SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.12716 · 2022

You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration

arXiv · PDF · Open in the Atlas

Code that ran

18 of 30 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 13 have no contract verdict; 4 failures of our instrument; 12 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2201.12716.json · badge: /api/ran/2201.12716.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
wenbowen123/BundleTrack canonical (classifier label)
classifier basis not recorded on the link
10 ran · 11 no recorded run
wenbowen123/catgrasp canonical (classifier label)
classifier basis not recorded on the link
8 ran · 1 no recorded run
FunctionStatusWhere it lives
index_points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wenbowen123/catgrasp/pointnet2.py
code served (permissive licence) · get_code("449a0265144f6530")
How it ran

Ran in Syntology's jail 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 (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:32:40Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# points: [B, N, C] where B=2 (batch), N=5 (num points), C=3 (channels)
points = torch.randn(2, 5, 3)

# idx: [B, S] where B=2 (batch), S=4 (num samples to index)
# Values should be valid indices into the N=5 dimension
idx = torch.tensor([[0, 2, 1, 4], [3, 1, 0, 2]], dtype=torch.long)

ARGS = {
    "points": points,
    "idx": idx,
}
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 (2, 4, 3) — shape (2, 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
add_argument_group Ran
ran; our contract draft was wrong, not the code
wenbowen123/BundleTrack/lf-net-release/common/argparse_utils.py
code served (permissive licence) · get_code("7ac251a2c9e673b8")
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 _ArgumentGroup. 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 argparse

torch_manual_seed_0 = __import__('torch').manual_seed(0)

parser = argparse.ArgumentParser()

ARGS = {
    "name": "test_group",
    "parser": parser
}
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 _ArgumentGroup — a _ArgumentGroup output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a _ArgumentGroup 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
compute_various_matching_score Ran
ran on a synthesized input
wenbowen123/BundleTrack/lf-net-release/eval_tools.py
code served (permissive licence) · get_code("f601ec8d7f89dca6")
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 numpy as np

# Create small test data
match_dist_all = np.array([0.5, 1.2, 0.8, 1.5, 0.3, 2.0])
kpvis2w = np.array([1.0, 1.0, 1.0, 0.0, 1.0, 1.0])
dist_thresh_list = [0.5, 1.0, 1.5, 2.0]

ARGS = {
    "match_dist_all": match_dist_all,
    "kpvis2w": kpvis2w,
    "dist_thresh_list": dist_thresh_list,
}
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
embed_breakpoint Ran
ran on a synthesized input
wenbowen123/BundleTrack/lf-net-release/utils.py
code served (permissive licence) · get_code("85ec3ec62fad094b")
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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'terminate': True
}
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 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
end_of_frame_masks Ran
ran on a synthesized input
wenbowen123/BundleTrack/lf-net-release/det_tools.py
code served (permissive licence) · get_code("811792227fa22c6f")
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 EagerTensor, ndim 4, dtype family float, shape (1, 10, 12, 1) 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 tensorflow as tf

ARGS = {
    "height": 10,
    "width": 12,
    "radius": 2,
    "dtype": tf.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (1, 10, 12, 1) — shape (1, 10, 12, 1) 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
estimate9DTransform Ran
ran on a synthesized input
wenbowen123/catgrasp/aligning.py
code served (permissive licence) · get_code("5adb1a0d38ff692f")
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 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
import cv2
from scipy.spatial import cKDTree

# Define a minimal stand-in for Open3D Point Cloud
class MockPointCloud:
    def __init__(self, points):
        self.points = points
    
    def voxel_down_sample(self, voxel_size):
        # Simple mock: just return self
        return self

def toOpen3dCloud(points):
    return MockPointCloud(points)

def to_homo(points):
    """Convert points to homogeneous coordinates"""
    ones = np.ones((points.shape[0], 1))
    return np.hstack([points, ones])

# Create small sample point clouds
np.random.seed(0)

# Source and target point clouds: 8 points in 3D
source = np.random.randn(8, 3).astype(np.float32)
target = np.random.randn(8, 3).astype(np.float32)

# Parameters
PassThreshold = 0.5
max_iter = 10  # Small number for quick execution
use_kdtree_for_eval = False
kdtree_eval_resolution = None
max_scale = np.array([99, 99, 99])
min_scale = np.array([0, 0, 0])
max_dimensions = None

