SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.03535 · 2018

Cell Detection with Star-convex Polygons

arXiv · PDF · Open in the Atlas

Code that ran

17 of 33 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 14 have no contract verdict; 3 failures of our instrument; 16 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/1806.03535.json · badge: /api/ran/1806.03535.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
hthierno/pytorch-stardist community (classifier label)
classifier basis not recorded on the link
11 ran · 8 no recorded run
uhlmanngroup/splinedist community (classifier label)
classifier basis not recorded on the link
5 ran · 7 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 1 no recorded run
FunctionStatusWhere it lives
choice Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/csbdeep_utils.py
code served (permissive licence) · get_code("c9012ff9b8f828b4")
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 numpy as np

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

# Define the population - can be a list of any hashable items
population = [1, 2, 3, 4, 5, 10, 20, 30]

# Define ARGS dict with all parameters
ARGS = {
    "population": population,
    "k": 3,
    "replace": 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 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
cmap_from_hls Ran
ran on a synthesized input
uhlmanngroup/splinedist/splinedist/plot/render.py
code served (permissive licence) · get_code("42c65b2291f9d204")
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 ListedColormap. 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

# Analyze the function:
# - h, l, s are parameters that get zipped together
# - They should be array-like with the same length
# - h is used modulo 1
# - l and s are clipped to [0, 1]
# - They're zipped together and passed to colorsys.hls_to_rgb
# - cols[0] is set to 0, so cols must be a numpy array
# - The function returns a matplotlib colormap

# Create small arrays for h, l, s with distinct sizes to avoid ambiguity
h = np.array([0.1, 0.5, 0.9, 1.2])  # 4 values
l = np.array([0.2, 0.4, 0.6, 0.8])  # 4 values, same length as h
s = np.array([0.3, 0.5, 0.7, 0.9])  # 4 values, same length as h

ARGS = {
    'h': h,
    'l': l,
    's': s
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ListedColormap — a ListedColormap output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ListedColormap 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
dist_to_coord Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/geometry/geom2d.py
code served (permissive licence) · get_code("cf3a9d8cf1cd5b76")
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, 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

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

# Construct arguments for dist_to_coord function
n_polys = 2
n_rays = 4

# dist: shape (n_polys, n_rays) - distances from center points
dist = np.random.rand(n_polys, n_rays).astype(np.float32) * 10

# points: shape (n_polys, 2) - center points in cartesian coordinates
points = np.array([[5.0, 3.0], [2.0, 7.0]], dtype=np.float32)

# scale_dist: tuple of length 2 - scaling factors for x and y
scale_dist = (1.5, 2.0)

ARGS = {
    "dist": dist,
    "points": points,
    "scale_dist": scale_dist,
}
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, 4) — shape (2, 2, 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
edt_prob Ran
ran on a synthesized input
uhlmanngroup/splinedist/splinedist/utils.py
code served (permissive licence) · get_code("a87d2df8f4ce612f")
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 (5, 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 simple labeled image for testing
# 2D image with two labeled regions
lbl_img = np.array([
    [0, 0, 1, 1, 0],
    [0, 1, 1, 1, 0],
    [0, 1, 1, 1, 0],
    [2, 2, 0, 0, 0],
    [2, 2, 0, 0, 0]
], dtype=np.int32)

# Define anisotropy (sampling) - can be None or a tuple/list
anisotropy = (1.0, 1.0)

ARGS = {
    'lbl_img': lbl_img,
    'anisotropy': anisotropy
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
edt, numpy, scipy — 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 (5, 5) — shape (5, 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
fill_label_holes Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/utils.py
code served (permissive licence) · get_code("3448ca18d7c202c7")
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 (5, 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
from scipy.ndimage.morphology import distance_transform_edt, binary_fill_holes
from scipy.ndimage.measurements import find_objects

# Create a small label image with some holes to fill
lbl_img = np.array([
    [0, 0, 0, 0, 0],
    [0, 1, 1, 1, 0],
    [0, 1, 0, 1, 0],  # hole in label 1
    [0, 1, 1, 1, 0],
    [0, 0, 0, 0, 0]
], dtype=np.int32)

