SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.06182 · 2018

CREPE: A Convolutional Representation for Pitch Estimation

arXiv · PDF · Open in the Atlas

Code that ran

20 of 23 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, 1 violated it and 17 have no contract verdict; 2 failures of our instrument; 3 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/1802.06182.json · badge: /api/ran/1802.06182.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
marl/crepe canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
bpiyush/SoundOfWater community (classifier label)
classifier basis not recorded on the link
17 ran · 3 no recorded run
FunctionStatusWhere it lives
add_margin Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/image.py
code served (permissive licence) · get_code("69866daba6f33b37")
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 Image. 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
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a small test PIL image
pil_img = Image.new('RGB', (10, 8), color=(255, 100, 50))

ARGS = {
    'pil_img': pil_img,
    'top': 5,
    'right': 7,
    'bottom': 3,
    'left': 4,
    'color': (200, 150, 100)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
build_and_load_model Ran
ran; our contract draft was wrong, not the code
marl/crepe/crepe/core.py
code served (permissive licence) · get_code("0478670b3c919823")
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 Functional. 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
import tempfile
from unittest.mock import patch, MagicMock

# Create a temporary directory to act as the package directory
temp_dir = tempfile.mkdtemp()

# Create mock .h5 files so load_weights doesn't fail
# We'll patch the load_weights method to do nothing
def mock_load_weights(self, filepath):
    pass

ARGS = {
    'model_capacity': 'tiny'
}

# Patch the load_weights method to prevent actual file I/O
import tensorflow.keras.models
original_load_weights = tensorflow.keras.models.Model.load_weights
tensorflow.keras.models.Model.load_weights = mock_load_weights

# Also patch os.path.dirname and os.path.realpath to return our temp dir
original_dirname = os.path.dirname
original_realpath = os.path.realpath

def mock_dirname(path):
    return temp_dir

def mock_realpath(path):
    return os.path.join(temp_dir, os.path.basename(path))

os.path.dirname = mock_dirname
os.path.realpath = mock_realpath
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
calculate_iou Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/metrics.py
code served (permissive licence) · get_code("b87e5ad31fa0cad5")
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 float, 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

# Set random seed for reproducibility
torch.manual_seed(0)

# Define bounding boxes in format (x1, y1, x2, y2)
# box1: top-left at (10, 20), bottom-right at (50, 60)
box1 = (10, 20, 50, 60)

# box2: top-left at (30, 40), bottom-right at (70, 80)
# This box overlaps with box1
box2 = (30, 40, 70, 80)

ARGS = {
    "box1": box1,
    "box2": box2,
}
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 float, 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
center_crop Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/image.py
code served (permissive licence) · get_code("d6fe3eeba94bee55")
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 Image. 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.

from PIL import Image
import numpy as np

# Create a test image: 800x600 pixels (wider than tall)
# This will be center-cropped to a 600x600 square
img_array = np.random.randint(0, 256, (600, 800, 3), dtype=np.uint8)
test_image = Image.fromarray(img_array, mode='RGB')

ARGS = {
    'im': test_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
compute_intersection_1d Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/metrics.py
code served (permissive licence) · get_code("5e9b6432446d547d")
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 int, ndim 0, dtype family int, 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)

# compute_intersection_1d takes two parameters: x and y
# Both are used with sorted() and then unpacked into two values each
# They should be sequences (lists, tuples, or similar) of numeric values
# The function sorts them and computes 1D interval intersection

x = [1, 5]
y = [3, 7]

ARGS = {
    "x": x,
    "y": y
}
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 int, ndim 0, dtype family int, 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
compute_union_1d Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/metrics.py
code served (permissive licence) · get_code("58f2e9c573ba8489")
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 float, 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

torch.manual_seed(0)

# The function compute_union_1d takes two parameters: x and y
# It expects them to be sequences/iterables that can be sorted and indexed
# It calls sorted(x) and sorted(y), then unpacks into two elements each
# So x and y should be sequences of length 2 (or convertible to length 2)

x = [1.0, 5.0]
y = [3.0, 7.0]

ARGS = {
    "x": x,
    "y": y
}
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 float, 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
define_axes Ran
ran on a synthesized input
bpiyush/SoundOfWater/demo/util.py
code served (permissive licence) · get_code("174fc5323ab98cbb")
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 matplotlib.pyplot as plt

ARGS = {
    'figsize': (13, 4),
    'width_ratios': [0.22, 0.78]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib — 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
load_json Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/io.py
code served (permissive licence) · get_code("f2e5cc3d297dbfda")
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 json
import tempfile
import os

# Create a temporary JSON file with valid test data
temp_dir = tempfile.mkdtemp()
test_json_path = os.path.join(temp_dir, "test.json")

test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "dict"}
}

with open(test_json_path, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "path": test_json_path
}
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 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
load_pkl Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/io.py
code served (permissive licence) · get_code("a7be5e2bbedb930e")
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 pickle
import tempfile
import os

