SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.11275 · 2020

Center-based 3D Object Detection and Tracking

arXiv · PDF · Open in the Atlas

Code that ran

19 of 22 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; 2 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 9 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/2006.11275.json · badge: /api/ran/2006.11275.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
tianweiy/CenterPoint-KITTI community (classifier label)
classifier basis not recorded on the link
10 ran · 3 no recorded run
zion-king/Center-based-3D-Object-Detection-and-Tracking community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
livox-sdk/livox_detection extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
cfg_from_yaml_file Ran
ran; our contract draft was wrong, not the code
tianweiy/CenterPoint-KITTI/pcdet/config.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from mickeykang16/Ev-Stereo3D, is pointer only (licence: NONE) · get_code("696fe155f9990d38")
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 mickeykang16/Ev-Stereo3D, 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.

check_numpy_to_torch Ran
ran; our contract draft was wrong, not the code
livox-sdk/livox_detection/tools/test_ros.py
code served (permissive licence) · get_code("5c4bac81583c34e1")
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 torch

torch.manual_seed(0)

# The function check_numpy_to_torch takes a single parameter 'x'
# It checks if x is a numpy array, and if so converts it to a torch tensor
# We need to test this with both a numpy array and a non-numpy array

# Create a small numpy array
numpy_array = np.array([[1.0, 2.0, 3.0, 4.0],
                        [5.0, 6.0, 7.0, 8.0]], dtype=np.float32)

ARGS = {
    "x": numpy_array
}
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 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
clip_sigmoid Ran
ran on a synthesized input
tianweiy/CenterPoint-KITTI/pcdet/models/dense_heads/centerpoint_head_single.py
code served (permissive licence) · get_code("2910537cc2d708f3")
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 4, dtype family float, shape (2, 4, 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 a small input tensor with shape [B, N, H, W]
# B=2 (batch), N=4 (channels), H=3 (height), W=5 (width)
x = torch.randn(2, 4, 3, 5)

# eps parameter - lower bound for clamping
eps = 0.0001

ARGS = {
    "x": x,
    "eps": eps,
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 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
cls_type_to_id Ran
ran, honoured the contract we drafted
tianweiy/CenterPoint-KITTI/pcdet/utils/object3d_kitti.py
code served (permissive licence) · get_code("68d59bd1b88d6e20")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    'cls_type': 'Car'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
div_up Ran
ran, honoured the contract we drafted
tianweiy/CenterPoint-KITTI/pcdet/datasets/kitti/kitti_object_eval_python/rotate_iou.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from datongjie/bevspread, is pointer only (licence: NONE) · get_code("20fbfa2279e1ce4b")
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 datongjie/bevspread, 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.

flip Ran
ran on a synthesized input
zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/core/utils/center_utils.py
code served (permissive licence) · get_code("71c86b456fb1f8d8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (2, 3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function flip takes an img parameter and performs numpy-style slicing
# on the last dimension (reverses it) and makes a copy.
# This suggests img should be a numpy array with at least 3 dimensions.

# Create a small test image: shape (2, 3, 4) for batch_size=2, height=3, width=4
img = np.random.randint(0, 256, size=(2, 3, 4), dtype=np.uint8)

ARGS = {
    "img": img
}
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 int, shape (2, 3, 4) — shape (2, 3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gaussian_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tianweiy/CenterPoint-KITTI/pcdet/models/dense_heads/centerpoint_head_single.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yifanlu0227/HEAL, is pointer only (licence: NOASSERTION) · get_code("ea036153b550642a")
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 yifanlu0227/HEAL, 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_affine_transform Ran
ran on a synthesized input
zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/core/utils/center_utils.py
code served (permissive licence) · get_code("da4199bc7189c53d")
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 (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import cv2

# Set up arguments for get_affine_transform
ARGS = {
    'center': np.array([256.0, 256.0], dtype=np.float32),
    'scale': np.array([200.0, 200.0], dtype=np.float32),
    'rot': 0.0,
    'output_size': (512, 512),
    'shift': np.array([0.0, 0.0], dtype=np.float32),
    'inv': 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_calib_from_file Ran
ran on a synthesized input
tianweiy/CenterPoint-KITTI/pcdet/utils/calibration_kitti.py
code served (permissive licence) · get_code("ebd8a3fc2a270133")
How it ran