ARGS = {
    "lbl_img": lbl_img,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 (5, 5) — shape (5, 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_valid_inds Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/sample_patches.py
code served (permissive licence) · get_code("c27f24601d5ec74e")
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, ndim 2, 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 numpy as np

# Create a simple image as a numpy array
# Using distinct dimensions: 5x7 for 2D image
img = np.random.rand(5, 7).astype(np.float32)

# Define patch_size as a tuple matching image dimensions
patch_size = (3, 3)

# Define a simple patch_filter function
# It takes img and patch_size, returns a boolean mask of same shape as img
def patch_filter(img, patch_size):
    # Return a boolean mask where all values are True (all patches are valid)
    return np.ones(img.shape, dtype=bool)

ARGS = {
    "img": img,
    "patch_size": patch_size,
    "patch_filter": patch_filter,
}
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 tuple, ndim 2, dtype family int — a tuple 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
is_array_of_integers Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/matching.py
code served (permissive licence) · get_code("d1f03663983cd95f")
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 numpy as np

# Test case 1: Valid numpy array of integers
y_valid_int = np.array([1, 2, 3, 4, 5], dtype=np.int32)

# Test case 2: Valid numpy array of integers (different dtype)
y_valid_int64 = np.array([10, 20, 30], dtype=np.int64)

# Test case 3: Numpy array of floats (should return False)
y_float = np.array([1.0, 2.0, 3.0], dtype=np.float32)

# Test case 4: Not a numpy array (should return False)
y_list = [1, 2, 3]

# Test case 5: Not a numpy array - Python int
y_int = 5

ARGS = {
    "y": y_valid_int
}
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 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
label_are_sequential Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/matching.py
code served (permissive licence) · get_code("7bbadcb4ea3c41c3")
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 numpy as np

def label_are_sequential(y):
    """ returns true if y has only sequential labels from 1... """
    labels = np.unique(y)
    return set(labels) - {0} == set(range(1, 1 + labels.max()))

# Test case 1: Sequential labels from 1 to 3 (should return True)
y_sequential = np.array([0, 1, 2, 3, 1, 2, 0, 3])

ARGS = {
    "y": y_sequential
}
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 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
label_overlap Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/matching.py
code served (permissive licence) · get_code("ae3b33643197b353")
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, 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
from numba import jit

def _raise(err):
    raise err

def label_are_sequential(y):
    """ returns true if y has only sequential labels from 1... """
    labels = np.unique(y)
    return set(labels) - {0} == set(range(1, 1 + labels.max()))

def is_array_of_integers(y):
    return isinstance(y, np.ndarray) and np.issubdtype(y.dtype, np.integer)

def _check_label_array(y, name=None, check_sequential=False):
    err = ValueError('{label} must be an array of {integers}.'.format(label='labels' if name is None else name, integers=('sequential ' if check_sequential else '') + 'non-negative integers'))
    is_array_of_integers(y) or _raise(err)
    if len(y) == 0:
        return True
    if check_sequential:
        label_are_sequential(y) or _raise(err)
    else:
        y.min() >= 0 or _raise(err)
    return True

@jit(nopython=True)
def _label_overlap(x, y):
    x = x.ravel()
    y = y.ravel()
    overlap = np.zeros((1 + x.max(), 1 + y.max()), dtype=np.uint)
    for i in range(len(x)):
        overlap[x[i], y[i]] += 1
    return overlap

def label_overlap(x, y, check=True):
    if check:
        _check_label_array(x, 'x', True)
        _check_label_array(y, 'y', True)
        x.shape == y.shape or _raise(ValueError('x and y must have the same shape'))
    return _label_overlap(x, y)

# Setup valid arguments
x = np.array([[1, 2], [2, 1]], dtype=np.int32)
y = np.array([[1, 1], [2, 2]], dtype=np.int32)

ARGS = {
    'x': x,
    'y': y,
    'check': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numba, 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, 3) — shape (3, 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
normalize Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/csbdeep_utils.py
code served (permissive licence) · get_code("74995849a380d482")
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 array with diverse values
np.random.seed(0)
x = np.random.rand(4, 5).astype(np.float32) * 100 + 50

ARGS = {
    'x': x,
    'pmin': 3,
    'pmax': 99.8,
    'axis': None,
    'clip': False,
    'eps': 1e-20,
    'dtype': np.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numexpr, 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
normalize_mi_ma Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/csbdeep_utils.py
code served (permissive licence) · get_code("267d15a20247127d")
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

