SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.05037 · 2023

Separate Anything You Describe

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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, 2 violated it and 0 have no contract verdict; 5 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/2308.05037.json · badge: /api/ran/2308.05037.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
audio-agi/audiosep canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
act Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
audio-agi/audiosep/models/base.py
code served (permissive licence) · get_code("3d4fcbbce6ace804")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

# Test with 'relu' activation
activation = 'relu'

ARGS = {
    'x': x.clone(),
    'activation': activation
}
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
create_logging Ran
ran; our contract draft was wrong, not the code
audio-agi/audiosep/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from littleflyingsheep/clapscore_for_lass, is pointer only (licence: NONE) · get_code("720ba14465467e12")
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 littleflyingsheep/clapscore_for_lass, 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.

float32_to_int16 Ran
ran, violated the contract we drafted
audio-agi/audiosep/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from littleflyingsheep/clapscore_for_lass, is pointer only (licence: NONE) · get_code("ffa5754c94663d62")
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 littleflyingsheep/clapscore_for_lass, 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_film_meta Ran
ran; our contract draft was wrong, not the code
audio-agi/audiosep/models/resunet.py
code served (permissive licence) · get_code("de10184f4a653fce")
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 torch.nn as nn

torch.manual_seed(0)

class MockBatchNorm(nn.Module):
    def __init__(self, num_features):
        super().__init__()
        self.num_features = num_features

class MockModuleWithFilm(nn.Module):
    def __init__(self, bn1_features, bn2_features):
        super().__init__()
        self.has_film = True
        self.bn1 = MockBatchNorm(bn1_features)
        self.bn2 = MockBatchNorm(bn2_features)

class MockModuleWithoutFilm(nn.Module):
    def __init__(self):
        super().__init__()
        self.has_film = False

class MockModuleNoFilmAttr(nn.Module):
    def __init__(self):
        super().__init__()

class TestModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.has_film = True
        self.bn1 = MockBatchNorm(4)
        self.bn2 = MockBatchNorm(3)
        self.child_with_film = MockModuleWithFilm(5, 6)
        self.child_without_film = MockModuleWithoutFilm()
        self.child_no_attr = MockModuleNoFilmAttr()

module = TestModule()

ARGS = {
    'module': module
}
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 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_loss_function Ran
ran; our contract draft was wrong, not the code
audio-agi/audiosep/losses.py
code served (permissive licence) · get_code("619a481adfa3ce11")
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 torch

torch.manual_seed(0)

ARGS = {
    'loss_type': 'l1_wav'
}
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 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
int16_to_float32 Ran
ran, violated the contract we drafted
audio-agi/audiosep/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from littleflyingsheep/clapscore_for_lass, is pointer only (licence: NONE) · get_code("cfd47b51fefe3711")
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 littleflyingsheep/clapscore_for_lass, 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.

l1 Ran
ran; our contract draft was wrong, not the code
audio-agi/audiosep/losses.py
code served (permissive licence) · get_code("9d43ef1e369fdd71")
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)

output = torch.randn(2, 4)
target = torch.randn(2, 4)

ARGS = {
    "output": output,
    "target": target
}
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
l1_wav Ran
ran, honoured the contract we drafted
audio-agi/audiosep/losses.py
code served (permissive licence) · get_code("5073e2ca7b39575f")
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 output_dict with a 'segment' key containing a tensor
output_tensor = torch.randn(2, 4)
output_dict = {'segment': output_tensor}

# Create target_dict with a 'segment' key containing a tensor of same shape
target_tensor = torch.randn(2, 4)
target_dict = {'segment': target_tensor}

ARGS = {
    'output_dict': output_dict,
    'target_dict': target_dict
}
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
get_model_class Not yet run
unverified (harvested, no recorded run)
audio-agi/audiosep/models/audiosep.py
code served (permissive licence) · get_code("856732fbad089eeb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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
create_logging 1 other paper
1 later
2407.04936 (2024-07)
A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining
float32_to_int16 1 other paper
1 later
2407.04936 (2024-07)
A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining
int16_to_float32 1 other paper
1 later
2407.04936 (2024-07)
A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining

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

Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries. We train AudioSep on large-scale multimodal datasets and extensively evaluate its capabilities on numerous tasks including audio event separation, musical instrument separation, and speech enhancement. AudioSep demonstrates strong separation performance and impressive zero-shot generalization ability using audio captions or text labels as queries, substantially outperforming previous audio-queried and language-queried sound separation models. For reproducibility of this work, we will release the source code, evaluation benchmark and pre-trained model at: https://github.com/Audio-AGI/AudioSep.

For agents

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

get_harvested_code_for_paper("2308.05037")
get_code_for_paper("2308.05037")
have("2308.05037")

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

curl https://syntology.ai/api/ran/2308.05037.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.05037.svg)](https://syntology.ai/paper/2308.05037)

Connect an agent — have() is free.