# Create a temporary pickle file for testing
temp_dir = tempfile.gettempdir()
test_data = {"key": "value", "number": 42, "list": [1, 2, 3]}

# Write test data to a pickle file
pkl_path = os.path.join(temp_dir, "test_load.pkl")
with open(pkl_path, 'wb') as f:
    pickle.dump(test_data, f)

ARGS = {
    'path': pkl_path,
    'encoding': 'ascii'
}
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 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
load_yml Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/io.py
code served (permissive licence) · get_code("5b21eaf9ef52a0da")
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 os
import tempfile
import yaml

# Create a temporary YAML file for testing
temp_dir = tempfile.mkdtemp()
yaml_file_path = os.path.join(temp_dir, "test_config.yml")

# Write a simple YAML file
test_data = {
    'param1': 'value1',
    'param2': 42,
    'param3': [1, 2, 3],
    'nested': {
        'key': 'value'
    }
}

with open(yaml_file_path, 'w') as f:
    yaml.dump(test_data, f)

ARGS = {
    'path': yaml_file_path,
    'loader_type': 'default'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
output_path Ran
ran; our contract draft was wrong, not the code
marl/crepe/crepe/core.py
code served (permissive licence) · get_code("782c3ee036f8a2e1")
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 str. 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
import re

ARGS = {
    'file': '/path/to/audio.wav',
    'suffix': '.txt',
    'output_dir': '/output'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
pad_to_square Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/image.py
code served (permissive licence) · get_code("78cfceace594ec65")
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 Image. 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.

from PIL import Image
import numpy as np

# Create a small PIL Image for testing
# Make a simple 10x8 RGB image (not square)
img_array = np.random.randint(0, 256, (8, 10, 3), dtype=np.uint8)
pil_img = Image.fromarray(img_array, mode='RGB')

ARGS = {
    'im': pil_img,
    'color': (0, 0, 0)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
project_2d_to_6d Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/keypoint_matching.py
code served (permissive licence) · get_code("b714e26e08416dae")
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 ndarray, ndim 2, dtype family float, shape (6, 6) 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 numpy as np

# Create a small 2D array with shape (N, 2)
N = 3
X = np.array([
    [1.0, 2.0],
    [3.0, 4.0],
    [5.0, 6.0]
], dtype=np.float32)

ARGS = {
    "X": X
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (6, 6) — shape (6, 6) 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
project_6d_to_2d Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/keypoint_matching.py
code served (permissive licence) · get_code("d33463ccd2e455f2")
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 ndarray, ndim 2, dtype family float, shape (3, 2) 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 numpy as np

# Construct a valid Z array with shape (2N, 6)
# where even rows contain X coordinates in columns 0:2
# and odd rows contain the same X coordinates in columns 2:4
N = 3
Z = np.zeros((2 * N, 6))

# Set even rows (indices 0, 2, 4) with X values in columns 0:2
Z[0, 0:2] = [1.0, 2.0]
Z[2, 0:2] = [3.0, 4.0]
Z[4, 0:2] = [5.0, 6.0]

# Set odd rows (indices 1, 3, 5) with same X values in columns 2:4
Z[1, 2:4] = [1.0, 2.0]
Z[3, 2:4] = [3.0, 4.0]
Z[5, 2:4] = [5.0, 6.0]

# Fill remaining columns with arbitrary values (not used by the function)
Z[:, 4:6] = 0.0

ARGS = {
    "Z": Z
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 2) — shape (3, 2) 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
read_html_file Ran
ran on a synthesized input
bpiyush/SoundOfWater/demo/util.py
code served (permissive licence) · get_code("af4b98b7641b70f2")
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 str. 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 os

# Create a temporary HTML file
temp_dir = tempfile.mkdtemp()
html_file_path = os.path.join(temp_dir, "test.html")

html_content = """<!DOCTYPE html>
<html>
<head>
    <title>Test Page</title>
</head>
<body>
    <h1>Hello World</h1>
    <p>This is a test HTML file.</p>
</body>
</html>"""

with open(html_file_path, 'w') as f:
    f.write(html_content)

ARGS = {
    "file": html_file_path
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
recursive_attr Ran
ran on a synthesized input
bpiyush/SoundOfWater/sound_of_water/audio_pitch/model.py
code served (permissive licence) · get_code("40aef86f184e81f7")
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 Linear. 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)

# Build a nested module structure to test recursive attribute access
class SubModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.value = 42

class NestedModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.sub = SubModule()
        self.param = nn.Parameter(torch.randn(2, 4))

class MainModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.nested = NestedModule()
        self.tensor = torch.randn(2, 4)

# Instantiate the module
module = MainModule()

# Test cases for recursive_attr:
# 1. Simple attribute: "nested" -> returns NestedModule instance
# 2. Nested attribute: "nested.sub" -> returns SubModule instance
# 3. Deeply nested attribute: "nested.sub.linear" -> returns Linear layer
# 4. Deeply nested value: "nested.sub.value" -> returns 42
# 5. Tensor attribute: "tensor" -> returns tensor