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

# Create sample input arrays with distinct shapes
x = np.random.randn(4, 3).astype(np.float32)
mi = np.random.randn(4, 3).astype(np.float32) - 2
ma = np.random.randn(4, 3).astype(np.float32) + 2

# Ensure ma > mi for valid normalization
ma = ma + np.abs(mi) + 1

ARGS = {
    'x': x,
    'mi': mi,
    'ma': ma,
    'clip': True,
    'eps': 1e-20,
    'dtype': np.float32
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numexpr, 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
path_absolute Ran
ran; our contract draft was wrong, not the code
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/utils.py
code served (permissive licence) · get_code("be509cf705126aab")
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

def path_absolute(path_relative):
    """ Get absolute path to resource"""
    base_path = os.path.abspath(os.path.dirname(__file__))
    return os.path.join(base_path, path_relative)

ARGS = {
    "path_relative": "data/config.json"
}
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
path_absolute Ran
ran; our contract draft was wrong, not the code
uhlmanngroup/splinedist/splinedist/utils.py
code served (permissive licence) · get_code("e6494e5bfe49a3b5")
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 tempfile

# Create a temporary directory to act as the base path
# This simulates the __file__ location
temp_dir = tempfile.mkdtemp()

# The function uses os.path.abspath(os.path.dirname(__file__)) to get base_path
# and then os.path.join(base_path, path_relative) to construct the absolute path
# We just need to provide a relative path string

path_relative = "subdir/resource.txt"

ARGS = {
    "path_relative": path_relative
}
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
random_hls Ran
ran on a synthesized input
uhlmanngroup/splinedist/splinedist/plot/render.py
code served (permissive licence) · get_code("620665ea9afc94c4")
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, ndim 2, 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

ARGS = {
    "n": 2 ** 16,
    "h0": 0.33,
    "l0": (0.8, 1),
    "s0": (0.5, 0.8)
}
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 tuple, ndim 2, dtype family float — a tuple 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
random_label_cmap Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from stardist/stardist
pointer only · get_code("78a539521e49ce67")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

random_label_cmap Ran
ran on a synthesized input
uhlmanngroup/splinedist/splinedist/plot/plot.py
code served (permissive licence) · get_code("2a0c16b0b5362349")
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 ListedColormap. 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 matplotlib.colors

ARGS = {
    "n": 256,
    "h": (0.0, 1.0),
    "l": (0.4, 1.0),
    "s": (0.2, 0.8),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ListedColormap — a ListedColormap output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ListedColormap 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
star_dist Ran
ran on a synthesized input
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/geometry/geom2d.py
code served (permissive licence) · get_code("0cfe987cd22b54ac")
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 (4, 3, 32) 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

def _raise(e):
    raise e

# Create a small label image (2D array with integer labels)
# Shape: (4, 3) - small but distinct dimensions
label_image = np.array([
    [0, 1, 1],
    [0, 1, 2],
    [3, 3, 2],
    [3, 0, 0]
], dtype=np.uint16)

ARGS = {
    'a': label_image,
    'n_rays': 32,
    'grid': (1, 1),
    'mode': 'python'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gputools, 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 (4, 3, 32) — shape (4, 3, 32) 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
dist_to_coord Not yet run
unverified (harvested, no recorded run)
uhlmanngroup/splinedist/splinedist/geometry/geom2d.py
code served (permissive licence) · get_code("2477234e229d4ac5")
How it ran

no invocation recorded.

draw_polygons Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from stardist/stardist
pointer only · get_code("ea01a227751d9661")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

draw_polygons Not yet run
unverified (harvested, no recorded run)
uhlmanngroup/splinedist/splinedist/plot/plot.py
code served (permissive licence) · get_code("a69140da1a089e81")
How it ran

no invocation recorded.

edt_prob Not yet run
unverified (harvested, no recorded run)
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/utils.py
code served (permissive licence) · get_code("8bedca20732673c0")
How it ran

no invocation recorded.

non_maximum_suppression Not yet run
unverified (harvested, no recorded run)
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/nms.py
code served (permissive licence) · get_code("e2dcd6ed644b4198")
How it ran

no invocation recorded.

