SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.13267 · 2023

ArchiSound: Audio Generation with 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, 2 violated it and 2 have no contract verdict; 2 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/2301.13267.json · badge: /api/ran/2301.13267.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
archinetai/audio-diffusion-pytorch canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
clip Ran
ran on a synthesized input
archinetai/audio-diffusion-pytorch/audio_diffusion_pytorch/diffusion.py
code served (permissive licence) · get_code("73879fb60563ab28")
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
from einops import rearrange, repeat

torch.manual_seed(0)

# Create a small tensor with batch size 2 and spatial/feature dimensions
x = torch.randn(2, 4, 3)  # batch=2, feature dims of different sizes for probing

# Test both cases: dynamic_threshold = 0.0 and non-zero
ARGS = {
    'x': x,
    'dynamic_threshold': 0.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, 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
exists Ran
ran, violated the contract we drafted
archinetai/audio-diffusion-pytorch/audio_diffusion_pytorch/utils.py
code served (permissive licence) · get_code("b7f514d1295ce8bf")
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 bool, 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
from typing import Optional

torch.manual_seed(0)

# The function exists() takes a single parameter 'val' of type Optional[T]
# and returns a TypeGuard[T]. The function body simply checks if val is not None.
# We need to provide a value for the 'val' parameter.

# Test with a non-None value
test_value = torch.randn(2, 4)

ARGS = {
    'val': test_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, typing_extensions — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
extend_dim Ran
ran on a synthesized input
archinetai/audio-diffusion-pytorch/audio_diffusion_pytorch/diffusion.py
code served (permissive licence) · get_code("5f96c88e1341917f")
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, 3, 4, 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, 3, 4)
x = torch.randn(2, 3, 4)

# Choose a target dimension that is larger than current ndim
# Current ndim is 3, so we extend to dim 5
dim = 5

ARGS = {
    "x": x,
    "dim": dim,
}
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, 3, 4, 1, 1) — shape (2, 3, 4, 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
iff Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
archinetai/audio-diffusion-pytorch/audio_diffusion_pytorch/utils.py
code served (permissive licence) · get_code("6f23ac079c8f083f")
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)

# The function `iff` is a simple conditional that returns a value if condition is True, else None
# Parameters:
# - condition: bool
# - value: T (TypeVar, can be any type)

# Create test arguments
ARGS = {
    "condition": True,
    "value": torch.randn(2, 4)
}
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
is_sequence Ran
ran, violated the contract we drafted
archinetai/audio-diffusion-pytorch/audio_diffusion_pytorch/utils.py
code served (permissive licence) · get_code("246e7d93f8c8366d")
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 bool, 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
import numpy as np
from typing import Union

torch.manual_seed(0)

# The function is_sequence takes one parameter: obj of type T
# It checks if obj is an instance of list or tuple
# We need to provide test cases for both True and False cases

# Test case 1: a list (should return True)
test_list = [1, 2, 3, 4]

# Test case 2: a tuple (should return True)
test_tuple = (1, 2, 3, 4)

# Test case 3: a non-sequence object (should return False)
test_non_sequence = "string"

# We'll use the list case as the primary argument
ARGS = {
    'obj': test_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, typing_extensions — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
pad_dims Ran
ran; our contract draft was wrong, not the code
archinetai/audio-diffusion-pytorch/audio_diffusion_pytorch/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

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, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 1 the same month, 4 later) and 2 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
exists 2 other papers
1 the same month, 1 later
2301.09474 (2023-01)
DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
2305.01319 (2023-05)
Long-Term Rhythmic Video Soundtracker
pad_dims 2 other papers
2 later
2305.01319 (2023-05)
Long-Term Rhythmic Video Soundtracker
2409.06190 (2024-09)
Multi-Source Music Generation with Latent Diffusion
iff 1 other paper
1 later
2305.01319 (2023-05)
Long-Term Rhythmic Video Soundtracker
is_sequence 1 other paper
1 later
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

The recent surge in popularity of diffusion models for image generation has brought new attention to the potential of these models in other areas of media generation. One area that has yet to be fully explored is the application of diffusion models to audio generation. Audio generation requires an understanding of multiple aspects, such as the temporal dimension, long term structure, multiple layers of overlapping sounds, and the nuances that only trained listeners can detect. In this work, we investigate the potential of diffusion models for audio generation. We propose a set of models to tackle multiple aspects, including a new method for text-conditional latent audio diffusion with stacked 1D U-Nets, that can generate multiple minutes of music from a textual description. For each model, we make an effort to maintain reasonable inference speed, targeting real-time on a single consumer GPU. In addition to trained models, we provide a collection of open source libraries with the hope of simplifying future work in the field. Samples can be found at https://bit.ly/audio-diffusion. Codes are at https://github.com/archinetai/audio-diffusion-pytorch.

For agents

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

get_harvested_code_for_paper("2301.13267")
get_code_for_paper("2301.13267")
have("2301.13267")

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

curl https://syntology.ai/api/ran/2301.13267.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.13267.svg)](https://syntology.ai/paper/2301.13267)

Connect an agent — have() is free.