SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.01955 · 2019

Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection

arXiv · PDF · Open in the Atlas

Code that ran

17 of 19 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 16 have no contract verdict; 1 failure 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/1909.01955.json · badge: /api/ran/1909.01955.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
xavysp/DexiNed canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
a-nau/Plane-Segmentation-Refinement community (classifier label)
classifier basis not recorded on the link
13 ran · 2 no recorded run
xavysp/MBIPED community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
check_if_file_is_image Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/image_other.py
code served (permissive licence) · get_code("962b8fa1e9017ffa")
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
import numpy as np

def check_if_file_is_image(filename):
    return filename.lower().endswith(('.png', '.jpg', '.jpeg', '.tiff', '.bmp', '.gif'))

ARGS = {
    'filename': 'test_image.png'
}
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 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
compute_convex_hull_for_mask Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/refiner/util/fall_back_segmentation.py
code served (permissive licence) · get_code("51a0c4713bee13a9")
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 int, shape (6, 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 cv2
import numpy as np

# Create a sample binary mask (2D numpy array)
# The mask should have some non-zero values for the convex hull to be computed
mask = np.zeros((10, 12), dtype=np.uint8)
# Add some points to the mask to create a meaningful convex hull
mask[2:5, 3:7] = 1
mask[6:9, 4:8] = 1
mask[3, 9] = 1

ARGS = {
    "mask": mask
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (6, 2) — shape (6, 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
compute_widened_contour_line_around_mask Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/refiner/clustering/edge_detection.py
code served (permissive licence) · get_code("771106050d7b2baa")
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 int, shape (10, 10) 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 cv2
import numpy as np

# Create a small binary mask for testing
# Using a simple 10x10 binary mask with some structure
mask = np.zeros((10, 10), dtype=np.uint8)
mask[3:7, 3:7] = 255  # Create a white square in the middle

ARGS = {
    "mask": mask,
    "ksize": 37
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (10, 10) — shape (10, 10) 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
dataset_info Ran
ran; our contract draft was wrong, not the code
xavysp/DexiNed/datasets.py
code served (permissive licence) · get_code("e43b592c20686019")
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)

# The function takes dataset_name and is_linux as parameters
# It simply looks up a dataset configuration from a hardcoded dict
# No complex objects needed - just strings and booleans

ARGS = {
    'dataset_name': 'BSDS',
    'is_linux': True
}
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
find_all_image_files_in_directory Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/image_other.py
code served (permissive licence) · get_code("48dc7d7468bdfdd7")
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 list, ndim 1, dtype family float; 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 os
import tempfile
import shutil

# Create a temporary directory with some test files
temp_dir = tempfile.mkdtemp()

# Create some image files
open(os.path.join(temp_dir, 'image1.png'), 'w').close()
open(os.path.join(temp_dir, 'image2.jpg'), 'w').close()
open(os.path.join(temp_dir, 'image3.jpeg'), 'w').close()
open(os.path.join(temp_dir, 'photo.TIFF'), 'w').close()
open(os.path.join(temp_dir, 'picture.bmp'), 'w').close()
open(os.path.join(temp_dir, 'animated.gif'), 'w').close()

# Create some non-image files
open(os.path.join(temp_dir, 'document.txt'), 'w').close()
open(os.path.join(temp_dir, 'data.csv'), 'w').close()

ARGS = {
    'directory': temp_dir
}
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 list, ndim 1, dtype family float — a list 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
find_matching_nested_list Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/refiner/util/fall_back_segmentation.py
code served (permissive licence) · get_code("45a5411d20e60e19")
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)

# The function find_matching_nested_list searches through a list of sublists
# looking for a sublist whose first element matches val, then returns the index.
# It uses: l (a list of lists), val (a value to match), l.index(), and == operator

