SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.02643 · ICCV · 2023

Segment Anything

Tete Xiao, Eric Mintun, Piotr Dollár, Ross Girshick, Alexander Kirillov, Hanzi Mao, Nikhila Ravi, Chloe Rolland, Laura Gustafson, Spencer Whitehead, Alexander Berg, Wan-Yen Lo

arXiv · PDF · Open in the Atlas

Code that ran

20 of 23 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 2 violated it and 11 have no contract verdict; 6 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2304.02643.json · badge: /api/ran/2304.02643.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
facebookresearch/segment-anything canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
HibaKob/MicroBundlePillarTrack community (classifier label)
classifier basis not recorded on the link
10 ran · 2 no recorded run
computational-cell-analytics/medico-sam community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
IDEA-Research/Grounded-Segment-Anything extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
harrytea/detect-anyshadow extension (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_otsu_thresh Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/src/microbundlepillartrack/pillar_analysis.py
code served (permissive licence) · get_code("8d9679be271d4b38")
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 (8, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from skimage.filters import threshold_otsu

# Create a small sample image array for testing
# Using a simple 2D grayscale image with values that will have a clear threshold
np.random.seed(0)
sample_image = np.random.randint(0, 256, size=(8, 6), dtype=np.uint8)

# Ensure we have a bimodal distribution for a clearer threshold
sample_image[:4, :] = np.random.randint(0, 100, size=(4, 6), dtype=np.uint8)
sample_image[4:, :] = np.random.randint(150, 256, size=(4, 6), dtype=np.uint8)

ARGS = {
    "array": sample_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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 2, dtype family float, shape (8, 6) — shape (8, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
calculate_dice_score Ran
ran on a synthesized input
computational-cell-analytics/medico-sam/medico_sam/evaluation/evaluation.py
code served (permissive licence) · get_code("a4a2d81002368f50")
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 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create small binary tensors for dice score calculation
# input_ and target should be binary predictions and ground truth
input_ = torch.tensor([[1.0, 0.0, 1.0, 0.0],
                       [1.0, 1.0, 0.0, 1.0]], dtype=torch.float32)

target = torch.tensor([[1.0, 0.0, 1.0, 1.0],
                       [1.0, 1.0, 0.0, 0.0]], dtype=torch.float32)

eps = 1e-07

ARGS = {
    "input_": input_,
    "target": target,
    "eps": eps
}
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 Tensor, 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
check_frame_low_contrast Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/src/microbundlepillartrack/create_pillar_mask.py
code served (permissive licence) · get_code("45dc7a1f3636a6c8")
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
from skimage import morphology, exposure

# Create a small test image with low contrast
# Using a small image with uniform-ish values to ensure low contrast
low_contrast_img = np.ones((4, 3), dtype=np.uint8) * 128 + np.random.randint(-5, 5, (4, 3))

ARGS = {
    "img": low_contrast_img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — 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_otsu_thresh Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/src/microbundlepillartrack/pillar_analysis.py
code served (permissive licence) · get_code("1fda4dacb4806edc")
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 int64, 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
from skimage.filters import threshold_otsu

# Create a small test image array
# Using a simple 2D grayscale image with values in typical image range
image_array = np.array([
    [50, 100, 150, 200],
    [60, 110, 160, 210],
    [70, 120, 170, 220]
], dtype=np.uint8)

ARGS = {
    "array": image_array
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int64, 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_amg_kwargs Ran
ran; our contract draft was wrong, not the code
facebookresearch/segment-anything/scripts/amg.py
code served (permissive licence) · get_code("a8051baeec435042")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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)

class Args:
    def __init__(self):
        self.points_per_side = 32
        self.points_per_batch = 64
        self.pred_iou_thresh = 0.88
        self.stability_score_thresh = 0.95
        self.stability_score_offset = 1.0
        self.box_nms_thresh = 0.7
        self.crop_n_layers = 0
        self.crop_nms_thresh = 0.7
        self.crop_overlap_ratio = 512 / 1500
        self.crop_n_points_downscale_factor = 1
        self.min_mask_region_area = 0

args = Args()

