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pytorch_lightning — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
normal_kl Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xzwy/msldm/SourceVAE/modules/distributions.py
pointer only (licence: MIT); the stored copy get_code serves, from NeuralCarver/Michelangelo, is pointer only (licence: GPL-3.0) · get_code("17eb0a31c91b671c")
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 NeuralCarver/Michelangelo, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

pad_dims Ran
ran; our contract draft was wrong, not the code
xzwy/msldm/msldm/main/diffusion.py
code served (permissive licence) · get_code("1714b81de8dbea7f")
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 5, dtype family float, shape (2, 4, 1, 1, 1) 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)

# ndim specifies how many dimensions to pad
ndim = 3

ARGS = {
    "x": x,
    "ndim": ndim,
}
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 5, dtype family float, shape (2, 4, 1, 1, 1) — shape (2, 4, 1, 1, 1) 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
retry_if_error Ran
ran; our contract draft was wrong, not the code
xzwy/msldm/msldm/main/utils.py
code served (permissive licence) · get_code("717f09b5b16b8d23")
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 torch.nn as nn
from typing import Callable, List, Optional, Sequence

torch.manual_seed(0)

# Create a simple callable that succeeds
def successful_fn():
    return "success"

# Create a callable that fails a few times then succeeds
call_count = [0]
def flaky_fn():
    call_count[0] += 1
    if call_count[0] < 3:
        raise ValueError("Temporary failure")
    return "eventual success"

# Create a callable that always fails
def always_fails():
    raise RuntimeError("This always fails")

ARGS = {
    "fn": successful_fn,
    "num_attemps": 10
}
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
sequential_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xzwy/msldm/msldm/main/diffusion.py
code served (permissive licence) · get_code("203f9e6f7f2d5dcb")
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, 3, 5) 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
from torch import Tensor

torch.manual_seed(0)

# Create a tensor with shape (batch=2, channels=3, length=5)
# The function uses like.shape[2] to get length and like.device
# It creates a mask of the same shape as 'like'
like = torch.randn(2, 3, 5)

# start parameter indicates where to begin zeroing out the mask
start = 2

ARGS = {
    "like": like,
    "start": start,
}
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, 3, 5) — shape (2, 3, 5) 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
snake Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xzwy/msldm/SourceVAE/modules/layers.py
code served (permissive licence) · get_code("f247e4748f379a76")
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 4, dtype family float, shape (2, 4, 3, 5) 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)

# The function takes two parameters: x (a tensor) and alpha (a scalar or tensor)
# x is reshaped, modified with sin operations, and reshaped back
# alpha is used in arithmetic operations (reciprocal, multiplication)

# Create a small tensor with shape (batch=2, channels=4, height=3, width=5)
x = torch.randn(2, 4, 3, 5)

# Create a scalar alpha parameter
alpha = torch.tensor(1.0)

ARGS = {
    "x": x,
    "alpha": alpha,
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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

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, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 2 later) and 1 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
normal_kl 34 other papers
24 dated earlier, 2 the same month, 8 later
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2209.15421 (2022-09)
TabDDPM: Modelling Tabular Data with Diffusion Models
2211.13221 (2022-11)
Latent Video Diffusion Models for High-Fidelity Long Video Generation
and 31 more not named here
snake 10 other papers
5 dated earlier, 5 later · 1 only as an assembly brick
2306.06546 (2023-06)
High-Fidelity Audio Compression with Improved RVQGAN
2307.04686 (2023-07)
VampNet: Music Generation via Masked Acoustic Token Modeling
2308.16692 (2023-08)
SPEECHTOKENIZER: UNIFIED SPEECH TOKENIZER FOR SPEECH LANGUAGE MODELS
and 7 more not named here
get_logger 2 other papers
2 dated earlier
2308.16177 (2023-08)
General Purpose Audio Effect Removal
2404.16969 (2024-04)
COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
pad_dims 2 other papers
2 dated earlier
2301.13267 (2023-01)
ArchiSound: Audio Generation with Diffusion
2305.01319 (2023-05)
Long-Term Rhythmic Video Soundtracker
sequential_mask 1 other paper
1 dated earlier
2305.01319 (2023-05)
Long-Term Rhythmic Video Soundtracker

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

Most music generation models directly generate a single music mixture. To allow for more flexible and controllable generation, the Multi-Source Diffusion Model (MSDM) has been proposed to model music as a mixture of multiple instrumental sources (e.g. piano, drums, bass, and guitar). Its goal is to use one single diffusion model to generate mutually-coherent music sources, that are then mixed to form the music. Despite its capabilities, MSDM is unable to generate music with rich melodies and often generates empty sounds. Its waveform diffusion approach also introduces significant Gaussian noise artifacts that compromise audio quality. In response, we introduce a Multi-Source Latent Diffusion Model (MSLDM) that employs Variational Autoencoders (VAEs) to encode each instrumental source into a distinct latent representation. By training a VAE on all music sources, we efficiently capture each source's unique characteristics in a "source latent." The source latents are concatenated and our diffusion model learns this joint latent space. This approach significantly enhances the total and partial generation of music by leveraging the VAE's latent compression and noise-robustness. The compressed source latent also facilitates more efficient generation. Subjective listening tests and Frechet Audio Distance (FAD) scores confirm that our model outperforms MSDM, showcasing its practical and enhanced applicability in music generation systems. We also emphasize that modeling sources is more effective than direct music mixture modeling. Codes and models are available at https://github.com/XZWY/MSLDM. Demos are available at https://xzwy.github.io/MSLDMDemo/.

For agents

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

get_harvested_code_for_paper("2409.06190")
get_code_for_paper("2409.06190")
have("2409.06190")

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

curl https://syntology.ai/api/ran/2409.06190.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.06190.svg)](https://syntology.ai/paper/2409.06190)

Connect an agent — have() is free.