ARGS = {
    "source": source,
    "target": target,
    "PassThreshold": PassThreshold,
    "max_iter": max_iter,
    "use_kdtree_for_eval": use_kdtree_for_eval,
    "kdtree_eval_resolution": kdtree_eval_resolution,
    "max_scale": max_scale,
    "min_scale": min_scale,
    "max_dimensions": max_dimensions,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, scipy, yaml — 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 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
estimate9DTransform_worker Ran
ran on a synthesized input
wenbowen123/catgrasp/aligning.py
code served (permissive licence) · get_code("774f4166271138ad")
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 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
import cv2
from scipy.spatial import cKDTree

def to_homo(points):
    """Convert points to homogeneous coordinates"""
    ones = np.ones((points.shape[0], 1))
    return np.hstack([points, ones])

def toOpen3dCloud(points):
    """Create a minimal Open3D-like point cloud object"""
    class SimpleCloud:
        def __init__(self, pts):
            self.points = pts
        
        def voxel_down_sample(self, voxel_size):
            # Simple downsampling: keep every nth point
            stride = max(1, int(1.0 / voxel_size)) if voxel_size > 0 else 1
            downsampled = self.points[::stride]
            new_cloud = SimpleCloud(downsampled)
            return new_cloud
    
    return SimpleCloud(points)

# Create small test data
np.random.seed(0)

# Source and target point clouds (N, 3)
N = 10
source = np.random.randn(N, 3).astype(np.float32)
target = np.random.randn(N, 3).astype(np.float32)

# Subsets for RANSAC
cur_src = source[:4].copy()
cur_dst = target[:4].copy()

# Pass threshold for inlier detection
PassThreshold = 0.5

# Additional parameters
use_kdtree_for_eval = False
kdtree_eval_resolution = 0.1
max_scale = np.array([99.0, 99.0, 99.0])
min_scale = np.array([0.0, 0.0, 0.0])
max_dimensions = None

ARGS = {
    'cur_src': cur_src,
    'cur_dst': cur_dst,
    'source': source,
    'target': target,
    'PassThreshold': PassThreshold,
    'use_kdtree_for_eval': use_kdtree_for_eval,
    'kdtree_eval_resolution': kdtree_eval_resolution,
    'max_scale': max_scale,
    'min_scale': min_scale,
    'max_dimensions': max_dimensions,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, scipy, yaml — 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 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
estimateAffine3D Ran
ran on a synthesized input
wenbowen123/catgrasp/aligning.py
code served (permissive licence) · get_code("44de4d8c644ea341")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import cv2

# Create source and target point clouds
# source: (N, 3) array of 3D points
np.random.seed(0)
N = 10
source = np.random.rand(N, 3).astype(np.float32) * 10
target = np.random.rand(N, 3).astype(np.float32) * 10

# PassThreshold: RANSAC threshold for inlier detection
PassThreshold = 1.0

ARGS = {
    "source": source,
    "target": target,
    "PassThreshold": PassThreshold,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
farthest_point_sample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wenbowen123/catgrasp/pointnet2.py
code served (permissive licence) · get_code("8016bf9f4fcc1ce4")
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 2, dtype family int, shape (2, 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 torch

torch.manual_seed(0)

# Construct arguments for farthest_point_sample
# xyz: pointcloud data of shape [B, N, 3]
# npoint: number of samples to select

B = 2  # batch size
N = 4  # number of points
npoint = 2  # number of points to sample

# Create random point cloud data [B, N, 3]
xyz = torch.randn(B, N, 3)

ARGS = {
    "xyz": xyz,
    "npoint": npoint,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family int, shape (2, 2) — shape (2, 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
find_all_files Ran
ran on a synthesized input
wenbowen123/BundleTrack/lf-net-release/common/io_utils.py
code served (permissive licence) · get_code("cb7119c9b5001fc0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import imghdr

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

# Create some subdirectories and files
os.makedirs(os.path.join(temp_dir, "subdir1"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "subdir2"), exist_ok=True)

# Create some regular text files
with open(os.path.join(temp_dir, "file1.txt"), "w") as f:
    f.write("test content")

with open(os.path.join(temp_dir, "subdir1", "file2.txt"), "w") as f:
    f.write("more content")

# Create a minimal valid PNG file (smallest valid PNG)
png_data = bytes([
    0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A,  # PNG signature
    0x00, 0x00, 0x00, 0x0D, 0x49, 0x48, 0x44, 0x52,  # IHDR chunk
    0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01,  # 1x1 image
    0x08, 0x02, 0x00, 0x00, 0x00, 0x90, 0x77, 0x53,
    0xDE, 0x00, 0x00, 0x00, 0x0C, 0x49, 0x44, 0x41,
    0x54, 0x08, 0xD9, 0x63, 0xF8, 0x0F, 0x00, 0x00,
    0x01, 0x01, 0x00, 0x05, 0x1B, 0x0B, 0xB4, 0x65,
    0x00, 0x00, 0x00, 0x00, 0x49, 0x45, 0x4E, 0x44,
    0xAE, 0x42, 0x60, 0x82
])

with open(os.path.join(temp_dir, "subdir2", "image.png"), "wb") as f:
    f.write(png_data)

with open(os.path.join(temp_dir, "subdir2", "document.pdf"), "w") as f:
    f.write("fake pdf")

