SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.04240 · 2026

SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Prediction

Ying-Cong Chen, Leheng Li, Suzeyu Chen

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 1 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/2602.04240.json · badge: /api/ran/2602.04240.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
chensuzeyu/SpotOcc canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
cumsum_trick Ran
ran; our contract draft was wrong, not the code
chensuzeyu/SpotOcc/projects/mmdet3d_plugin/spotocc/image2bev/ViewTransformerLSSBEVDepth.py
code served (permissive licence) · get_code("8945de8524a23486")
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 torch

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# x: cumsum operates on dimension 0, so shape (batch, features)
x = torch.randn(2, 4, dtype=torch.float32)

# geom_feats: needs to be indexable with kept boolean tensor, same batch size as x
geom_feats = torch.randn(2, 3, dtype=torch.float32)

# ranks: used for comparison ranks[1:] != ranks[:-1], needs length matching x.shape[0]
ranks = torch.tensor([0, 1], dtype=torch.int64)

ARGS = {
    "x": x,
    "geom_feats": geom_feats,
    "ranks": ranks
}
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 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
gen_dx_bx Ran
ran, violated the contract we drafted
chensuzeyu/SpotOcc/projects/mmdet3d_plugin/spotocc/image2bev/ViewTransformerLSSBEVDepth.py
code served (permissive licence) · get_code("f6a173f4830f978c")
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 2, 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 torch

torch.manual_seed(0)

# Each bound is a list with [min, max, step]
# The function expects three bounds: xbound, ybound, zbound
xbound = [0.0, 10.0, 0.5]
ybound = [-5.0, 5.0, 0.25]
zbound = [0.0, 20.0, 1.0]

ARGS = {
    "xbound": xbound,
    "ybound": ybound,
    "zbound": zbound,
}
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 tuple, ndim 2, 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
get_model_dataset Ran
ran; our contract draft was wrong, not the code
chensuzeyu/SpotOcc/mmdetection3d/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("da059252c88ecf40")
How it ran

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

import torch
import os
import tempfile

torch.manual_seed(0)

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Create test log JSON paths with dataset keywords
log_json_path_coco = os.path.join(temp_dir, "results_coco_experiment.json")
log_json_path_nus = os.path.join(temp_dir, "nus_detection_log.json")
log_json_path_kitti = os.path.join(temp_dir, "kitti-3d-3class_results.json")
log_json_path_lyft = os.path.join(temp_dir, "lyft_benchmark.json")
log_json_path_scannet_seg = os.path.join(temp_dir, "scannet_seg_output.json")

# Test with a simple coco path
test_log_json_path = os.path.join(temp_dir, "coco_results.json")

ARGS = {
    "log_json_path": test_log_json_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
process_checkpoint Ran
ran; our contract draft was wrong, not the code
chensuzeyu/SpotOcc/mmdetection3d/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("e76a491553cf9fcf")
How it ran

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

import torch
import tempfile
import os

torch.manual_seed(0)

# Create a temporary directory for checkpoint files
temp_dir = tempfile.mkdtemp()

# Create a minimal checkpoint dict with a model state and optimizer
checkpoint = {
    'model': {
        'layer1.weight': torch.randn(4, 3),
        'layer1.bias': torch.randn(4),
    },
    'optimizer': {
        'state': {},
        'param_groups': [],
    },
    'epoch': 1,
}

# Save the checkpoint to a temporary file
in_file = os.path.join(temp_dir, 'checkpoint.pth')
torch.save(checkpoint, in_file)

# Define output file path
out_file = os.path.join(temp_dir, 'checkpoint_processed.pth')

ARGS = {
    'in_file': in_file,
    'out_file': out_file,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_final_epoch Not yet run
unverified (harvested, no recorded run)
chensuzeyu/SpotOcc/mmdetection3d/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("90f6ae7209cde36f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 0 later) and 0 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
process_checkpoint 45 other papers
44 dated earlier, 1 undated
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 42 more not named here
get_final_epoch 35 other papers
34 dated earlier, 1 undated
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 32 more not named here
get_model_dataset 26 other papers
25 dated earlier, 1 undated
2104.06114 (2021-04)
Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
2104.10956 (2021-04)
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
2112.04680 (2021-12)
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
and 23 more not named here
cumsum_trick 4 other papers
4 dated earlier
2210.07729 (2022-10)
Model-Based Imitation Learning for Urban Driving
2304.11379 (2023-04)
LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation
2311.11762 (2023-11)
MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations
and 1 more not named here
gen_dx_bx 1 other paper
1 dated earlier
2310.15670 (2023-10)
Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Achieving highly accurate and real-time 3D occupancy prediction from cameras is a critical requirement for the safe and practical deployment of autonomous vehicles. While this shift to sparse 3D representations solves the encoding bottleneck, it creates a new challenge for the decoder: how to efficiently aggregate information from a sparse, nonuniformly distributed set of voxel features without resorting to computationally prohibitive dense attention. In this paper, we propose a novel Prototype-based Sparse Transformer Decoder that replaces this costly interaction with an efficient, two-stage process of guided feature selection and focused aggregation. Our core idea is to make the decoder's attention prototypeguided. We achieve this through a sparse prototype selection mechanism, where each query adaptively identifies a compact set of the most salient voxel features, termed prototypes, for focused feature aggregation. To ensure this dynamic selection is stable and effective, we introduce a complementary denoising paradigm. This approach leverages ground-truth masks to provide explicit guidance, guaranteeing a consistent queryprototype association across decoder layers. Our model, dubbed SPOT-Occ, outperforms previous methods with a significant margin in speed while also improving accuracy. Source code is released at https://github.com/chensuzeyu/SpotOcc.

For agents

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

get_harvested_code_for_paper("2602.04240")
get_code_for_paper("2602.04240")
have("2602.04240")

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

curl https://syntology.ai/api/ran/2602.04240.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.04240.svg)](https://syntology.ai/paper/2602.04240)

Connect an agent — have() is free.