SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.06292 · 2019

3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions

arXiv · PDF · Open in the Atlas

Code that ran

18 of 25 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 12 have no contract verdict; 4 failures of our instrument; 7 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1905.06292.json · badge: /api/ran/1905.06292.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
EricDai0/AdvGCGAN community (classifier label)
classifier basis not recorded on the link
9 ran · 3 no recorded run
prajwalsingh/TreeGCN-ED community (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
prajwalsingh/TreeGCN-GAN community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
SOR Ran
ran on a synthesized input
EricDai0/AdvGCGAN/defense.py
code served (permissive licence) · get_code("41e39b6bcd645cfb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family float, shape (2, 5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small point cloud batch for testing
# Shape: (batch_size, num_points, num_features)
# batch_size=2, num_points=5, num_features=3
np.random.seed(0)
points = np.random.randn(2, 5, 3).astype(np.float64)

ARGS = {
    "points": points,
    "alpha": 1.1,
    "k": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 5, 3) — shape (2, 5, 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
SRS Ran
ran on a synthesized input
EricDai0/AdvGCGAN/defense.py
code served (permissive licence) · get_code("5cfb3f364d06cb8b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family float, shape (2, 5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

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

# Create a small sample points array with shape (batch_size, num_points, features)
# Using distinct dimensions: 2 for batch, 5 for points, 3 for features
points = np.random.randn(2, 5, 3).astype(np.float32)

# Define the percentage parameter
percentage = 0.2

ARGS = {
    'points': points,
    'percentage': percentage
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 5, 3) — shape (2, 5, 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
aug_pc Ran
ran on a synthesized input
prajwalsingh/TreeGCN-ED/utils.py
code served (permissive licence) · get_code("bf160a07c8a8b8bd")
How it ran

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

import numpy as np
import math
import random

# Set seed for reproducibility
random.seed(42)
np.random.seed(42)

# Create a small point cloud: 4 points with 3 coordinates (x, y, z)
# Shape should be (N, 3) where N is number of points
pointcloud = np.array([
    [1.0, 0.0, 0.0],
    [0.0, 1.0, 0.0],
    [1.0, 1.0, 0.5],
    [0.5, 0.5, 1.0]
], dtype=np.float32)

ARGS = {
    "pointcloud": pointcloud
}
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 (4, 3) — shape (4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
critic_loss_gp Ran
ran on a synthesized input
prajwalsingh/TreeGCN-GAN/losses.py
code served (permissive licence) · get_code("3c2006a89e44a5f3")
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 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 tensorflow as tf
import numpy as np

# Define a minimal model with a critic method
class CriticModel(tf.Module):
    def __init__(self):
        super(CriticModel, self).__init__()
        self.dense = tf.keras.layers.Dense(1)
    
    def critic(self, x, training=False):
        # x shape: [batch_size, 1, 1] or similar
        # Flatten and pass through dense layer
        batch_size = tf.shape(x)[0]
        x_flat = tf.reshape(x, [batch_size, -1])
        output = self.dense(x_flat, training=training)
        return output

# Create sample tensors
batch_size = 2
height = 1
width = 1

# D_real: discriminator output for real data, shape [batch_size]
D_real = tf.constant([0.5, 0.6], dtype=tf.float32)

# D_fake: discriminator output for fake data, shape [batch_size]
D_fake = tf.constant([0.3, 0.4], dtype=tf.float32)

# Y: real data, shape [batch_size, height, width]
Y = tf.constant([[[1.0]], [[2.0]]], dtype=tf.float32)

# Y_cap: generated/fake data, shape [batch_size, height, width]
Y_cap = tf.constant([[[0.9]], [[1.8]]], dtype=tf.float32)

# model: instance with critic method
model = CriticModel()

ARGS = {
    "D_real": D_real,
    "D_fake": D_fake,
    "Y": Y,
    "Y_cap": Y_cap,
    "model": model,
    "batch_size": batch_size
}
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 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
distChamfer Ran
ran; our contract draft was wrong, not the code
EricDai0/AdvGCGAN/evaluation_metrics.py
pointer only (licence: MIT); the stored copy get_code serves, from duasoi/Mind2Cloud, is pointer only (licence: NONE) · get_code("9a578f2a671a37e4")
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 duasoi/Mind2Cloud, 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.

euler2quat Ran
ran, honoured the contract we drafted
EricDai0/AdvGCGAN/eulerangles.py
code served (permissive licence) · get_code("2d9e8ce18f344f58")
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 math
import numpy as np

# The function euler2quat takes three scalar parameters: z, y, x (Euler angles in radians)
# It performs mathematical operations on them and returns a quaternion array