ARGS = {
    "path": temp_dir,
    "only_img": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_class_name Ran
ran on a synthesized input
wenbowen123/catgrasp/Utils.py
code served (permissive licence) · get_code("edcd07ad5580f332")
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 torch

ARGS = {
    'ob_dir': '/nut/object_001'
}
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 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
get_config Ran
ran on a synthesized input
wenbowen123/BundleTrack/lf-net-release/common/argparse_utils.py
code served (permissive licence) · get_code("3c9b628b6015e189")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import argparse
import torch

torch.manual_seed(0)

# Create a minimal argument parser
parser = argparse.ArgumentParser(description='Test parser')
parser.add_argument('--learning_rate', type=float, default=0.001)
parser.add_argument('--batch_size', type=int, default=32)
parser.add_argument('--epochs', type=int, default=10)
parser.add_argument('--model_name', type=str, default='test_model')

ARGS = {
    'parser': parser
}
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 tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_degree_maps Ran
ran on a synthesized input
wenbowen123/BundleTrack/lf-net-release/det_tools.py
code served (permissive licence) · get_code("3b2817c96bd3ce01")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import tensorflow as tf

def get_angle_colorbar():
    hue = np.arange(360)[:, None, None].astype(np.float32)
    ones = np.ones_like(hue)
    hsv = np.concatenate([hue, ones, ones], axis=-1)
    import cv2
    colorbar = cv2.cvtColor(hsv, cv2.COLOR_HSV2RGB)
    colorbar = np.squeeze(colorbar)
    return colorbar

# Create a small ori_maps tensor with shape [batch, height, width, 2]
# where the last dimension has [cos, sin] values
batch_size = 2
height = 4
width = 3
ori_maps = tf.constant(
    np.random.randn(batch_size, height, width, 2).astype(np.float32)
)

ARGS = {
    'ori_maps': ori_maps
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_place_success_func Ran
ran on a synthesized input
wenbowen123/catgrasp/Utils.py
code served (permissive licence) · get_code("47f97a7b46d4b164")
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 function. 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

def get_place_success_func(class_name):
    if class_name == 'nut':

        def func(ob_pose, place_pose):
            if np.linalg.norm(ob_pose[:2, 3] - place_pose[:2, 3]) > 0.005:
                print('placement check failed: center dist', np.linalg.norm(ob_pose[:2, 3] - place_pose[:2, 3]))
                return False
            if np.abs(ob_pose[2, 3] - place_pose[2, 3]) > 0.02:
                print(f'placement check failed: height wrong, ob_pose[2,3]={ob_pose[2, 3]}, place_pose[2,3]={place_pose[2, 3]}')
                return False
            return True
    elif class_name == 'hnm':

        def func(ob_pose, place_pose):
            if np.linalg.norm(ob_pose[:2, 3] - place_pose[:2, 3]) > 0.005:
                print('placement check failed: center dist', np.linalg.norm(ob_pose[:2, 3] - place_pose[:2, 3]))
                return False
            ob_dir = (ob_pose[:3, :3] @ np.array([0, 0, 1]).reshape(3, 1)).reshape(3)
            place_dir = (place_pose[:3, :3] @ np.array([0, 0, 1]).reshape(3, 1)).reshape(3)
            dot = np.dot(ob_dir, place_dir)
            if np.abs(dot) < np.cos(80 / 180.0 * np.pi):
                print('placement failed: orientation not parallel')
                return False
            return True
    elif class_name == 'screw':

        def func(ob_pose, place_pose):
            xy_dist = np.linalg.norm(ob_pose[:2, 3] - place_pose[:2, 3])
            if xy_dist >= 0.01:
                print('placement check failed: center dist', xy_dist)
                return False
            ob_dir = (ob_pose[:3, :3] @ np.array([0, 0, 1]).reshape(3, 1)).reshape(3)
            place_dir = (place_pose[:3, :3] @ np.array([0, 0, 1]).reshape(3, 1)).reshape(3)
            dot = np.dot(ob_dir, place_dir)
            if np.abs(dot) < np.cos(80 / 180.0 * np.pi):
                print('placement failed: orientation not parallel')
                return False
            return True
    return func


