SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.04463 · 2021

A multi-centre polyp detection and segmentation dataset for generalisability assessment

arXiv · PDF · Open in the Atlas

Code that ran

9 of 16 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 6 have no contract verdict; 3 failures of our instrument; 7 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/2106.04463.json · badge: /api/ran/2106.04463.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
sharibox/polypgen-benchmark canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
sharib-vision/PolypGen-Benchmark reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 3 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
sharibox/polypgen-benchmark/network/axialNet.py
code served (permissive licence) · get_code("d9def42110729a85")
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 Conv2d. 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)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
convrelu Ran
ran on a synthesized input
sharibox/polypgen-benchmark/network/axialNet.py
code served (permissive licence) · get_code("56689af33d286bee")
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 Sequential. 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)

ARGS = {
    "in_channels": 3,
    "out_channels": 16,
    "kernel_size": 3,
    "stride": 1,
    "padding": 1,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
detect_imgs Ran
ran on a synthesized input
sharibox/polypgen-benchmark/polypGen_inference-seg.py
code served (permissive licence) · get_code("228421b7a5601682")
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 1, dtype family float, shape (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 os
import tempfile
import numpy as np

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

# Create some dummy .tif files
test_files = ['image1.tif', 'image2.tif', 'photo.TIF', 'document.pdf', 'data.tif']
for filename in test_files:
    filepath = os.path.join(temp_dir, filename)
    with open(filepath, 'w') as f:
        f.write('dummy content')

# Define arguments for detect_imgs
ARGS = {
    'infolder': temp_dir,
    'ext': '.tif'
}
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 1, dtype family float, shape (4,) — shape (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
kmoment Ran
ran on a synthesized input
sharibox/polypgen-benchmark/network/network.py
code served (permissive licence) · get_code("d77b4e5c7bc5bd55")
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 float64, ndim 0, 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 numpy as np

# kmoment takes two parameters:
# - x: array-like input that will be raised to power k and summed
# - k: the power/moment order

# Create a small numpy array for x
x = np.array([1.0, 2.0, 3.0, 4.0])

# Create a scalar k value (moment order)
k = 2

ARGS = {
    "x": x,
    "k": k
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
locate_folders Ran
ran; our contract draft was wrong, not the code
sharib-vision/PolypGen-Benchmark/metrics/compute_seg.py
code served (permissive licence) · get_code("3297c96e4c60ba89")
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 1, dtype family float, shape (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 os
import tempfile
import shutil

# Create a temporary directory structure with test files
tmpdir = tempfile.mkdtemp()

# Create subdirectories with test .tif files containing 'c' in the name
subdir1 = os.path.join(tmpdir, "subdir1")
subdir2 = os.path.join(tmpdir, "subdir2")
os.makedirs(subdir1, exist_ok=True)
os.makedirs(subdir2, exist_ok=True)

# Create .tif files with 'c' in the name
open(os.path.join(subdir1, "channel_001.tif"), "w").close()
open(os.path.join(subdir1, "image_c.tif"), "w").close()
open(os.path.join(subdir2, "c_data.tif"), "w").close()

# Also create files that shouldn't match
open(os.path.join(subdir1, "image.tif"), "w").close()
open(os.path.join(subdir2, "data.txt"), "w").close()

ARGS = {
    "rootfolder": tmpdir
}
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 1, dtype family float, shape (2,) — shape (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
panel_imgs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sharib-vision/PolypGen-Benchmark/metrics/compute_seg.py
code served (permissive licence) · get_code("6d292246dab9d292")
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 (6, 10, 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 batch of images: 4 images, each 3x5 pixels, 3 channels (RGB)
N = 4  # number of images
m = 3  # height of each image
n = 5  # width of each image
c = 3  # number of channels

imgs = np.random.rand(N, m, n, c).astype(np.float32)

# Grid layout: 2x2 arrangement of images
grid = (2, 2)

ARGS = {
    "imgs": imgs,
    "grid": grid
}
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 (6, 10, 3) — shape (6, 10, 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
plotInference Ran
ran on a synthesized input
sharibox/polypgen-benchmark/main_polypGen.py
code served (permissive licence) · get_code("871e79260c9007eb")
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 Figure. 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 torch

torch.manual_seed(0)

# The function uses resize() on imgs and depth, which expects array-like inputs
# It calls plt.imshow() on the resized results
# imgs should be a 2D or 3D array (image or batch of images)
# depth should be a 2D or 3D array (depth map or batch of depth maps)

# Create sample image data - small 2D RGB image
imgs = np.random.rand(64, 48, 3).astype(np.float32)

# Create sample depth data - small 2D depth map
depth = np.random.rand(64, 48).astype(np.float32)

ARGS = {
    "imgs": imgs,
    "depth": depth,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, skimage, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
rescale_im_stack Ran
ran on a synthesized input
sharib-vision/PolypGen-Benchmark/metrics/compute_seg.py
code served (permissive licence) · get_code("868e1e3a3d191711")
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 4, dtype family float, shape (2, 256, 256, 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
import tempfile
import os
from PIL import Image