ARGS = {
    'z': 0.5,
    'y': 0.3,
    'x': 0.2
}
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
feature_transform_regularizer Ran
ran; our contract draft was wrong, not the code
EricDai0/AdvGCGAN/models/pointnet.py
pointer only (licence: MIT); the stored copy get_code serves, from boschresearch/Open3DSG, is pointer only (licence: AGPL-3.0) · get_code("e996c64ee89d2b50")
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 boschresearch/Open3DSG, and AGPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

fetch_data Ran
ran on a synthesized input
prajwalsingh/TreeGCN-ED/utils.py
code served (permissive licence) · get_code("fa73af0144d9c1c5")
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 3, 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 torch
import math
import random

# Create a temporary in-memory numpy file that can be loaded
# We'll create a mock path object that has a .numpy() method returning bytes
class MockPath:
    def __init__(self, data):
        self.data = data
    
    def numpy(self):
        # Return the bytes representation of a saved numpy array
        import io
        buffer = io.BytesIO()
        np.save(buffer, self.data)
        return buffer.getvalue()
    
    def decode(self, encoding):
        # This won't actually be called since we're mocking,
        # but we need a way to intercept the actual load
        pass

# Create sample pointcloud data (N points, 3 coordinates)
sample_pc = np.random.randn(5, 3).astype(np.float32)

# Create a mock path that behaves like a tensor with .numpy().decode() chain
class MockTensorPath:
    def __init__(self, pc_data):
        self.pc_data = pc_data
    
    def numpy(self):
        # Return an object that has .decode() method
        import io
        buffer = io.BytesIO()
        np.save(buffer, self.pc_data)
        buffer.seek(0)
        
        class BytesWithDecode:
            def __init__(self, buf):
                self.buf = buf
            def decode(self, encoding):
                self.buf.seek(0)
                return self.buf.name if hasattr(self.buf, 'name') else ''
        
        # Actually, we need to create a temporary file path as string bytes
        import tempfile
        import os
        
        # Create temp file with the numpy array
        fd, tmp_path = tempfile.mkstemp(suffix='.npy')
        os.close(fd)
        np.save(tmp_path, self.pc_data)
        
        class PathBytes:
            def __init__(self, path):
                self.path = path
            def decode(self, encoding):
                return self.path
        
        return PathBytes(tmp_path)

sample_pointcloud = np.random.randn(5, 3).astype(np.float32)
path_arg = MockTensorPath(sample_pointcloud)

ARGS = {
    'path': path_arg
}
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, ndim 3, 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
find_triangle_area Ran
ran on a synthesized input
prajwalsingh/TreeGCN-ED/Preprocessing_Data/meshtopc.py
code served (permissive licence) · get_code("b037cba8391e5a6d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create small 3D vertex coordinate arrays
# N x 3 format: N vertices, each with 3 coordinates (x, y, z)
N = 2  # batch size

v1 = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0]
], dtype=np.float32)  # 2 x 3

v2 = np.array([
    [0.0, 0.0, 0.0],
    [1.0, 1.0, 1.0]
], dtype=np.float32)  # 2 x 3

v3 = np.array([
    [2.0, 0.0, 1.0],
    [5.0, 2.0, 3.0]
], dtype=np.float32)  # 2 x 3

ARGS = {
    "v1": v1,
    "v2": v2,
    "v3": v3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gen_loss Ran
ran on a synthesized input
prajwalsingh/TreeGCN-GAN/losses.py
code served (permissive licence) · get_code("5452ec5020495768")
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 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 tensorflow as tf
import numpy as np

# Create a small TensorFlow tensor for D_fake
# The function uses tf.reduce_mean on it, so we need a valid tensor
D_fake = tf.constant([[0.5, -0.3, 0.2, 0.1],
                       [-0.4, 0.6, -0.1, 0.8]], dtype=tf.float32)

ARGS = {
    "D_fake": D_fake
}
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 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
get_average_dis Ran
ran on a synthesized input
EricDai0/AdvGCGAN/evaluate.py
code served (permissive licence) · get_code("2a8d832a5a30956c")
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

torch.manual_seed(0)

# Create a small point cloud tensor
# Shape: [B, dims, N] where B=batch, dims=feature dimensions, N=number of points
B = 2
dims = 4
N = 5

x = torch.randn(B, dims, N)

ARGS = {
    "x": x,
    "k": 20,
    "num": -1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
get_graph_feature Ran
ran on a synthesized input
EricDai0/AdvGCGAN/models/dgcnn.py
code served (permissive licence) · get_code("d4e1cb56cdef48af")
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, 8, 3, 2) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
# Shape: (batch_size, num_dims, num_points)
# batch_size=2, num_dims=4, num_points=3
x = torch.randn(2, 4, 3)

