SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.10739 · NeurIPS · 2024

PointMamba: A Simple State Space Model for Point Cloud Analysis

Xiao Tan, Wei Xu, Xiang Bai, Xiaoqing Ye, Dingkang Liang, Xin Zhou, Xingkui Zhu, Zhikang Zou

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 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/2402.10739.json · badge: /api/ran/2402.10739.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
LMD0311/PointMamba canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
batch2offset Ran
ran; our contract draft was wrong, not the code
LMD0311/PointMamba/models/serialization.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hzxie/GaussianCity, is pointer only (licence: NOASSERTION) · get_code("c02237104f832f3d")
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 hzxie/GaussianCity, 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.

farthest_point_sample Ran
ran; our contract draft was wrong, not the code
LMD0311/PointMamba/datasets/ModelNetDataset.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("f80066a00e7156a2")
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 Yuzhe-Fu/FlashFPS, 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.

gray2binary Ran
ran; our contract draft was wrong, not the code
LMD0311/PointMamba/models/hilbert.py
code served (permissive licence) · get_code("f3ce15083e63461d")
How it ran

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

torch.manual_seed(0)

# Create a small tensor of Gray codes
# Shape: (2, 4) - batch of 2, 4-bit values
gray = torch.randint(0, 2, (2, 4), dtype=torch.uint8)

# Define ARGS dict with all parameters for gray2binary
ARGS = {
    "gray": gray,
    "axis": -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 2, dtype family float, shape (2, 4) — shape (2, 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
load_modelnet_data Ran
ran; our contract draft was wrong, not the code
LMD0311/PointMamba/datasets/ModelNetDataset.py
code served (permissive licence) · get_code("39b2b4edb312a41a")
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 os
import tempfile
import h5py
import numpy as np

# Create a temporary directory structure with mock HDF5 files
temp_dir = tempfile.mkdtemp()
data_dir = os.path.join(temp_dir, 'data', 'modelnet40_ply_hdf5_2048')
os.makedirs(data_dir, exist_ok=True)

# Create mock HDF5 files for 'train' partition
for i in range(2):
    h5_path = os.path.join(data_dir, f'ply_data_train{i}.h5')
    with h5py.File(h5_path, 'w') as f:
        # Create datasets with appropriate shapes and dtypes
        f.create_dataset('data', data=np.random.rand(4, 2048, 3).astype('float32'))
        f.create_dataset('label', data=np.random.randint(0, 40, (4,)).astype('int64'))

# Monkey patch os.path.join to redirect to our temp directory
original_join = os.path.join
def patched_join(base, *args):
    if base == './' and args and args[0] == 'data':
        return os.path.join(temp_dir, *args)
    return original_join(base, *args)

os.path.join = patched_join

ARGS = {
    'partition': 'train'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, 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
offset2batch Ran
ran; our contract draft was wrong, not the code
LMD0311/PointMamba/models/serialization.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hzxie/GaussianCity, is pointer only (licence: NOASSERTION) · get_code("784720b30e505460")
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 hzxie/GaussianCity, 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.

offset2bincount Ran
ran; our contract draft was wrong, not the code
LMD0311/PointMamba/models/serialization.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hzxie/GaussianCity, is pointer only (licence: NOASSERTION) · get_code("c17c79b2e37251f8")
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 hzxie/GaussianCity, 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.

pc_normalize Ran
ran, honoured the contract we drafted
LMD0311/PointMamba/datasets/ModelNetDataset.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ajhamdi/MVTN, is pointer only (licence: NONE) · get_code("4783fbece52f500e")
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 ajhamdi/MVTN, 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.

right_shift Ran
ran; our contract draft was wrong, not the code
LMD0311/PointMamba/models/hilbert.py
code served (permissive licence) · get_code("7af58291b04f4410")
How it ran

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

torch.manual_seed(0)

# Create a small binary tensor with distinct dimensions
# Shape: (2, 4) - batch size 2, 4 binary values
binary = torch.randint(0, 2, (2, 4), dtype=torch.float32)