# Construct test data
nested_list = [
    [10, 'a', 'b'],
    [20, 'c', 'd'],
    [30, 'e', 'f'],
    [40, 'g', 'h']
]

search_value = 20

ARGS = {
    'l': nested_list,
    'val': search_value
}
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
gamma_correction Ran
ran on a synthesized input
xavysp/MBIPED/data_augmentation.py
code served (permissive licence) · get_code("4e835882a8e92379")
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 3, dtype family float, shape (2, 2, 3) 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 image array (3D: height, width, channels)
image_data = np.array([
    [[0.2, 0.4, 0.6], [0.1, 0.5, 0.9]],
    [[0.3, 0.7, 0.8], [0.4, 0.2, 0.5]]
], dtype=np.float32)

# Gamma value
gamma_value = 2.2

# Boolean flag for gamma correction
gamma_flag = True

ARGS = {
    "i": image_data,
    "g": gamma_value,
    "gamma": gamma_flag
}
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 3, dtype family float, shape (2, 2, 3) — shape (2, 2, 3) 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_depth_of_nested_list Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/other.py
code served (permissive licence) · get_code("6e296812cf5c772f")
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
import numpy as np

# Construct arguments for get_depth_of_nested_list
# The function takes a list parameter 'l' and computes its nesting depth

# Test with various nested list structures
ARGS = {
    "l": [[[1, 2], [3, 4]], [[5, 6], [7, 8]]]
}
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 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
get_grayscaled_image Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/image_modification.py
code served (permissive licence) · get_code("e936f375f1204ee3")
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 int, 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 cv2
import numpy as np

# Create a small test image - 3D BGR image
img_3d = np.random.randint(0, 256, (4, 5, 3), dtype=np.uint8)

# Create a small test image - 2D grayscale image
img_2d = np.random.randint(0, 256, (4, 5), dtype=np.uint8)

ARGS = {
    "img": img_3d
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, 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
get_immediate_subdirectories Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/directories.py
code served (permissive licence) · get_code("da6f23f917f8e66a")
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 list, ndim 1, dtype family float; 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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()

# Create some subdirectories
subdir1 = os.path.join(temp_dir, "subdir1")
subdir2 = os.path.join(temp_dir, "subdir2")
subdir3 = os.path.join(temp_dir, "subdir3")

os.makedirs(subdir1, exist_ok=True)
os.makedirs(subdir2, exist_ok=True)
os.makedirs(subdir3, exist_ok=True)

# Create a file (not a directory) to ensure it's filtered out
file_path = os.path.join(temp_dir, "file.txt")
with open(file_path, "w") as f:
    f.write("test")

ARGS = {
    "dir": temp_dir
}
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 list, ndim 1, dtype family float — a list 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
get_n_unique_rows Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/other.py
code served (permissive licence) · get_code("c90cc20d70b48f19")
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 numpy as np

# The function get_n_unique_rows takes an 'edge' parameter
# It converts rows to tuples, finds unique rows, and returns the count
# 'edge' should be a 2D array-like structure where each row can be converted to a tuple

edge = np.array([
    [1, 2, 3],
    [4, 5, 6],
    [1, 2, 3],
    [7, 8, 9]
])

ARGS = {
    "edge": edge
}
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 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
get_unique_rows Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/other.py
code served (permissive licence) · get_code("d176d029260f74a6")
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 int, shape (3, 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 numpy as np

# The function get_unique_rows takes an edge array and returns unique rows
# It uses np.unique with axis=0, so we need a 2D numpy array

# Create a small 2D array with some duplicate rows
edge = np.array([
    [1, 2, 3, 4],
    [5, 6, 7, 8],
    [1, 2, 3, 4],
    [9, 10, 11, 12]
])

ARGS = {
    "edge": edge
}
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 int, shape (3, 4) — shape (3, 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
get_width_cropped_image Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/image_modification.py
code served (permissive licence) · get_code("321fb290ea271633")
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 3, dtype family float, shape (2, 2, 3) 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 crops an image tensor along the width dimension
# image: 2D or 3D tensor where the second dimension is width
# roi: list/tuple with [x_start, y_start, width, height] or similar indexing
#      where roi[0] is the starting column and roi[2] is the width