# k parameter for nearest neighbors
k = 2

# idx parameter - set to None to let the function compute it
idx = None

ARGS = {
    "x": x,
    "k": k,
    "idx": idx,
}
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, 8, 3, 2) — shape (2, 8, 3, 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
knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
EricDai0/AdvGCGAN/models/dgcnn.py
code served (permissive licence) · get_code("cdd0141594039dcb")
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 int, shape (2, 3, 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)

# x is used with:
# - transpose(2, 1): expects 3D tensor
# - matmul with transposed version: matrix multiplication
# - sum(x ** 2, dim=1, keepdim=True): sum over dimension 1
# - topk(k=k, dim=-1): get top k indices along last dimension
# 
# Shape should be (batch, features, num_points) based on the transpose operations
# Let's use batch=2, features=4, num_points=3

x = torch.randn(2, 4, 3)

# k is the number of nearest neighbors to find
# Should be less than num_points (3), so k=2
k = 2

ARGS = {
    "x": x,
    "k": k,
}
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 int, shape (2, 3, 2) — shape (2, 3, 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
load_batch Ran
ran on a synthesized input
prajwalsingh/TreeGCN-ED/utils.py
code served (permissive licence) · get_code("7d586ed5128718bb")
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 _BatchDataset. 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 tensorflow as tf
import numpy as np

# Create a small mock dataset (list of numpy arrays or tensors)
# The function calls tf.data.Dataset.from_tensor_slices(path)
# and then .shuffle(len(path)) and .batch(batch_size, drop_remainder=True)
# So path needs to be something that can be passed to from_tensor_slices
# and has a len() method

# Create synthetic data: a list of samples
path_data = [
    np.array([1.0, 2.0, 3.0, 4.0], dtype=np.float32),
    np.array([5.0, 6.0, 7.0, 8.0], dtype=np.float32),
    np.array([9.0, 10.0, 11.0, 12.0], dtype=np.float32),
    np.array([13.0, 14.0, 15.0, 16.0], dtype=np.float32),
    np.array([17.0, 18.0, 19.0, 20.0], dtype=np.float32),
    np.array([21.0, 22.0, 23.0, 24.0], dtype=np.float32),
    np.array([25.0, 26.0, 27.0, 28.0], dtype=np.float32),
    np.array([29.0, 30.0, 31.0, 32.0], dtype=np.float32),
]

# Stack into a single array for from_tensor_slices
path = np.stack(path_data, axis=0)

ARGS = {
    "path": path,
    "batch_size": 2
}
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 _BatchDataset — a _BatchDataset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a _BatchDataset 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
mat2euler Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
EricDai0/AdvGCGAN/eulerangles.py
code served (permissive licence) · get_code("dd1f3e0945b180f2")
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 math
import numpy as np

# Create a valid 3x3 rotation matrix
# Using a simple rotation matrix for testing
M = np.array([
    [0.9363, -0.3518, 0.0000],
    [0.3518, 0.9363, 0.0000],
    [0.0000, 0.0000, 1.0000]
], dtype=np.float64)

# cy_thresh can be None (will be auto-computed) or a scalar
cy_thresh = None

ARGS = {
    "M": M,
    "cy_thresh": cy_thresh
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 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
mesh_to_pc Ran
ran on a synthesized input
prajwalsingh/TreeGCN-ED/Preprocessing_Data/meshtopc.py
code served (permissive licence) · get_code("2331393383bc00db")
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 (100, 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

np.random.seed(0)

# Create a simple mesh: a tetrahedron with 4 vertices and 4 faces
vertices = np.array([
    [0.0, 0.0, 0.0],
    [1.0, 0.0, 0.0],
    [0.5, 1.0, 0.0],
    [0.5, 0.5, 1.0]
], dtype=np.float32)

# Define 4 triangular faces using vertex indices
faces = np.array([
    [0, 1, 2],
    [0, 1, 3],
    [1, 2, 3],
    [0, 2, 3]
], dtype=np.int32)

# Number of points to sample in the point cloud
N = 100

ARGS = {
    "vertices": vertices,
    "faces": faces,
    "N": N
}
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 (100, 3) — shape (100, 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
parse_data Ran
ran on a synthesized input
prajwalsingh/TreeGCN-ED/infer_testresult.py
code served (permissive licence) · get_code("fc9e78141623c787")
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 float, 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

def parse_data(data):
    data = list(map(str.strip, data))
    data = [float(item.split(':')[1]) for item in data]
    return float(sum(data)) / float(len(data))

# Construct valid arguments for parse_data
# The function expects data to be an iterable of strings
# Each string should have format "something:number"
# It strips whitespace, splits by ':', takes the second part as float, and returns average

data_arg = [
    "  key1:42.5  ",
    "key2:10.0",
    "  key3:27.5  "
]