# Parameter k: number of bits to shift
k = 1

# Parameter axis: axis along which to shift
axis = -1

ARGS = {
    "binary": binary,
    "k": k,
    "axis": axis,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
binary2gray Not yet run
unverified (harvested, no recorded run)
LMD0311/PointMamba/models/hilbert.py
code served (permissive licence) · get_code("48079b763eddc476")
How it ran

no invocation recorded.

init_OrderScale Not yet run
unverified (harvested, no recorded run)
LMD0311/PointMamba/models/point_mamba_scan.py
code served (permissive licence) · get_code("7a38a2ca78379629")
How it ran

no invocation recorded.

serialization Not yet run
unverified (harvested, no recorded run)
LMD0311/PointMamba/models/point_mamba_scan.py
code served (permissive licence) · get_code("1ab92811ce8e8b53")
How it ran

no invocation 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, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 2 the same month, 9 later) and 2 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
pc_normalize 47 other papers
25 dated earlier, 1 the same month, 20 later, 1 same year, order not determinable
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
1912.12098 (2019-12)
Quaternion Equivariant Capsule Networks for 3D Point Clouds
2003.00492 (2020-03)
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
and 44 more not named here
farthest_point_sample 43 other papers
21 dated earlier, 1 the same month, 20 later, 1 same year, order not determinable
1811.07246 (2018-11)
PointConv: Deep Convolutional Networks on 3D Point Clouds
2003.00492 (2020-03)
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
2010.05272 (2020-10)
IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
and 40 more not named here
load_modelnet_data 4 other papers
4 later
2403.01439 (2024-03)
Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
2405.15463 (2024-05)
PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis
2410.08114 (2024-10)
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
and 1 more not named here
batch2offset 2 other papers
1 dated earlier, 1 later
2312.10035 (2023-12)
Point Transformer V3: Simpler, Faster, Stronger
2406.06526 (2024-06)
Generative Gaussian Splatting for Unbounded 3D City Generation
binary2gray 2 other papers
1 dated earlier, 1 later
2312.10035 (2023-12)
Point Transformer V3: Simpler, Faster, Stronger
2503.16429 (2025-03)
Sonata: Self-Supervised Learning of Reliable Point Representations
gray2binary 2 other papers
1 dated earlier, 1 later
2312.10035 (2023-12)
Point Transformer V3: Simpler, Faster, Stronger
2503.16429 (2025-03)
Sonata: Self-Supervised Learning of Reliable Point Representations
offset2batch 2 other papers
1 dated earlier, 1 later
2312.10035 (2023-12)
Point Transformer V3: Simpler, Faster, Stronger
2406.06526 (2024-06)
Generative Gaussian Splatting for Unbounded 3D City Generation
offset2bincount 2 other papers
1 dated earlier, 1 later
2312.10035 (2023-12)
Point Transformer V3: Simpler, Faster, Stronger
2406.06526 (2024-06)
Generative Gaussian Splatting for Unbounded 3D City Generation
right_shift 2 other papers
1 dated earlier, 1 later
2312.10035 (2023-12)
Point Transformer V3: Simpler, Faster, Stronger
2503.16429 (2025-03)
Sonata: Self-Supervised Learning of Reliable Point Representations

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

leverages space-filling curves for effective point tokenization and adopts an extremely simple, non-hierarchical Mamba encoder as the backbone. Comprehensive evaluations demonstrate that PointMamba achieves superior performance across multiple datasets while significantly reducing GPU memory usage and FLOPs. This work underscores the potential of SSMs in 3D vision-related tasks and presents a simple yet effective Mamba-based baseline for future research. The code will be made available at https://github.com/LMD0311/PointMamba.

For agents

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

get_harvested_code_for_paper("2402.10739")
get_code_for_paper("2402.10739")
have("2402.10739")

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

curl https://syntology.ai/api/ran/2402.10739.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.10739.svg)](https://syntology.ai/paper/2402.10739)

Connect an agent — have() is free.