SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.10316 · ICCV · 2023

CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation

Zhuangwei Zhuang, Mingkui Tan, Jingdong Wang, Cen Chen, Lizhao Liu, Shangxin Huang, Xunlong Xiao, Tianhang Xiang

arXiv · PDF · Open in the Atlas

Code that ran

11 of 11 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, 1 violated it and 0 have no contract verdict; 8 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2307.10316.json · badge: /api/ran/2307.10316.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
lizhaoliu-Lec/CPCM canonical (classifier label)
classifier basis: census
11 ran · 0 no recorded run
FunctionStatusWhere it lives
all_gather Ran
ran; our contract draft was wrong, not the code
lizhaoliu-Lec/CPCM/lib/distributed.py
code served (permissive licence) · get_code("95b5d00548dba1c3")
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. 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 and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import pickle

torch.manual_seed(0)

# The function all_gather takes one parameter: data
# It pickles the data, so data can be any picklable object
# Let's use a simple dictionary as test data

test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": torch.tensor([1.0, 2.0, 3.0, 4.0])
}

ARGS = {
    "data": test_data
}
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 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
all_gather_differentiable Ran
ran, honoured the contract we drafted
lizhaoliu-Lec/CPCM/lib/distributed.py
code served (permissive licence) · get_code("21a20dd6b4072587")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 3, dtype family float; no output shape is stated. 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 and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.distributed as dist

torch.manual_seed(0)

# Create a small tensor with shape [num_points, feature_dim]
# Using distinct sizes: 2 points, 4 feature dimensions
tensor = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    "tensor": tensor
}
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 list, ndim 3, 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
colorize_pointcloud Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lizhaoliu-Lec/CPCM/lib/pc_utils.py
code served (permissive licence) · get_code("e9cb06004b17fb2e")
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, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create sample point cloud data
# xyz: N x 3 array of point coordinates
xyz = np.random.rand(5, 3).astype(np.float32)

# label: N array of label indices
# Labels should be valid indices into COLOR_MAP_RGB (0-15) or ignore_label (255)
label = np.array([0, 1, 2, 3, 255], dtype=np.int32)

# ignore_label: the label value to ignore (default 255)
ignore_label = 255

ARGS = {
    "xyz": xyz,
    "label": label,
    "ignore_label": ignore_label,
}
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, 6) — shape (5, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
fast_hist Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lizhaoliu-Lec/CPCM/lib/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from yilmazkadir/segmentation_losses, is pointer only (licence: NONE) · get_code("3e350d1ea4a3538d")
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 yilmazkadir/segmentation_losses, 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.

is_master_proc Ran
ran, violated the contract we drafted
lizhaoliu-Lec/CPCM/lib/distributed.py
code served (permissive licence) · get_code("7b044f8063a9b668")
How it ran

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

import torch

# For this function, we need to handle the case where torch.distributed might not be initialized
# We'll test with num_gpus = 1 to avoid needing to set up distributed training

torch.manual_seed(0)

# The function takes num_gpus as a parameter
# When num_gpus == 1, it returns True (single GPU case - current process is master)
# When num_gpus > 1, it would call torch.distributed.get_rank() which requires initialized distributed training
# For safety and simplicity, we test with num_gpus = 1

ARGS = {
    "num_gpus": 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 bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_state_with_same_shape Ran
ran; our contract draft was wrong, not the code
lizhaoliu-Lec/CPCM/lib/utils.py
code served (permissive licence) · get_code("04dfd706a56764cb")
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 torch
import torch.nn as nn
import logging

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear2(self.linear1(x))

# Instantiate the model
model = SimpleModel()

# Create weights dict that matches model state_dict structure
weights = {
    'linear1.weight': torch.randn(3, 4),
    'linear1.bias': torch.randn(3),
    'linear2.weight': torch.randn(2, 3),
    'linear2.bias': torch.randn(2),
}

ARGS = {
    'model': model,
    'weights': weights,
}
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 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
precision_at_one Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lizhaoliu-Lec/CPCM/lib/utils.py
code served (permissive licence) · get_code("4f6287104e513039")
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 torch.nn as nn

torch.manual_seed(0)

# Create small tensors for pred and target
# pred: predicted class labels
# target: ground truth class labels
# Both need to be reshaped to (1, -1) in the function, so we start with flattened shape
pred = torch.tensor([0, 1, 2, 3, 1, 2], dtype=torch.long)
target = torch.tensor([0, 1, 2, 255, 1, 2], dtype=torch.long)

ignore_label = 255

ARGS = {
    "pred": pred,
    "target": target,
    "ignore_label": ignore_label,
}
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 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
random_sampling Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lizhaoliu-Lec/CPCM/lib/pc_utils.py
code served (permissive licence) · get_code("1d1392e58959df67")
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