ARGS = {
    "data": data_arg
}
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 float, 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
pc_normalize Ran
ran, honoured the contract we drafted
prajwalsingh/TreeGCN-ED/Preprocessing_Data/mesh_to_pointcloud.py
code served (permissive licence) · get_code("870dbef57748b010")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small point cloud: N=5 points, C=3 coordinates (x, y, z)
pc = np.random.randn(5, 3).astype(np.float32)

ARGS = {
    "pc": pc
}
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 (5, 3) — shape (5, 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
chamfer_distance Not yet run
unverified (harvested, no recorded run)
prajwalsingh/TreeGCN-ED/losses.py
code served (permissive licence) · get_code("d55242abeb8deaae")
How it ran

no invocation recorded.

chamfer_loss Not yet run
unverified (harvested, no recorded run)
prajwalsingh/TreeGCN-ED/losses.py
code served (permissive licence) · get_code("0a1ea77d65404236")
How it ran

no invocation recorded.

distChamferCUDA Not yet run
unverified (harvested, no recorded run)
EricDai0/AdvGCGAN/evaluation_metrics.py
code served (permissive licence) · get_code("8f015719220a9779")
How it ran

no invocation recorded.

emd_approx Not yet run
unverified (harvested, no recorded run)
EricDai0/AdvGCGAN/evaluation_metrics.py
code served (permissive licence) · get_code("b3f758ce4a2dc4cd")
How it ran

no invocation recorded.

euler2mat Not yet run
unverified (harvested, no recorded run)
EricDai0/AdvGCGAN/eulerangles.py
code served (permissive licence) · get_code("c895ee22fc847eed")
How it ran

no invocation recorded.

fetch_data Not yet run
unverified (harvested, no recorded run)
prajwalsingh/TreeGCN-GAN/utils.py
code served (permissive licence) · get_code("03ad94b765c74aa7")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
prajwalsingh/TreeGCN-GAN/utils.py
code served (permissive licence) · get_code("7cd79aa08d856d8c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 9 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 9 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
knn 52 other papers
1 dated earlier, 51 later · 12 only as an assembly brick
1801.07829 (2018-01)
Dynamic Graph CNN for Learning on Point Clouds
2005.06734 (2020-05)
Dense-Resolution Network for Point Cloud Classification and Segmentation
2006.12052 (2020-06)
Few-shot 3D Point Cloud Semantic Segmentation
and 49 more not named here
pc_normalize 36 other papers
3 dated earlier, 33 later
1803.05827 (2018-03)
Local Spectral Graph Convolution for Point Set Feature Learning
1904.02375 (2019-04)
ConvPoint: Continuous Convolutions for Point Cloud Processing
1904.10014 (2019-04)
Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
and 33 more not named here
distChamfer 6 other papers
6 later
1906.12320 (2019-06)
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
2004.01301 (2020-04)
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
2008.06520 (2020-08)
Learning Gradient Fields for Shape Generation
and 3 more not named here
euler2mat 6 other papers
6 later
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2001.05574 (2020-01)
Advbox: a toolbox to generate adversarial examples that fool neural networks
2004.01301 (2020-04)
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
and 3 more not named here
euler2quat 6 other papers
6 later
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2001.05574 (2020-01)
Advbox: a toolbox to generate adversarial examples that fool neural networks
2004.01301 (2020-04)
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
and 3 more not named here
mat2euler 6 other papers
6 later
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
2001.05574 (2020-01)
Advbox: a toolbox to generate adversarial examples that fool neural networks
2004.01301 (2020-04)
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
and 3 more not named here
feature_transform_regularizer 4 other papers
1 dated earlier, 3 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1912.00280 (2019-12)
Morphing and Sampling Network for Dense Point Cloud Completion
2311.14265 (2023-11)
Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks
and 1 more not named here
distChamferCUDA 1 other paper
1 later
1906.12320 (2019-06)
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
emd_approx 1 other paper
1 later
1906.12320 (2019-06)
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

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

In this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-class 3D point cloud generation, a tree-structured graph convolution network (TreeGCN) is introduced as a generator for tree-GAN. Because TreeGCN performs graph convolutions within a tree, it can use ancestor information to boost the representation power for features. To evaluate GANs for 3D point clouds accurately, we develop a novel evaluation metric called Frechet point cloud distance (FPD). Experimental results demonstrate that the proposed tree-GAN outperforms state-of-the-art GANs in terms of both conventional metrics and FPD, and can generate point clouds for different semantic parts without prior knowledge.

For agents

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

get_harvested_code_for_paper("1905.06292")
get_code_for_paper("1905.06292")
have("1905.06292")

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

curl https://syntology.ai/api/ran/1905.06292.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.06292.svg)](https://syntology.ai/paper/1905.06292)

Connect an agent — have() is free.