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

import tempfile
import os

# Create a temporary calibration file with the expected format
temp_dir = tempfile.mkdtemp()
calib_file = os.path.join(temp_dir, "calib.txt")

with open(calib_file, 'w') as f:
    # Lines 0-1: dummy content
    f.write("P0: dummy\n")
    f.write("P1: dummy\n")
    # Line 2: P2 (3x4 = 12 values)
    f.write("P2: " + " ".join([str(i) for i in range(12)]) + "\n")
    # Line 3: P3 (3x4 = 12 values)
    f.write("P3: " + " ".join([str(i+12) for i in range(12)]) + "\n")
    # Line 4: R0 (3x3 = 9 values)
    f.write("R0: " + " ".join([str(i+24) for i in range(9)]) + "\n")
    # Line 5: Tr_velo_to_cam (3x4 = 12 values)
    f.write("Tr_velo_to_cam: " + " ".join([str(i+33) for i in range(12)]) + "\n")

ARGS = {
    "calib_file": calib_file
}
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 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_image_index_str Ran
ran; our contract draft was wrong, not the code
tianweiy/CenterPoint-KITTI/pcdet/datasets/kitti/kitti_object_eval_python/kitti_common.py
code served (permissive licence) · get_code("3415a0d1c950c1c7")
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

torch.manual_seed(0)

ARGS = {
    "img_idx": 42
}
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_image_path Ran
ran on a synthesized input
tianweiy/CenterPoint-KITTI/pcdet/datasets/kitti/kitti_object_eval_python/kitti_common.py
code served (permissive licence) · get_code("c8b847449b3be5dc")
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 pathlib
import tempfile
import os

# Create a temporary directory structure to satisfy the file existence check
temp_dir = tempfile.mkdtemp()
training_dir = pathlib.Path(temp_dir) / 'training' / 'image_2'
training_dir.mkdir(parents=True, exist_ok=True)

# Create a dummy image file
dummy_image = training_dir / '000000.png'
dummy_image.touch()

# Define arguments for get_image_path
ARGS = {
    'idx': 0,
    'prefix': temp_dir,
    'training': True,
    'relative_path': True
}
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
get_objects_from_label Ran
ran; our contract draft was wrong, not the code
tianweiy/CenterPoint-KITTI/pcdet/utils/object3d_kitti.py
code served (permissive licence) · get_code("4ebc0d049adc6eac")
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
import os

# Create a temporary label file with valid KITTI format data
temp_dir = tempfile.mkdtemp()
label_file = os.path.join(temp_dir, "test_label.txt")

# Write sample KITTI format lines to the temporary file
# Format: type truncation occlusion alpha bbox_left bbox_top bbox_right bbox_bottom height width length loc_x loc_y loc_z rotation_y [score]
sample_lines = [
    "Car 0.00 0 -0.20 100.0 50.0 200.0 150.0 1.57 1.89 4.63 5.0 10.0 20.0 -1.57",
    "Pedestrian 0.15 1 0.50 120.0 60.0 160.0 180.0 1.73 0.58 0.61 2.5 5.0 15.0 0.87 0.95",
    "Cyclist 0.30 2 -0.80 90.0 40.0 180.0 160.0 1.65 0.62 1.87 1.0 8.0 25.0 1.23",
]

with open(label_file, 'w') as f:
    for line in sample_lines:
        f.write(line + '\n')