# Create a small point cloud: 5 points with 3 coordinates each
pc = np.random.randn(5, 3).astype(np.float32)

# Number of samples to draw
num_sample = 3

# Replace parameter
replace = False

# Return choices flag
return_choices = True

ARGS = {
    "pc": pc,
    "num_sample": num_sample,
    "replace": replace,
    "return_choices": return_choices
}
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
read_plyfile Ran
ran, honoured the contract we drafted
lizhaoliu-Lec/CPCM/lib/pc_utils.py
code served (permissive licence) · get_code("2959b7c77776b51d")
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 (3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os
from plyfile import PlyData, PlyElement
import numpy as np

# Create a temporary PLY file for testing
temp_dir = tempfile.mkdtemp()
filepath = os.path.join(temp_dir, "test.ply")

# Create sample vertex data
vertex_data = np.array([
    (0.0, 0.0, 0.0),
    (1.0, 1.0, 1.0),
    (2.0, 2.0, 2.0)
], dtype=[('x', 'f4'), ('y', 'f4'), ('z', 'f4')])

# Create PLY element and file
vertex_el = PlyElement.describe(vertex_data, 'vertex')
ply_data = PlyData([vertex_el])
ply_data.write(filepath)

ARGS = {
    'filepath': filepath
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, plyfile — 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 (3, 3) — shape (3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
torch_intersect Ran
ran; our contract draft was wrong, not the code
lizhaoliu-Lec/CPCM/model/build.py
code served (permissive licence) · get_code("09cb5ffa3484c7c1")
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 1, dtype family int, 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 torch
import numpy as np

torch.manual_seed(0)

# Create two small tensors with some overlapping elements
t1 = torch.tensor([1, 2, 3, 4, 2, 1])
t2 = torch.tensor([3, 4, 5, 6, 4, 3])

ARGS = {
    "t1": t1,
    "t2": t2
}
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 1, dtype family int, 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
trunc_normal_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lizhaoliu-Lec/CPCM/model/res16unet.py
pointer only (licence: MIT); the stored copy get_code serves, from LHDuan/ConDaFormer, is pointer only (licence: NONE) · get_code("5436174f8c0e64e0")
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 LHDuan/ConDaFormer, 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.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 later) and 5 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
trunc_normal_ 160 other papers
62 dated earlier, 3 the same month, 93 later, 2 same year, order not determinable · 36 only as an assembly brick
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2007.12911 (2020-07)
Tighter risk certificates for neural networks
and 157 more not named here
all_gather 7 other papers
5 dated earlier, 1 later, 1 same year, order not determinable
2004.01946 (2020-04)
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
2007.10985 (2020-07)
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
2104.10011 (2021-04)
Perceptual Loss for Robust Unsupervised Homography Estimation
and 4 more not named here
random_sampling 2 other papers
2 later
2309.01692 (2023-09)
Mask-Attention-Free Transformer for 3D Instance Segmentation
2412.02402 (2024-12)
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
all_gather_differentiable 1 other paper
1 dated earlier
2007.10985 (2020-07)
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
fast_hist 1 other paper
1 later
2312.05391 (2023-12)
Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook
is_master_proc 1 other paper
1 dated earlier
2007.10985 (2020-07)
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding

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

We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations (e.g., less than 0.1% points are labeled), aiming to reduce the expensive cost of dense annotations. Unfortunately, with extremely sparse annotated points, it is very difficult to extract both contextual and object information for scene understanding such as semantic segmentation. Motivated by masked modeling (e.g. method. Specifically, RegionMask masks the point cloud continuously in geometric space to construct a meaningful masked prediction task for subsequent context learning. CMT disentangles the learning of supervised segmentation and unsupervised masked context prediction for effectively learning the very limited labeled points and mass unlabeled points, respectively. Extensive experiments on the widelytested ScanNet V2 and S3DIS benchmarks demonstrate the superiority of CPCM over the state-of-the-art.

For agents

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

get_harvested_code_for_paper("2307.10316")
get_code_for_paper("2307.10316")
have("2307.10316")

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

curl https://syntology.ai/api/ran/2307.10316.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.10316.svg)](https://syntology.ai/paper/2307.10316)

Connect an agent — have() is free.