ARGS = {'args': args}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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
get_rel_pos Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
computational-cell-analytics/medico-sam/medico_sam/models/sam_med2d/image_encoder.py
code served (permissive licence) · get_code("733d7f0bedcb74c2")
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 Tensor, ndim 3, dtype family float, shape (3, 4, 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small relative position embedding tensor
# Shape: (L, C) where L is the sequence length and C is the channel dimension
# Using a small size that will be resized by the function
rel_pos = torch.randn(5, 4)  # 5 positions, 4 channels

# Define query and key sizes
q_size = 3
k_size = 4

ARGS = {
    "q_size": q_size,
    "k_size": k_size,
    "rel_pos": rel_pos,
}
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 Tensor, ndim 3, dtype family float, shape (3, 4, 4) — shape (3, 4, 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_training_files Ran
ran; our contract draft was wrong, not the code
harrytea/detect-anyshadow/sam_finetune.py
code served (permissive licence) · get_code("3c0c7ead4d811dd1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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 that matches what the function expects
temp_dir = tempfile.mkdtemp()

# Create the expected directory structure: path/images/video1, path/images/video2, etc.
images_dir = os.path.join(temp_dir, 'images')
os.makedirs(images_dir)

# Create a couple of video directories
video1_dir = os.path.join(images_dir, 'video1')
video2_dir = os.path.join(images_dir, 'video2')
os.makedirs(video1_dir)
os.makedirs(video2_dir)

# Create some dummy image files in each video directory
for i in range(3):
    open(os.path.join(video1_dir, f'img_{i:03d}.jpg'), 'w').close()

for i in range(2):
    open(os.path.join(video2_dir, f'img_{i:03d}.jpg'), 'w').close()

ARGS = {
    'path': temp_dir
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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
image_folder_to_path_list Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/src/microbundlepillartrack/image_analysis.py
code served (permissive licence) · get_code("c349ec599a048d0d")
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 tempfile
from pathlib import Path
import os

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

# Create some dummy .TIF files to simulate an image folder
for i in range(3):
    dummy_file = Path(temp_dir) / f"image_{i:02d}.TIF"
    dummy_file.touch()

folder_path = Path(temp_dir)

ARGS = {
    "folder_path": folder_path,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
label_regions Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/src/microbundlepillartrack/create_pillar_mask.py
code served (permissive licence) · get_code("afe29ffaba40716e")
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 numpy as np
from skimage.measure import label, regionprops

# Create a small binary image with some regions
binary_img = np.array([
    [1, 1, 0, 0],
    [1, 1, 0, 0],
    [0, 0, 1, 1],
    [0, 0, 1, 1]
], dtype=np.uint8)

ARGS = {
    "binary_img": binary_img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — 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
list_sum Ran
ran, violated the contract we drafted
IDEA-Research/Grounded-Segment-Anything/EfficientSAM/EdgeSAM/common.py
code served (permissive licence) · get_code("57deafe250be5b10")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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

torch.manual_seed(0)

# The function recursively sums elements in a list
# It needs a list with at least one element
# Elements should support the + operator

x = [1, 2, 3, 4, 5]

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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
read_all_tiff Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/src/microbundlepillartrack/image_analysis.py
code served (permissive licence) · get_code("8834474b0ab07f80")
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 3, 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 tempfile
import numpy as np
from pathlib import Path
from PIL import Image
import os

# Create temporary directory and TIFF files for testing
temp_dir = tempfile.mkdtemp()

# Create a few sample TIFF files
tiff_paths = []
for i in range(2):
    # Create a small numpy array
    img_array = np.random.randint(0, 256, size=(4, 3), dtype=np.uint8)
    
    # Convert to PIL Image and save as TIFF
    img = Image.fromarray(img_array)
    tiff_path = Path(temp_dir) / f"test_{i}.tiff"
    img.save(tiff_path)
    tiff_paths.append(tiff_path)

# Define ARGS dictionary
ARGS = {
    "path_list": tiff_paths
}
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 list, ndim 3, 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
rename_folder Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/src/microbundlepillartrack/pillar_analysis.py
code served (permissive licence) · get_code("c0246065ce1b33b4")
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 PosixPath. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os
from pathlib import Path

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

# Create a folder to rename
original_folder_name = "old_folder"
original_folder = temp_path / original_folder_name
original_folder.mkdir(exist_ok=True)