ARGS = {
    'label_file': label_file,
}
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 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
inverse_sigma Ran
ran on a synthesized input
zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/datasets/utils/ground_plane_detection.py
code served (permissive licence) · get_code("363a2d53034b488a")
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 MatrixLike. 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 MatrixLike:
    """Stand-in class that mimics matrix behavior with copy() and transpose() methods"""
    def __init__(self, data):
        self.data = data
    
    def copy(self):
        """Return a copy of self with copied data"""
        new_obj = MatrixLike(self.data.copy())
        return new_obj
    
    def transpose(self):
        """Return transposed version"""
        transposed = MatrixLike(self.data.T)
        return transposed
    
    def __getitem__(self, key):
        return self.data[key]
    
    def __setitem__(self, key, value):
        self.data[key] = value
    
    @property
    def shape(self):
        return self.data.shape

# Create a small matrix for testing
# Use a 4x3 matrix to have distinct dimensions
matrix_data = np.array([
    [2.0, 0.5, 0.1],
    [0.0, 4.0, 0.2],
    [0.0, 0.0, 0.5],
    [0.1, 0.2, 0.3]
], dtype=np.float32)

S = MatrixLike(matrix_data)

ARGS = {
    "S": S
}
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 MatrixLike — a MatrixLike output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MatrixLike 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
mask_points_out_of_range Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
livox-sdk/livox_detection/tools/test_ros.py
code served (permissive licence) · get_code("b17bee95672f577a")
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 (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a point cloud with some points in and out of range
# Shape: (N, 3) where N is number of points
pc = np.array([
    [0.5, 0.5, 0.5],      # inside range
    [1.5, 1.5, 1.5],      # inside range
    [-5.0, -5.0, -5.0],   # outside range (negative)
    [10.0, 10.0, 10.0],   # outside range (too large)
], dtype=np.float32)

# Define a point cloud range [x_min, y_min, z_min, x_max, y_max, z_max]
pc_range = [0.0, 0.0, 0.0, 2.0, 2.0, 2.0]

ARGS = {
    "pc": pc,
    "pc_range": pc_range,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
merge_new_config Ran
ran; our contract draft was wrong, not the code
tianweiy/CenterPoint-KITTI/pcdet/config.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from mickeykang16/Ev-Stereo3D, is pointer only (licence: NONE) · get_code("392c0cf3a1b07b12")
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 mickeykang16/Ev-Stereo3D, 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.

rotate_points_along_z Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
livox-sdk/livox_detection/tools/test_ros.py
code served (permissive licence) · get_code("df17a2b345c6cccd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 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 numpy as np

torch.manual_seed(0)

# Create sample points: (B=2, N=4, 3+C where C=1)
# Shape: (batch_size, num_points, features)
points = torch.randn(2, 4, 4)

# Create sample angles: (B=2,)
angle = torch.randn(2)

ARGS = {
    "points": points,
    "angle": angle
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 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
svd Ran
ran on a synthesized input
zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/datasets/utils/ground_plane_detection.py
code served (permissive licence) · get_code("0215535ccf00014e")
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

# The function svd(A) takes a matrix A and computes its SVD decomposition
# It uses numpy.linalg.svd and constructs a diagonal matrix S with the singular values
# A should be a numpy array with shape (m, n) where m and n are different for clarity

# Create a small test matrix with distinct dimensions
A = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0],
    [7.0, 8.0, 9.0],
    [10.0, 11.0, 12.0]
], dtype=np.float64)

ARGS = {
    "A": A
}
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 — 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
svd_solve Ran
ran on a synthesized input
zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/datasets/utils/ground_plane_detection.py
code served (permissive licence) · get_code("d9f32b1e24612346")
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 numpy as np

# Create a simple system: A @ x = b
# Using a 4x3 matrix A and a 4-element vector b
# This creates an overdetermined system (more equations than unknowns)

np.random.seed(0)

# Create A as a 4x3 matrix
A = np.random.randn(4, 3).astype(np.float64)

# Create b as a 4-element vector
b = np.random.randn(4).astype(np.float64)

ARGS = {
    'A': A,
    'b': b
}
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
transform_preds Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/core/utils/center_utils.py
code served (permissive licence) · get_code("fcb93febe125336c")
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 (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import cv2

