SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.11325 · 2023

MusicLM: Generating Music From Text

arXiv · PDF · Open in the Atlas

Code that ran

10 of 16 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; 1 honoured the contract we drafted, 3 violated it and 3 have no contract verdict; 3 failures of our instrument; 6 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/2301.11325.json · badge: /api/ran/2301.11325.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
zhvng/open-musiclm community (classifier label)
classifier basis not recorded on the link
10 ran · 6 no recorded run
FunctionStatusWhere it lives
FeedForward Ran
ran on a synthesized input
zhvng/open-musiclm/open_musiclm/transformer.py
code served (permissive licence) · get_code("6d9fb8daed873991")
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 Sequential. 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

torch.manual_seed(0)

ARGS = {
    'dim': 64,
    'mult': 4,
    'dropout': 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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
accum_log Ran
ran; our contract draft was wrong, not the code
zhvng/open-musiclm/open_musiclm/trainer.py
code served (permissive licence) · get_code("5d19651094278e5c")
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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - accum_log takes two parameters: log and new_logs
# - log is a dict that gets values via .get(key, 0.0) and items assigned
# - new_logs is a dict that is iterated over with .items()
# - The function accumulates numeric values from new_logs into log

# Create valid arguments
log = {
    "loss": 0.5,
    "accuracy": 0.85,
    "steps": 10
}

new_logs = {
    "loss": 0.3,
    "accuracy": 0.1,
    "steps": 5,
    "new_metric": 2.0
}

ARGS = {
    "log": log,
    "new_logs": new_logs
}
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 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
beartype_jit Ran
ran on a synthesized input
zhvng/open-musiclm/open_musiclm/utils.py
code served (permissive licence) · get_code("56705ebbd1719df9")
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 function. 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 os
from beartype import beartype

def beartype_jit(func):
    """decorator to enable beartype only if USE_BEARTYPE is set to 1"""
    return beartype(func) if os.environ.get('USE_BEARTYPE', '0') == '1' else func

# Create a simple test function to decorate
def sample_function(x: int, y: str) -> str:
    """A simple function with type hints"""
    return f"{y}: {x}"

# ARGS dict mapping the single parameter 'func' to a callable
ARGS = {
    'func': sample_function
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
beartype — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
cast_tuple Ran
ran, honoured the contract we drafted
zhvng/open-musiclm/open_musiclm/data.py
code served (permissive licence) · get_code("f70dcb896366697c")
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 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)

ARGS = {
    "val": 42,
    "length": 3,
}
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 1, dtype family int — 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
default Ran
ran, violated the contract we drafted
zhvng/open-musiclm/open_musiclm/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
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 ThomasMrY/VCT, 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.

exists Ran
ran, violated the contract we drafted
zhvng/open-musiclm/open_musiclm/data.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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_optimizer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhvng/open-musiclm/open_musiclm/optimizer.py
pointer only (licence: MIT); the stored copy get_code serves, from levyisthebest/echopulse_prelease, is pointer only (licence: NONE) · get_code("04ffba60741eafce")
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 levyisthebest/echopulse_prelease, 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.

has_duplicates Ran
ran on a synthesized input
zhvng/open-musiclm/open_musiclm/preprocess.py
code served (permissive licence) · get_code("b61c115f6f3d1f0a")
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

torch.manual_seed(0)

# The function takes a single parameter 'tup' which should be a tuple
# It iterates through elements, counts occurrences, and checks if any element appears more than once
# We need to provide a tuple with some elements that may or may not have duplicates

# Test case 1: tuple with duplicates
tup_with_duplicates = (1, 2, 3, 2, 4)

ARGS = {
    "tup": tup_with_duplicates
}
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 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
separate_weight_decayable_params Ran
ran; our contract draft was wrong, not the code
zhvng/open-musiclm/open_musiclm/optimizer.py
pointer only (licence: MIT); the stored copy get_code serves, from levyisthebest/echopulse_prelease, is pointer only (licence: NONE) · get_code("fdc11aefc97f3abb")
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 levyisthebest/echopulse_prelease, 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.

yes_or_no Ran
ran, violated the contract we drafted
zhvng/open-musiclm/open_musiclm/preprocess.py
code served (permissive licence) · get_code("d95562c398a6b25e")
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 unittest.mock as mock

