SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.09859 · 2024

OccMamba: Semantic Occupancy Prediction with State Space Models

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2408.09859.json · badge: /api/ran/2408.09859.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
USTCLH/OccMamba canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
ancestors Ran
ran; our contract draft was wrong, not the code
USTCLH/OccMamba/dependence/dag.py
code served (permissive licence) · get_code("1d3a5ccf3a75a0d3")
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 set. 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 networkx as nx

# Create a simple directed acyclic graph (DAG)
G = nx.DiGraph()

# Add nodes
G.add_nodes_from([1, 2, 3, 4, 5])

# Add edges to create a DAG with ancestors
# Edge direction: (ancestor) -> (descendant)
G.add_edge(1, 2)  # 1 -> 2
G.add_edge(1, 3)  # 1 -> 3
G.add_edge(2, 4)  # 2 -> 4
G.add_edge(3, 4)  # 3 -> 4
G.add_edge(4, 5)  # 4 -> 5

# Choose a source node that has ancestors
source = 5

# Construct the arguments dictionary
ARGS = {
    'G': G,
    'source': source
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
descendants Ran
ran; our contract draft was wrong, not the code
USTCLH/OccMamba/dependence/dag.py
code served (permissive licence) · get_code("05a195cac900ea0e")
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 set. 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 networkx as nx

# Create a simple directed acyclic graph (DAG)
G = nx.DiGraph()

# Add nodes
G.add_nodes_from(['A', 'B', 'C', 'D', 'E'])

# Add edges to create a DAG with reachable descendants from source
G.add_edges_from([
    ('A', 'B'),
    ('A', 'C'),
    ('B', 'D'),
    ('C', 'E'),
    ('D', 'E')
])

source = 'A'

ARGS = {
    'G': G,
    'source': source
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
fast_hist Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
USTCLH/OccMamba/projects/occ_plugin/occupancy/detectors/occmamba.py
code served (permissive licence) · get_code("4b39850e5b66c8ba")
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 int, shape (18, 18) 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 copy

# Construct valid arguments for fast_hist function
# The function expects:
# - pred: array-like that can be flattened and used in bincount
# - label: array-like that can be flattened and used in bincount
# - max_label: int specifying the number of classes (default 18)

# Create small prediction and label arrays
# pred and label should be integer arrays (they're used in bincount)
np.random.seed(0)

# Create predictions: shape (2, 3) with values in range [0, max_label)
pred = np.array([[0, 1, 2], [1, 2, 0]], dtype=np.int32)

# Create labels: shape (2, 3) with values in range [0, max_label)
label = np.array([[0, 1, 1], [2, 0, 1]], dtype=np.int32)

# Set max_label
max_label = 18

ARGS = {
    'pred': pred,
    'label': label,
    'max_label': max_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 int, shape (18, 18) — shape (18, 18) 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

Training deep learning models for semantic occupancy prediction is challenging due to factors such as a large number of occupancy cells, severe occlusion, limited visual cues, complicated driving scenarios, etc. Recent methods often adopt transformer-based architectures given their strong capability in learning input-conditioned weights and long-range relationships. However, transformer-based networks are notorious for their quadratic computation complexity, seriously undermining their efficacy and deployment in semantic occupancy prediction. Inspired by the global modeling and linear computation complexity of the Mamba architecture, we present the first Mamba-based network for semantic occupancy prediction, termed OccMamba. Specifically, we first design the hierarchical Mamba module and local context processor to better aggregate global and local contextual information, respectively. Besides, to relieve the inherent domain gap between the linguistic and 3D domains, we present a simple yet effective 3D-to-1D reordering scheme, i.e., height-prioritized 2D Hilbert expansion. It can maximally retain the spatial structure of 3D voxels as well as facilitate the processing of Mamba blocks. Endowed with the aforementioned designs, our OccMamba is capable of directly and efficiently processing large volumes of dense scene grids, achieving state-of-the-art performance across three prevalent occupancy prediction benchmarks, including OpenOccupancy, SemanticKITTI, and SemanticPOSS. Notably, on OpenOccupancy, our OccMamba outperforms the previous state-of-the-art Co-Occ by 5.1% IoU and 4.3% mIoU, respectively. Our implementation is open-sourced and available at: https://github.com/USTCLH/OccMamba.

For agents

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

get_harvested_code_for_paper("2408.09859")
get_code_for_paper("2408.09859")
have("2408.09859")

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

curl https://syntology.ai/api/ran/2408.09859.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.09859.svg)](https://syntology.ai/paper/2408.09859)

Connect an agent — have() is free.