# Define the helper functions needed by transform_preds
def get_dir(src_point, rot_rad):
    sn, cs = (np.sin(rot_rad), np.cos(rot_rad))
    src_result = [0, 0]
    src_result[0] = src_point[0] * cs - src_point[1] * sn
    src_result[1] = src_point[0] * sn + src_point[1] * cs
    return src_result

def get_3rd_point(a, b):
    direct = a - b
    return b + np.array([-direct[1], direct[0]], dtype=np.float32)

def affine_transform(pt, t):
    new_pt = np.array([pt[0], pt[1], 1.0], dtype=np.float32).T
    new_pt = np.dot(t, new_pt)
    return new_pt[:2]

def get_affine_transform(center, scale, rot, output_size, shift=np.array([0, 0], dtype=np.float32), inv=0):
    if not isinstance(scale, np.ndarray) and (not isinstance(scale, list)):
        scale = np.array([scale, scale], dtype=np.float32)
    scale_tmp = scale
    src_w = scale_tmp[0]
    dst_w = output_size[0]
    dst_h = output_size[1]
    rot_rad = np.pi * rot / 180
    src_dir = get_dir([0, src_w * -0.5], rot_rad)
    dst_dir = np.array([0, dst_w * -0.5], np.float32)
    src = np.zeros((3, 2), dtype=np.float32)
    dst = np.zeros((3, 2), dtype=np.float32)
    src[0, :] = center + scale_tmp * shift
    src[1, :] = center + src_dir + scale_tmp * shift
    dst[0, :] = [dst_w * 0.5, dst_h * 0.5]
    dst[1, :] = np.array([dst_w * 0.5, dst_h * 0.5], np.float32) + dst_dir
    src[2:, :] = get_3rd_point(src[0, :], src[1, :])
    dst[2:, :] = get_3rd_point(dst[0, :], dst[1, :])
    if inv:
        trans = cv2.getAffineTransform(np.float32(dst), np.float32(src))
    else:
        trans = cv2.getAffineTransform(np.float32(src), np.float32(dst))
    return trans

def transform_preds(coords, center, scale, output_size):
    target_coords = np.zeros(coords.shape)
    trans = get_affine_transform(center, scale, 0, output_size, inv=1)
    for p in range(coords.shape[0]):
        target_coords[p, 0:2] = affine_transform(coords[p, 0:2], trans)
    return target_coords

# Create small valid arguments for transform_preds
coords = np.array([
    [10.5, 20.3, 0.9],
    [15.2, 25.7, 0.8]
], dtype=np.float32)

center = np.array([64.0, 64.0], dtype=np.float32)

scale = np.array([128.0, 128.0], dtype=np.float32)

output_size = (256, 256)

ARGS = {
    'coords': coords,
    'center': center,
    'scale': scale,
    'output_size': output_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 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_corner_loss_lidar Not yet run
unverified (harvested, no recorded run)
tianweiy/CenterPoint-KITTI/pcdet/utils/loss_utils.py
code served (permissive licence) · get_code("1780d388cc532a6d")
How it ran

no invocation recorded.

get_kitti_info_path Not yet run
unverified (harvested, no recorded run)
tianweiy/CenterPoint-KITTI/pcdet/datasets/kitti/kitti_object_eval_python/kitti_common.py
code served (permissive licence) · get_code("f027b5ae160547ce")
How it ran

no invocation recorded.