# The function uses input() to get user input and checks if the answer is in ('yes', 'y')
# We need to mock input() to return a valid answer

ARGS = {
    'question': 'Do you want to continue?'
}

# Mock the input function to return 'y' so the function can execute
import builtins
original_input = builtins.input
builtins.input = mock.Mock(return_value='y')
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 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
ConvFeedForward Not yet run
unverified (harvested, no recorded run)
zhvng/open-musiclm/open_musiclm/transformer.py
code served (permissive licence) · get_code("c50f4517f73b2754")
How it ran

no invocation recorded.

adapt_array Not yet run
unverified (harvested, no recorded run)
zhvng/open-musiclm/open_musiclm/data.py
code served (permissive licence) · get_code("30d228edc2deac18")
How it ran

no invocation recorded.

determine_types Not yet run
unverified (harvested, no recorded run)
zhvng/open-musiclm/open_musiclm/preprocess.py
code served (permissive licence) · get_code("da5e3e1bd72253c5")
How it ran

no invocation recorded.

get_kmeans_model Not yet run
unverified (harvested, no recorded run)
zhvng/open-musiclm/open_musiclm/hf_hubert_kmeans.py
code served (permissive licence) · get_code("e7ef2d4d1d4d4bc3")
How it ran

no invocation recorded.

get_linear_scheduler Not yet run
unverified (harvested, no recorded run)
zhvng/open-musiclm/open_musiclm/optimizer.py
code served (permissive licence) · get_code("efaa647252de0ebc")
How it ran

no invocation recorded.

sanitize_hparams Not yet run
unverified (harvested, no recorded run)
zhvng/open-musiclm/open_musiclm/trainer.py
code served (permissive licence) · get_code("aa541f9cfeec7a35")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 8 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 8 later) and 8 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 486 other papers
138 dated earlier, 5 the same month, 337 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 163 other papers
68 dated earlier, 3 the same month, 90 later, 1 same year, order not determinable, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
cast_tuple 9 other papers
4 dated earlier, 5 later · 1 only as an assembly brick
2106.02689 (2021-06)
RegionViT: Regional-to-Local Attention for Vision Transformers
2108.00154 (2021-08)
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
2203.08913 (2022-03)
Memorizing Transformers
and 6 more not named here
separate_weight_decayable_params 8 other papers
1 dated earlier, 7 later
2202.01855 (2022-02)
Self-Supervised Learning with Random-Projection Quantizer for Speech Recognition
2302.04761 (2023-02)
Toolformer: Language Models Can Teach Themselves to Use Tools
2303.05511 (2023-03)
Scaling up GANs for Text-to-Image Synthesis
and 5 more not named here
yes_or_no 7 other papers
1 dated earlier, 6 later
2202.01855 (2022-02)
Self-Supervised Learning with Random-Projection Quantizer for Speech Recognition
2302.01327 (2023-02)
Dual PatchNorm
2305.09636 (2023-05)
SoundStorm: Efficient Parallel Audio Generation
and 4 more not named here
accum_log 2 other papers
2 later
2309.13207 (2023-09)
Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications
2410.11758 (2024-10)
Latent Action Pretraining from Videos
adapt_array 2 other papers
1 dated earlier, 1 later
1806.05975 (2018-06)
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
2306.04201 (2023-06)
Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models
get_optimizer 2 other papers
2 later
2410.03143 (2024-10)
ECHOPulse: ECG controlled echocardio-grams video generation
2410.11758 (2024-10)
Latent Action Pretraining from Videos

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 introduce MusicLM, a model generating high-fidelity music from text descriptions such as "a calming violin melody backed by a distorted guitar riff". MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Our experiments show that MusicLM outperforms previous systems both in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption. To support future research, we publicly release MusicCaps, a dataset composed of 5.5k music-text pairs, with rich text descriptions provided by human experts.

For agents

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

get_harvested_code_for_paper("2301.11325")
get_code_for_paper("2301.11325")
have("2301.11325")

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

curl https://syntology.ai/api/ran/2301.11325.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.11325.svg)](https://syntology.ai/paper/2301.11325)

Connect an agent — have() is free.