# Create a small image tensor (batch_size, height, width) = (2, 4, 3)
image = torch.randn(2, 4, 3)

# Create ROI: [x_start, y_start, width, height]
# roi[0] = starting column index
# roi[2] = width (number of columns to include)
roi = [1, 0, 2]  # start at column 1, take 2 columns

ARGS = {
    "image": image,
    "roi": roi,
}
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 3, dtype family float, shape (2, 2, 3) — shape (2, 2, 3) 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
image_normalization Ran
ran on a synthesized input
xavysp/MBIPED/data_augmentation.py
code served (permissive licence) · get_code("dadc5e13005d80a2")
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, 3) 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 (grayscale or color)
# Using a simple 4x3 image with values in typical image range
test_image = np.array([
    [50, 100, 150],
    [75, 125, 200],
    [25, 175, 225],
    [10, 90, 180]
], dtype=np.uint8)

ARGS = {
    'img': test_image,
    'img_min': 0,
    'img_max': 255
}
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, 3) — shape (4, 3) 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
make_dirs Ran
ran on a synthesized input
xavysp/MBIPED/data_augmentation.py
code served (permissive licence) · get_code("e67ef5668121eaab")
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 os
import tempfile

# The function takes a 'paths' parameter which should be a string representing
# a directory path. We'll use a temporary directory path that doesn't exist yet.
temp_dir = tempfile.gettempdir()
test_paths = os.path.join(temp_dir, "test_make_dirs_" + str(os.getpid()))

ARGS = {
    "paths": test_paths
}
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
scale_image Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/image_modification.py
code served (permissive licence) · get_code("0112cce5a48470ac")
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 3, dtype family int, shape (3, 4, 3) 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 cv2
import numpy as np

# Create a small test image (height=6, width=8, 3 channels for BGR)
img = np.random.randint(0, 256, (6, 8, 3), dtype=np.uint8)

ARGS = {
    "img": img,
    "scale": 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (3, 4, 3) — shape (3, 4, 3) 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
select_subset_from_list Ran
ran on a synthesized input
a-nau/Plane-Segmentation-Refinement/utils/image_other.py
code served (permissive licence) · get_code("a10498279a84a98a")
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 list, 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 random

# Set seed for reproducibility
random.seed(0)

# Construct arguments for select_subset_from_list
list_data = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
subset_size = 5

ARGS = {
    "list_data": list_data,
    "subset_size": subset_size,
}
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 list, ndim 1, dtype family int — a list 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
dbscan_with_masked_image Not yet run
unverified (harvested, no recorded run)
a-nau/Plane-Segmentation-Refinement/refiner/clustering/dbscan.py
code served (permissive licence) · get_code("4ae062da72b50fb3")
How it ran

no invocation recorded.

dbscan_with_points Not yet run
unverified (harvested, no recorded run)
a-nau/Plane-Segmentation-Refinement/refiner/clustering/dbscan.py
code served (permissive licence) · get_code("aed54a259fe338ee")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 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 19 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

This paper proposes a Deep Learning based edge detector, which is inspired on both HED (Holistically-Nested Edge Detection) and Xception networks. The proposed approach generates thin edge-maps that are plausible for human eyes; it can be used in any edge detection task without previous training or fine tuning process. As a second contribution, a large dataset with carefully annotated edges has been generated. This dataset has been used for training the proposed approach as well the state-of-the-art algorithms for comparisons. Quantitative and qualitative evaluations have been performed on different benchmarks showing improvements with the proposed method when F-measure of ODS and OIS are considered.

For agents

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

get_harvested_code_for_paper("1909.01955")
get_code_for_paper("1909.01955")
have("1909.01955")

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

curl https://syntology.ai/api/ran/1909.01955.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.01955.svg)](https://syntology.ai/paper/1909.01955)

Connect an agent — have() is free.