SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03022 · NeurIPS · 2022

HEAR: Holistic Evaluation of Audio Representations

Shinji Watanabe, Joseph Turian, Max Henry, Jesse Engel, Humair Khan, Colin Malloy, George Tzanetakis, Kirk Mcnally, Nicolas Pinto, Camille Noufi, Christian Clough, Eduardo Fonseca, and 2 more

arXiv · PDF · Open in the Atlas

Code that ran

3 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 3 have no contract verdict; 0 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/2203.03022.json · badge: /api/ran/2203.03022.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
neuralaudio/hear-eval-kit canonical (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
label_to_binary_vector Ran
ran on a synthesized input
neuralaudio/hear-eval-kit/heareval/score.py
code served (permissive licence) · get_code("78bbfdb0f93b2535")
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 1, dtype family float, shape (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)

# Test case 1: non-empty label list
label_input = [0, 2, 3]
num_labels_input = 5

ARGS = {
    "label": label_input,
    "num_labels": num_labels_input,
}
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 1, dtype family float, shape (5,) — shape (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
label_vocab_as_dict Ran
ran on a synthesized input
neuralaudio/hear-eval-kit/heareval/score.py
code served (permissive licence) · get_code("b49c243b3b8f3268")
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 pandas as pd

# Create a simple DataFrame with 'label' and 'idx' columns
df = pd.DataFrame({
    'label': ['cat', 'dog', 'bird', 'fish'],
    'idx': [0, 1, 2, 3]
})

ARGS = {
    'df': df,
    'key': 'label',
    'value': 'idx'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — 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
label_vocab_nlabels Ran
ran on a synthesized input
neuralaudio/hear-eval-kit/heareval/predictions/task_predictions.py
code served (permissive licence) · get_code("a3f31dcd665f7f62")
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. 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 tempfile
import pandas as pd
from pathlib import Path

# Create a temporary directory with a labelvocabulary.csv file
temp_dir = tempfile.TemporaryDirectory()
embedding_path = Path(temp_dir.name)

# Create a valid labelvocabulary.csv with idx column
label_data = pd.DataFrame({
    'idx': [0, 1, 2, 3],
    'label': ['label_0', 'label_1', 'label_2', 'label_3']
})
label_data.to_csv(embedding_path / 'labelvocabulary.csv', index=False)

ARGS = {
    'embedding_path': embedding_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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_logger Not yet run
unverified (harvested, no recorded run)
neuralaudio/hear-eval-kit/heareval/predictions/runner.py
code served (permissive licence) · get_code("e85245b6910393ed")
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, 0 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
label_to_binary_vector 1 other paper
1 dated earlier
2105.01051 (2021-05)
SUPERB: Speech processing Universal PERformance Benchmark
label_vocab_as_dict 1 other paper
1 dated earlier
2105.01051 (2021-05)
SUPERB: Speech processing Universal PERformance Benchmark

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

What audio embedding approach generalizes best to a wide range of downstream tasks across a variety of everyday domains without fine-tuning? The aim of the HEAR benchmark is to develop a general-purpose audio representation that provides a strong basis for learning in a wide variety of tasks and scenarios. HEAR evaluates audio representations using a benchmark suite across a variety of domains, including speech, environmental sound, and music. HEAR was launched as a NeurIPS 2021 shared challenge. In the spirit of shared exchange, each participant submitted an audio embedding model following a common API that is general-purpose, open-source, and freely available to use. Twenty-nine models by thirteen external teams were evaluated on nineteen diverse downstream tasks derived from sixteen datasets. Open evaluation code, submitted models and datasets are key contributions, enabling comprehensive and reproducible evaluation, as well as previously impossible longitudinal studies. It still remains an open question whether one single generalpurpose audio representation can perform as holistically as the human ear.

For agents

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

get_harvested_code_for_paper("2203.03022")
get_code_for_paper("2203.03022")
have("2203.03022")

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

curl https://syntology.ai/api/ran/2203.03022.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03022.svg)](https://syntology.ai/paper/2203.03022)

Connect an agent — have() is free.