multi_apply Not yet run
unverified (harvested, no recorded run)
tianweiy/CenterPoint-KITTI/pcdet/models/dense_heads/centerpoint_head_single.py
code served (permissive licence) · get_code("77ab54971d45f552")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 18 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 1 the same month, 13 later) and 4 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_corner_loss_lidar 49 other papers
3 dated earlier, 46 later
1907.03670 (2019-07)
From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network
1912.13192 (2019-12)
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
2005.10821 (2020-05)
Hierarchical Multi-Scale Attention for Semantic Segmentation
and 46 more not named here
merge_new_config 15 other papers
2 dated earlier, 13 later
1912.13192 (2019-12)
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
2005.10821 (2020-05)
Hierarchical Multi-Scale Attention for Semantic Segmentation
2105.00373 (2021-05)
Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving
and 12 more not named here
cfg_from_yaml_file 13 other papers
2 dated earlier, 11 later
1912.13192 (2019-12)
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
2005.10821 (2020-05)
Hierarchical Multi-Scale Attention for Semantic Segmentation
2105.00373 (2021-05)
Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving
and 10 more not named here
multi_apply 10 other papers
2 dated earlier, 1 the same month, 7 later
1911.09070 (2019-11)
EfficientDet: Scalable and Efficient Object Detection
2003.10152 (2020-03)
SOLOv2: Dynamic and Fast Instance Segmentation
2006.05683 (2020-06)
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
and 7 more not named here
div_up 9 other papers
4 dated earlier, 5 later
1908.09492 (2019-08)
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
1911.11288 (2019-11)
Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors
and 6 more not named here
cls_type_to_id 6 other papers
6 later
2007.11901 (2020-07)
Weakly Supervised 3D Object Detection from Lidar Point Cloud
2203.11405 (2022-03)
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception
2203.15882 (2022-03)
Learning to Detect Mobile Objects from LiDAR Scans Without Labels
and 3 more not named here
gaussian_2d 6 other papers
6 later
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
2205.13542 (2022-05)
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
2303.16818 (2023-03)
SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection
and 3 more not named here
get_calib_from_file 5 other papers
1 dated earlier, 4 later
1812.04244 (2018-12)
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
2007.08856 (2020-07)
EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection
2007.11901 (2020-07)
Weakly Supervised 3D Object Detection from Lidar Point Cloud
and 2 more not named here
get_image_index_str 5 other papers
3 dated earlier, 2 later
1908.09492 (2019-08)
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
1912.13192 (2019-12)
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
and 2 more not named here
get_kitti_info_path 4 other papers
4 dated earlier
1907.06038 (2019-07)
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
1908.09492 (2019-08)
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
and 1 more not named here
transform_preds 4 other papers
1 dated earlier, 3 later
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
2007.09548 (2020-07)
Kinematic 3D Object Detection in Monocular Video
2208.00453 (2022-08)
One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement
and 1 more not named here
check_numpy_to_torch 3 other papers
3 later
2203.13394 (2022-03)
Point2Seq: Detecting 3D Objects as Sequences
2303.15286 (2023-03)
Unsupervised Adaptation from Repeated Traversals for Autonomous Driving
2412.01812 (2024-12)
V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction
get_image_path 3 other papers
3 dated earlier
1908.09492 (2019-08)
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
1912.13192 (2019-12)
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
get_objects_from_label 3 other papers
3 later
2107.13774 (2021-07)
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
2207.08531 (2022-07)
DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection
2310.07602 (2023-10)
Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autonomous Driving
inverse_sigma 1 other paper
1 dated earlier
1908.09492 (2019-08)
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
rotate_points_along_z 1 other paper
1 later
2203.13394 (2022-03)
Point2Seq: Detecting 3D Objects as Sequences
svd 1 other paper
1 dated earlier
1908.09492 (2019-08)
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
svd_solve 1 other paper
1 dated earlier
1908.09492 (2019-08)
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

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

Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional challenges. Objects in a 3D world do not follow any particular orientation, and box-based detectors have difficulties enumerating all orientations or fitting an axis-aligned bounding box to rotated objects. In this paper, we instead propose to represent, detect, and track 3D objects as points. Our framework, CenterPoint, first detects centers of objects using a keypoint detector and regresses to other attributes, including 3D size, 3D orientation, and velocity. In a second stage, it refines these estimates using additional point features on the object. In CenterPoint, 3D object tracking simplifies to greedy closest-point matching. The resulting detection and tracking algorithm is simple, efficient, and effective. CenterPoint achieved state-of-the-art performance on the nuScenes benchmark for both 3D detection and tracking, with 65.5 NDS and 63.8 AMOTA for a single model. On the Waymo Open Dataset, CenterPoint outperforms all previous single model method by a large margin and ranks first among all Lidar-only submissions. The code and pretrained models are available at https://github.com/tianweiy/CenterPoint.

For agents

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

get_harvested_code_for_paper("2006.11275")
get_code_for_paper("2006.11275")
have("2006.11275")

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

curl https://syntology.ai/api/ran/2006.11275.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.11275.svg)](https://syntology.ai/paper/2006.11275)

Connect an agent — have() is free.