# Create test 4x4 pose matrices (homogeneous transformation matrices)
# Each pose is a 4x4 matrix with rotation (top-left 3x3) and translation (top-right 3x1)
ob_pose = np.array([
    [1.0, 0.0, 0.0, 0.1],
    [0.0, 1.0, 0.0, 0.2],
    [0.0, 0.0, 1.0, 0.3],
    [0.0, 0.0, 0.0, 1.0]
], dtype=np.float32)

place_pose = np.array([
    [1.0, 0.0, 0.0, 0.1],
    [0.0, 1.0, 0.0, 0.2],
    [0.0, 0.0, 1.0, 0.3],
    [0.0, 0.0, 0.0, 1.0]
], dtype=np.float32)

ARGS = {
    'class_name': 'nut'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
read_text Ran
ran on a synthesized input
wenbowen123/BundleTrack/lf-net-release/common/io_utils.py
code served (permissive licence) · get_code("e84972e37db0a57a")
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 (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 tempfile
import os
import numpy as np

# Create a temporary file with some text content
temp_dir = tempfile.mkdtemp()
temp_filename = os.path.join(temp_dir, "test.txt")

with open(temp_filename, 'w') as f:
    f.write("line one\n")
    f.write("line two\n")
    f.write("line three\n")

ARGS = {
    "filename": temp_filename
}
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 (3,) — shape (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
square_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wenbowen123/catgrasp/pointnet2.py
code served (permissive licence) · get_code("3bfe172e686075cd")
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 (2, 3, 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 torch

torch.manual_seed(0)

# Create source points: [B, N, C]
# B=2 (batch), N=3 (num source points), C=4 (coordinates)
src = torch.randn(2, 3, 4)

# Create destination points: [B, M, C]
# B=2 (batch), M=5 (num destination points), C=4 (coordinates)
dst = torch.randn(2, 5, 4)

ARGS = {
    "src": src,
    "dst": dst,
}
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 (2, 3, 5) — shape (2, 3, 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
str2bool Ran
ran, violated the contract we drafted
wenbowen123/BundleTrack/lf-net-release/common/argparse_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from haoran0301/amenunet, is pointer only (licence: NONE) · get_code("248284f69adfeaad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from haoran0301/amenunet, 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.

transformer_crop Ran
ran on a synthesized input
wenbowen123/BundleTrack/lf-net-release/spatial_transformer.py
code served (permissive licence) · get_code("7124c6a564ede370")
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 EagerTensor, ndim 4, dtype family float, shape (3, 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 tensorflow as tf
import numpy as np

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

# Create small test tensors
batch_size = 2
img_height = 8
img_width = 8
num_channels = 3
num_keypoints = 3

# images: [batch_size, height, width, channels]
images = tf.constant(
    np.random.randn(batch_size, img_height, img_width, num_channels).astype(np.float32)
)

# out_size: can be int or tuple
out_size = 4

# batch_inds: [num_keypoints] - indices into batch dimension
batch_inds = tf.constant([0, 1, 0], dtype=tf.int32)

# kpts_xy: [num_keypoints, 2] - (x, y) coordinates
kpts_xy = tf.constant(
    [[2.0, 3.0], [5.0, 4.0], [3.0, 2.0]],
    dtype=tf.float32
)

# kpts_scale: [num_keypoints] - optional scale factors
kpts_scale = tf.constant([1.0, 1.2, 0.9], dtype=tf.float32)

# kpts_ori: [num_keypoints, 2] - (cos, sin) orientation
kpts_ori = tf.constant(
    [[1.0, 0.0], [0.866, 0.5], [0.707, 0.707]],
    dtype=tf.float32
)

# thetas: optional transformation matrices, leave as None to let function compute
thetas = None

ARGS = {
    'images': images,
    'out_size': out_size,
    'batch_inds': batch_inds,
    'kpts_xy': kpts_xy,
    'kpts_scale': kpts_scale,
    'kpts_ori': kpts_ori,
    'thetas': thetas,
    'name': 'SpatialTransformCropper'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (3, 4, 4, 3) — shape (3, 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
apply_scale_on_intrinsic Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/train_lfnet.py
code served (permissive licence) · get_code("66ca18d25d909631")
How it ran

no invocation recorded.

build_deep_detector Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/inference.py
code served (permissive licence) · get_code("9bb1eda061ea6175")
How it ran

no invocation recorded.