ARGS = {
    "module": module,
    "attr": "nested.sub.linear"
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
timestamp_to_seconds Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/epic.py
code served (permissive licence) · get_code("6a7ab8acfa1aad95")
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 float, 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 datetime

def timestamp_to_seconds(timestamp: str):
    time_obj = datetime.datetime.strptime(timestamp, '%H:%M:%S.%f')
    total_seconds = time_obj.time().second + time_obj.time().minute * 60 + time_obj.time().hour * 3600 + time_obj.time().microsecond / 1000000
    return total_seconds

ARGS = {
    "timestamp": "12:34:56.123456"
}
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 float, 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
to_local_average_cents Ran
ran, violated the contract we drafted
marl/crepe/crepe/core.py
code served (permissive licence) · get_code("78fc7cf6c4993dc2")
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) and returned float64, 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 numpy as np

# Test case 1: 1D salience array
salience_1d = np.array([0.1, 0.2, 0.5, 0.3, 0.2, 0.1, 0.05, 0.15, 0.25, 0.35])

# Test case 2: 2D salience array
salience_2d = np.array([
    [0.1, 0.2, 0.5, 0.3, 0.2, 0.1, 0.05, 0.15, 0.25, 0.35],
    [0.05, 0.15, 0.3, 0.4, 0.25, 0.2, 0.1, 0.05, 0.15, 0.2]
])

ARGS = {
    "salience": salience_1d,
    "center": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
tqdm_iterator Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/log.py
code served (permissive licence) · get_code("fcc214ee70fe8c3c")
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 tqdm_asyncio. 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
from tqdm.auto import tqdm

torch.manual_seed(0)

# Simple list of items to iterate over
items = [1, 2, 3, 4, 5]

# Description for the progress bar
desc = "Processing items"

# Bar format string for customizing the progress bar appearance
bar_format = "{l_bar}{bar}{r_bar}"

# Additional kwargs that tqdm accepts
additional_kwargs = {
    "total": 5,
    "leave": True,
    "disable": False,
}

ARGS = {
    "items": items,
    "desc": desc,
    "bar_format": bar_format,
    **additional_kwargs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tqdm_asyncio — a tqdm_asyncio output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a tqdm_asyncio 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
warp Ran
ran on a synthesized input
bpiyush/SoundOfWater/shared/utils/keypoint_matching.py
code served (permissive licence) · get_code("422a90cfab67fc09")
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 ndarray, ndim 2, dtype family float, shape (4, 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 numpy as np

# Create a small test image
im = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0],
    [7.0, 8.0, 9.0]
], dtype=np.float32)

# Create a transformation matrix M
# The function expects M to be applied as: [u, v] = [[i, j, 0, 0, 1, 0], [0, 0, i, j, 0, 1]] @ M
# M should be a 6-element vector or 6x1 array for the matrix multiplication to work
M = np.array([1.0, 0.0, 0.0, 1.0, 0.0, 0.0], dtype=np.float32)

# Output shape
output_shape = (4, 5)

ARGS = {
    "im": im,
    "M": M,
    "output_shape": output_shape
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 5) — shape (4, 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
check_audio Not yet run
unverified (harvested, no recorded run)
bpiyush/SoundOfWater/shared/utils/misc.py
code served (permissive licence) · get_code("05cc638a791e3258")
How it ran

no invocation recorded.

compute_spec_freq_mean Not yet run
unverified (harvested, no recorded run)
bpiyush/SoundOfWater/shared/utils/audio.py
code served (permissive licence) · get_code("6c49fe145f92059d")
How it ran

no invocation recorded.

download_youtube_video Not yet run
unverified (harvested, no recorded run)
bpiyush/SoundOfWater/shared/utils/misc.py
code served (permissive licence) · get_code("429cb9cff7a4aec9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 23 samples lifted from this paper's linked repositories, 23 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 23 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.

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 task of estimating the fundamental frequency of a monophonic sound recording, also known as pitch tracking, is fundamental to audio processing with multiple applications in speech processing and music information retrieval. To date, the best performing techniques, such as the pYIN algorithm, are based on a combination of DSP pipelines and heuristics. While such techniques perform very well on average, there remain many cases in which they fail to correctly estimate the pitch. In this paper, we propose a data-driven pitch tracking algorithm, CREPE, which is based on a deep convolutional neural network that operates directly on the time-domain waveform. We show that the proposed model produces state-of-the-art results, performing equally or better than pYIN. Furthermore, we evaluate the model's generalizability in terms of noise robustness. A pre-trained version of CREPE is made freely available as an open-source Python module for easy application.

For agents

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

get_harvested_code_for_paper("1802.06182")
get_code_for_paper("1802.06182")
have("1802.06182")

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

curl https://syntology.ai/api/ran/1802.06182.json

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

[![Syntology run record](https://syntology.ai/api/ran/1802.06182.svg)](https://syntology.ai/paper/1802.06182)

Connect an agent — have() is free.