# Create a dummy file inside to make it a real folder
(original_folder / "dummy.txt").write_text("test")

ARGS = {
    "folder_path": temp_path,
    "folder_name": original_folder_name,
    "new_folder_name": "new_folder"
}
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 PosixPath — a PosixPath output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PosixPath 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
resize_expand_sequence Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/finetune_SAM/finetune_microbundle_SAM_script.py
code served (permissive licence) · get_code("d1d0fd96d4844bd5")
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 int, shape (2, 8, 8, 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 cv2

# Create a small sequence of images
# The function expects img_array to be iterable, containing image arrays
# Each image should be 2D (grayscale) since the function will expand dims to add channel
img1 = np.random.randint(0, 256, (4, 3), dtype=np.uint8)
img2 = np.random.randint(0, 256, (4, 3), dtype=np.uint8)
img_array = [img1, img2]

# Size parameter for resizing
size = 8

ARGS = {
    "img_array": img_array,
    "size": size
}
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 4, dtype family int, shape (2, 8, 8, 3) — shape (2, 8, 8, 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
resize_sequence Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/finetune_SAM/finetune_microbundle_SAM_script.py
code served (permissive licence) · get_code("45fc1f3231e37cd7")
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 int, shape (2, 4, 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
import cv2

# Create a small sequence of images
# OpenCV expects images as numpy arrays with shape (height, width) or (height, width, channels)
# Create 2 sample images of size 8x6 (height x width) with 3 channels (BGR)
img1 = np.random.randint(0, 256, (8, 6, 3), dtype=np.uint8)
img2 = np.random.randint(0, 256, (8, 6, 3), dtype=np.uint8)
img_array = np.array([img1, img2])

size = 4

ARGS = {
    'img_array': img_array,
    'size': size
}
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 4, dtype family int, shape (2, 4, 4, 3) — shape (2, 4, 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
run_example Ran
ran, violated the contract we drafted
harrytea/detect-anyshadow/demo_app.py
code served (permissive licence) · get_code("8ef94ab3cad34e94")
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 Tensor, ndim 5, dtype family float, shape (2, 3, 4, 8, 8) 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 torch.nn as nn

torch.manual_seed(0)

# The function simply returns video_input, so we need to provide a valid video input
# A video input is typically a tensor with shape (batch, channels, frames, height, width)
# or similar video format. We'll create a small tensor.

video_input = torch.randn(2, 3, 4, 8, 8)  # batch=2, channels=3, frames=4, height=8, width=8

ARGS = {
    "video_input": video_input
}
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 Tensor, ndim 5, dtype family float, shape (2, 3, 4, 8, 8) — shape (2, 3, 4, 8, 8) 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
txt_file_to_csv Ran
ran on a synthesized input
HibaKob/MicroBundlePillarTrack/tutorials/text_file_to_csv_file.py
code served (permissive licence) · get_code("bb3c76fbb6e98e5e")
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 PosixPath. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
from pathlib import Path
import numpy as np

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

# Create a sample .txt file with numeric data
file_name = "test_data"
txt_file_path = folder_path / f"{file_name}.txt"

# Create sample numeric data and save it as a text file
sample_data = np.array([[1.5, 2.3, 3.1], [4.2, 5.7, 6.9], [7.1, 8.4, 9.6]])
np.savetxt(txt_file_path, sample_data)

ARGS = {
    "folder_path": folder_path,
    "file_name": file_name,
}
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 PosixPath — a PosixPath output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PosixPath 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
val2list Ran
ran, honoured the contract we drafted
IDEA-Research/Grounded-Segment-Anything/EfficientSAM/EdgeSAM/common.py
code served (permissive licence) · get_code("f1073b4e93f4484c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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 torch
import numpy as np

torch.manual_seed(0)

# Test case 1: x is a list
x_list = [1, 2, 3]
repeat_time_1 = 1

# Test case 2: x is a tuple
x_tuple = (4, 5, 6)
repeat_time_2 = 1

# Test case 3: x is a single value (not list or tuple) with repeat_time > 1
x_single = 42
repeat_time_3 = 5

# Test case 4: x is a tensor (single value case)
x_tensor = torch.tensor([1.0, 2.0])
repeat_time_4 = 3

# We'll use test case 3 as the main example since it exercises the repeat logic
ARGS = {
    'x': x_single,
    'repeat_time': repeat_time_3
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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
val2tuple Ran
ran; our contract draft was wrong, not the code
IDEA-Research/Grounded-Segment-Anything/EfficientSAM/EdgeSAM/common.py
code served (permissive licence) · get_code("7a8e24c5db77ad97")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple, 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 torch
import numpy as np

torch.manual_seed(0)