non_maximum_suppression Not yet run
unverified (harvested, no recorded run)
uhlmanngroup/splinedist/splinedist/nms.py
code served (permissive licence) · get_code("141dc23558e58934")
How it ran

no invocation recorded.

non_maximum_suppression_3d Not yet run
unverified (harvested, no recorded run)
uhlmanngroup/splinedist/splinedist/nms.py
code served (permissive licence) · get_code("76c1af1838b03158")
How it ran

no invocation recorded.

non_maximum_suppression_3d_sparse Not yet run
unverified (harvested, no recorded run)
uhlmanngroup/splinedist/splinedist/nms.py
code served (permissive licence) · get_code("c87e4462ca73b3f7")
How it ran

no invocation recorded.

non_maximum_suppression_inds Not yet run
unverified (harvested, no recorded run)
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/nms.py
code served (permissive licence) · get_code("8237fa3b96720d36")
How it ran

no invocation recorded.

non_maximum_suppression_sparse Not yet run
unverified (harvested, no recorded run)
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/nms.py
code served (permissive licence) · get_code("d65ff3a37c542e41")
How it ran

no invocation recorded.

polygons_to_label Not yet run
unverified (harvested, no recorded run)
uhlmanngroup/splinedist/splinedist/geometry/geom2d.py
code served (permissive licence) · get_code("01af078012c49fdf")
How it ran

no invocation recorded.

polygons_to_label_coord Not yet run
unverified (harvested, no recorded run)
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/geometry/geom2d.py
code served (permissive licence) · get_code("4cba6d519a0927db")
How it ran

no invocation recorded.

rays_from_json Not yet run
unverified (harvested, no recorded run)
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/rays3d.py
code served (permissive licence) · get_code("f7197778e73bf45b")
How it ran

no invocation recorded.

render_polygons Not yet run
unverified (harvested, no recorded run)
uhlmanngroup/splinedist/splinedist/big.py
code served (permissive licence) · get_code("d765618fa8dd022f")
How it ran

no invocation recorded.

reorder_faces Not yet run
unverified (harvested, no recorded run)
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/rays3d.py
code served (permissive licence) · get_code("cdaf70ead486e3e7")
How it ran

no invocation recorded.

sample_patches Not yet run
unverified (harvested, no recorded run)
hthierno/pytorch-stardist/stardist_tools_/stardist_tools/sample_patches.py
code served (permissive licence) · get_code("e8d6bfb5ef31c7c4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 33 samples lifted from this paper's linked repositories, 33 carry a function identity and 0 do not. Of the 31 distinct functions with an identity, 13 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 13 later) and 18 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
dist_to_coord 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
draw_polygons 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
edt_prob 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
is_array_of_integers 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
label_are_sequential 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
non_maximum_suppression 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
non_maximum_suppression_inds 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
non_maximum_suppression_sparse 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
path_absolute 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
polygons_to_label_coord 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
random_label_cmap 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
rays_from_json 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist
reorder_faces 1 other paper
1 later
2203.02284 (2022-03)
Nuclei instance segmentation and classification in histopathology images with StarDist

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

Automatic detection and segmentation of cells and nuclei in microscopy images is important for many biological applications. Recent successful learning-based approaches include per-pixel cell segmentation with subsequent pixel grouping, or localization of bounding boxes with subsequent shape refinement. In situations of crowded cells, these can be prone to segmentation errors, such as falsely merging bordering cells or suppressing valid cell instances due to the poor approximation with bounding boxes. To overcome these issues, we propose to localize cell nuclei via star-convex polygons, which are a much better shape representation as compared to bounding boxes and thus do not need shape refinement. To that end, we train a convolutional neural network that predicts for every pixel a polygon for the cell instance at that position. We demonstrate the merits of our approach on two synthetic datasets and one challenging dataset of diverse fluorescence microscopy images.

For agents

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

get_harvested_code_for_paper("1806.03535")
get_code_for_paper("1806.03535")
have("1806.03535")

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

curl https://syntology.ai/api/ran/1806.03535.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.03535.svg)](https://syntology.ai/paper/1806.03535)

Connect an agent — have() is free.