# Create temporary directory with test images
tmpdir = tempfile.mkdtemp()

# Create a few test images with different sizes
test_images = []
for i in range(2):
    # Create a simple RGB image with distinct dimensions
    img_array = np.random.randint(0, 256, (64 + i*10, 128 + i*10, 3), dtype=np.uint8)
    img = Image.fromarray(img_array)
    img_path = os.path.join(tmpdir, f"test_image_{i}.png")
    img.save(img_path)
    test_images.append(img_path)

ARGS = {
    "imfiles": test_images,
    "size": (256, 256)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (2, 256, 256, 3) — shape (2, 256, 256, 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
voc_cmap Ran
ran on a synthesized input
sharibox/polypgen-benchmark/datasets/polypGen2021.py
code served (permissive licence) · get_code("874968823d3561fe")
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 (256, 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

ARGS = {
    'N': 256,
    'normalized': True
}
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 (256, 3) — shape (256, 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
axial50s Not yet run
unverified (harvested, no recorded run)
sharibox/polypgen-benchmark/network/axialNet.py
code served (permissive licence) · get_code("df035572d17eaf87")
How it ran

no invocation recorded.

convert_to_separable_conv Not yet run
unverified (harvested, no recorded run)
sharibox/polypgen-benchmark/network/_deeplab.py
code served (permissive licence) · get_code("ce942a958c0ae909")
How it ran

no invocation recorded.

create_predFolder Not yet run
unverified (harvested, no recorded run)
sharibox/polypgen-benchmark/polypGen_inference-seg.py
code served (permissive licence) · get_code("4ed3491d5fe9d707")
How it ran

no invocation recorded.

deeplabv3_mobilenet Not yet run
unverified (harvested, no recorded run)
sharib-vision/PolypGen-Benchmark/network/modeling.py
code served (permissive licence) · get_code("26e4e1876120be62")
How it ran

no invocation recorded.

deeplabv3_resnet101 Not yet run
unverified (harvested, no recorded run)
sharib-vision/PolypGen-Benchmark/network/modeling.py
code served (permissive licence) · get_code("187bc8c967b6d23b")
How it ran

no invocation recorded.

deeplabv3_resnet50 Not yet run
unverified (harvested, no recorded run)
sharib-vision/PolypGen-Benchmark/network/modeling.py
code served (permissive licence) · get_code("85f770a1a3693de2")
How it ran

no invocation recorded.

download_extract Not yet run
unverified (harvested, no recorded run)
sharibox/polypgen-benchmark/datasets/polypGen2021.py
code served (permissive licence) · get_code("569164e3b040e8bb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 5 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 5 later) and 11 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
conv1x1 431 other papers
132 dated earlier, 5 the same month, 288 later, 5 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
convert_to_separable_conv 10 other papers
3 dated earlier, 6 later, 1 same year, order not determinable
1706.05587 (2017-06)
Rethinking Atrous Convolution for Semantic Image Segmentation
1905.03561 (2019-05)
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
2007.07984 (2020-07)
Leveraging Category Information for Single-Frame Visual Sound Source Separation
and 7 more not named here
deeplabv3_resnet50 4 other papers
1 dated earlier, 2 later, 1 same year, order not determinable
1706.05587 (2017-06)
Rethinking Atrous Convolution for Semantic Image Segmentation
2108.04562 (2021-08)
Deep Metric Learning for Open World Semantic Segmentation
and 1 more not named here
deeplabv3_mobilenet 2 other papers
1 later, 1 same year, order not determinable
Jain_Scaling_Semantic_Segmentation_Beyond_1K_Classes_on_a_Single_GPU_ICCV_2021_paper (2021 (year only))
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
2108.04562 (2021-08)
Deep Metric Learning for Open World Semantic Segmentation
deeplabv3_resnet101 2 other papers
1 later, 1 same year, order not determinable
Jain_Scaling_Semantic_Segmentation_Beyond_1K_Classes_on_a_Single_GPU_ICCV_2021_paper (2021 (year only))
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
2108.04562 (2021-08)
Deep Metric Learning for Open World Semantic Segmentation

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

Polyps in the colon are widely known cancer precursors identified by colonoscopy. Whilst most polyps are benign, the polyp's number, size and surface structure are linked to the risk of colon cancer. Several methods have been developed to automate polyp detection and segmentation. However, the main issue is that they are not tested rigorously on a large multicentre purpose-built dataset, one reason being the lack of a comprehensive public dataset. As a result, the developed methods may not generalise to different population datasets. To this extent, we have curated a dataset from six unique centres incorporating more than 300 patients. The dataset includes both single frame and sequence data with 3762 annotated polyp labels with precise delineation of polyp boundaries verified by six senior gastroenterologists. To our knowledge, this is the most comprehensive detection and pixel-level segmentation dataset (referred to as \textit{PolypGen}) curated by a team of computational scientists and expert gastroenterologists. The paper provides insight into data construction and annotation strategies, quality assurance, and technical validation. Our dataset can be downloaded from \url{ https://doi.org/10.7303/syn26376615}.

For agents

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

get_harvested_code_for_paper("2106.04463")
get_code_for_paper("2106.04463")
have("2106.04463")

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

curl https://syntology.ai/api/ran/2106.04463.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.04463.svg)](https://syntology.ai/paper/2106.04463)

Connect an agent — have() is free.