SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.02192 · 2021

Audio Retrieval with Natural Language Queries

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 2 failures of our instrument; 2 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/2105.02192.json · badge: /api/ran/2105.02192.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
oncescuandreea/audio-retrieval canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
retrieval_as_classification Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
oncescuandreea/audio-retrieval/model/metric.py
code served (permissive licence) · get_code("a5a7db2dc3069c5d")
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 numpy as np

# Create a small similarity matrix (num_labels x num_queries)
# Before transpose: (num_queries, num_labels) = (3, 4)
sims = np.array([
    [0.9, 0.1, 0.2, 0.3],
    [0.4, 0.8, 0.3, 0.2],
    [0.1, 0.2, 0.95, 0.1]
], dtype=np.float32)

# Create query masks indicating which labels are relevant for each query
# Same shape as sims: (num_queries, num_labels) = (3, 4)
# Each row indicates which labels are relevant (1) or not (0) for that query
query_masks = np.array([
    [1, 0, 0, 0],
    [0, 1, 0, 0],
    [0, 0, 1, 0]
], dtype=np.int32)

ARGS = {
    'sims': sims,
    'query_masks': query_masks,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
ipdb, matplotlib, numpy, scipy, zsvision — 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
t2v_metrics Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
oncescuandreea/audio-retrieval/model/metric.py
code served (permissive licence) · get_code("c5497b09ac6e500b")
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 numpy as np
import scipy.stats

# Set seed for reproducibility
np.random.seed(0)

# Create a similarity matrix (num_queries x num_vids)
# num_queries = 8, num_vids = 2
# This represents a text-to-video similarity matrix
sims = np.random.randn(8, 2).astype(np.float32)

# Create query_masks - all queries are valid (no masking)
query_masks = np.ones(8, dtype=bool)

# Create query_masks_class_t2v - class labels for filtering queries
# 1 means include, 0 means exclude
query_masks_class_t2v = np.array([1, 1, 1, 1, 1, 1, 1, 1], dtype=np.int32)

# Create query_masks_class_v2t (not used in t2v_metrics but keeping for completeness)
query_masks_class_v2t = None

ARGS = {
    'sims': sims,
    'query_masks': query_masks,
    'query_masks_class_t2v': query_masks_class_t2v,
    'query_masks_class_v2t': query_masks_class_v2t,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
ipdb, matplotlib, numpy, scipy, zsvision — 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
kronecker_prod Not yet run
unverified (harvested, no recorded run)
oncescuandreea/audio-retrieval/model/model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hbzhang/cvpr2020, is pointer only (licence: NONE) · get_code("fc6aa51656b4be1e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from hbzhang/cvpr2020, 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. No invocation recorded.

v2t_metrics Not yet run
unverified (harvested, no recorded run)
oncescuandreea/audio-retrieval/model/metric.py
code served (permissive licence) · get_code("382b08bd2c7acdef")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 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
retrieval_as_classification 4 other papers
3 dated earlier, 1 later
1907.13487 (2019-07)
Use What You Have: Video Retrieval Using Representations From Collaborative Experts
2104.00650 (2021-04)
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
2104.08271 (2021-04)
TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval
and 1 more not named here
kronecker_prod 2 other papers
2 dated earlier
1907.13487 (2019-07)
Use What You Have: Video Retrieval Using Representations From Collaborative Experts
2104.08271 (2021-04)
TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval

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 consider the task of retrieving audio using free-form natural language queries. To study this problem, which has received limited attention in the existing literature, we introduce challenging new benchmarks for text-based audio retrieval using text annotations sourced from the Audiocaps and Clotho datasets. We then employ these benchmarks to establish baselines for cross-modal audio retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into cross-modal text-based audio retrieval with free-form text queries.

For agents

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

get_harvested_code_for_paper("2105.02192")
get_code_for_paper("2105.02192")
have("2105.02192")

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

curl https://syntology.ai/api/ran/2105.02192.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.02192.svg)](https://syntology.ai/paper/2105.02192)

Connect an agent — have() is free.