# Test case 1: x is a single value (not list or tuple)
x_single = 5
min_len_single = 3
idx_repeat_single = -1

# Test case 2: x is a list
x_list = [1, 2]
min_len_list = 5
idx_repeat_list = -1

# Test case 3: x is a tuple
x_tuple = (10, 20, 30)
min_len_tuple = 4
idx_repeat_tuple = 1

# Test case 4: x is empty list
x_empty = []
min_len_empty = 2
idx_repeat_empty = -1

# Using test case 2 for the ARGS dict
ARGS = {
    'x': x_list,
    'min_len': min_len_list,
    'idx_repeat': idx_repeat_list
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
computational-cell-analytics/medico-sam/medico_sam/models/sam_med2d/image_encoder.py
pointer only (licence: MIT); the stored copy get_code serves, from LeapLabTHU/EchoWorld, is pointer only (licence: NONE) · get_code("105fa08885dc36cc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from LeapLabTHU/EchoWorld, and GitHub detected no licence in that repository when it was checked. 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.

window_unpartition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
computational-cell-analytics/medico-sam/medico_sam/models/sam_med2d/image_encoder.py
pointer only (licence: MIT); the stored copy get_code serves, from yatengLG/ISAT_with_segment_anything, is pointer only (licence: NOASSERTION) · get_code("27be441cc8213e52")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from yatengLG/ISAT_with_segment_anything, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

get_monai_models Not yet run
unverified (harvested, no recorded run)
computational-cell-analytics/medico-sam/medico_sam/models/monai_models.py
code served (permissive licence) · get_code("ada1ce39af7d60ef")
How it ran

no invocation recorded.

read_tiff Not yet run
unverified (harvested, no recorded run)
HibaKob/MicroBundlePillarTrack/src/microbundlepillartrack/image_analysis.py
code served (permissive licence) · get_code("2325d8c44e5d9cf8")
How it ran

no invocation recorded.

txt_results_to_mean_max_csv Not yet run
unverified (harvested, no recorded run)
HibaKob/MicroBundlePillarTrack/tutorials/output_summary_reults_csv.py
code served (permissive licence) · get_code("df2f44871adc6846")
How it ran

no invocation recorded.

Also present in other papers' code

Of 23 samples lifted from this paper's linked repositories, 23 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 7 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 3 the same month, 7 later) and 16 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
get_rel_pos 47 other papers
3 the same month, 44 later · 5 only as an assembly brick
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
2304.13785 (2023-04)
Customized Segment Anything Model for Medical Image Segmentation
and 44 more not named here
window_partition 47 other papers
3 the same month, 44 later · 1 only as an assembly brick
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
2304.13785 (2023-04)
Customized Segment Anything Model for Medical Image Segmentation
and 44 more not named here
window_unpartition 46 other papers
3 the same month, 43 later · 1 only as an assembly brick
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
2304.13785 (2023-04)
Customized Segment Anything Model for Medical Image Segmentation
and 43 more not named here
get_amg_kwargs 2 other papers
2 later
2404.08255 (2024-04)
Practical Region-level Attack against Segment Anything Models
2408.09110 (2024-08)
Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community
val2list 2 other papers
2 later
2409.03460 (2024-09)
LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones
2506.00045 (2025-06)
ACE-Step: A Step Towards Music Generation Foundation Model
val2tuple 2 other papers
2 later
2409.03460 (2024-09)
LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones
2506.00045 (2025-06)
ACE-Step: A Step Towards Music Generation Foundation Model
list_sum 1 other paper
1 later
2410.10812 (2024-10)
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

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

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Meta AI Research, FAIR (b) Model: Segment Anything Model (SAM) prompt image valid mask image encoder prompt encoder lightweight mask decoder (a) Task: promptable segmentation segmentation prompt image model cat with black ears

For agents

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

get_harvested_code_for_paper("2304.02643")
get_code_for_paper("2304.02643")
have("2304.02643")

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

curl https://syntology.ai/api/ran/2304.02643.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.02643.svg)](https://syntology.ai/paper/2304.02643)

Connect an agent — have() is free.