build_detector_helper Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/run_lfnet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from vcg-uvic/lf-net-release, is pointer only (licence: NOASSERTION) · get_code("f4bcd058b9843722")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from vcg-uvic/lf-net-release, 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. No invocation recorded.

build_networks Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/run_lfnet.py
code served (permissive licence) · get_code("8cb4e5eb0308baae")
How it ran

no invocation recorded.

compute_matching_score_numpy Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/eval_tools.py
code served (permissive licence) · get_code("c07599f3dffba3e5")
How it ran

no invocation recorded.

compute_sift Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/eval_tools.py
code served (permissive licence) · get_code("c53b75c25e8cdbef")
How it ran

no invocation recorded.

get_symmetry_tfs Not yet run
unverified (harvested, no recorded run)
wenbowen123/catgrasp/Utils.py
code served (permissive licence) · get_code("42549259b0657b13")
How it ran

no invocation recorded.

inplane_coordinate_warp Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/spatial_transformer.py
code served (permissive licence) · get_code("22d184419399f006")
How it ran

no invocation recorded.

inplane_inverse_warp Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/spatial_transformer.py
code served (permissive licence) · get_code("db44c54af29bb3cd")
How it ran

no invocation recorded.

inverse_warp_view_2_to_1 Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/det_tools.py
code served (permissive licence) · get_code("a13e6c8cc66e5727")
How it ran

no invocation recorded.

load_pickle Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/common/io_utils.py
code served (permissive licence) · get_code("4db2549fc621ca1f")
How it ran

no invocation recorded.

save_as_gif Not yet run
unverified (harvested, no recorded run)
wenbowen123/BundleTrack/lf-net-release/common/jupyter_utils.py
code served (permissive licence) · get_code("594fb6efc68d762e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 30 samples lifted from this paper's linked repositories, 30 carry a function identity and 0 do not. Of the 30 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 4 later) and 24 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
square_distance 75 other papers
10 dated earlier, 1 the same month, 63 later, 1 same year, order not determinable · 9 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.00410 (2020-03)
PF-Net: Point Fractal Network for 3D Point Cloud Completion
and 72 more not named here
index_points 42 other papers
7 dated earlier, 1 the same month, 34 later · 6 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.13479 (2020-03)
RPM-Net: Robust Point Matching using Learned Features
and 39 more not named here
str2bool 33 other papers
21 dated earlier, 11 later, 1 same year, order not determinable
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1506.03134 (2015-06)
Pointer Networks
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
and 30 more not named here
farthest_point_sample 9 other papers
4 dated earlier, 5 later · 4 only as an assembly brick
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2004.10904 (2020-04)
Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes
and 6 more not named here
add_argument_group 1 other paper
1 dated earlier
2008.05049 (2020-08)
Distantly Supervised Relation Extraction in Federated Settings
build_detector_helper 1 other paper
1 dated earlier
1805.09662 (2018-05)
LF-Net: Learning Local Features from Images

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

Promising results have been achieved recently in category-level manipulation that generalizes across object instances. Nevertheless, it often requires expensive real-world data collection and manual specification of semantic keypoints for each object category and task. Additionally, coarse keypoint predictions and ignoring intermediate action sequences hinder adoption in complex manipulation tasks beyond pick-and-place. This work proposes a novel, category-level manipulation framework that leverages an object-centric, category-level representation and model-free 6 DoF motion tracking. The canonical object representation is learned solely in simulation and then used to parse a category-level, task trajectory from a single demonstration video. The demonstration is reprojected to a target trajectory tailored to a novel object via the canonical representation. During execution, the manipulation horizon is decomposed into longrange, collision-free motion and last-inch manipulation. For the latter part, a category-level behavior cloning (CatBC) method leverages motion tracking to perform closed-loop control. CatBC follows the target trajectory, projected from the demonstration and anchored to a dynamically selected category-level coordinate frame. The frame is automatically selected along the manipulation horizon by a local attention mechanism. This framework allows to teach different manipulation strategies by solely providing a single demonstration, without complicated manual programming. Extensive experiments demonstrate its efficacy in a range of challenging industrial tasks in highprecision assembly, which involve learning complex, long-horizon policies. The process exhibits robustness against uncertainty due to dynamics as well as generalization across object instances and scene configurations. The supplementary video is available at https://www.youtube.com/watch?v=WAr8ZY3mYyw

For agents

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

get_harvested_code_for_paper("2201.12716")
get_code_for_paper("2201.12716")
have("2201.12716")

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

curl https://syntology.ai/api/ran/2201.12716.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.12716.svg)](https://syntology.ai/paper/2201.12716)

Connect an agent — have() is free.