SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.14302 · CVPR · 2024

SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks

Zhaofei Yu, Zecheng Hao, Xinyu Shi

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/2403.14302.json · badge: /api/ran/2403.14302.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
xyshi2000/SpikingResformer canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xyshi2000/SpikingResformer/utils/utils.py
code served (permissive licence) · get_code("07e28eaf04297032")
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. 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)

# Create small tensors for testing
batch_size = 2
num_classes = 4

# output: model predictions/logits, shape (batch_size, num_classes)
output = torch.randn(batch_size, num_classes)

# target: ground truth class indices, shape (batch_size,)
target = torch.tensor([1, 2])

# topk: tuple of k values to compute accuracy for
topk = (1, 2)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk,
}
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
unpack_for_conv Ran
ran; our contract draft was wrong, not the code
xyshi2000/SpikingResformer/utils/utils.py
code served (permissive licence) · get_code("370fafd58269c37f")
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 3, dtype family float, shape (8, 3, 5) 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)

# The function unpack_for_conv accepts either a torch.Tensor or a Tuple[torch.Tensor]
# It checks if input is a tuple, asserts length 1, unpacks it, then flattens dims 0 and 1

# Test case 1: Pass a tuple containing a single tensor
x_tensor = torch.randn(2, 4, 3, 5)  # shape: (batch=2, channels=4, height=3, width=5)
x_tuple = (x_tensor,)

# Test case 2: Pass a tensor directly
x_direct = torch.randn(2, 4, 3, 5)

# Create ARGS with the tuple case (since the function explicitly handles tuples)
ARGS = {
    "x": x_tuple
}
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 3, dtype family float, shape (8, 3, 5) — shape (8, 3, 5) 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
unpack_for_linear Ran
ran; our contract draft was wrong, not the code
xyshi2000/SpikingResformer/utils/utils.py
code served (permissive licence) · get_code("f41c1d335d8b60e7")
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 (6, 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
import torch.utils.data

torch.manual_seed(0)

# The function unpack_for_linear accepts a Union[Tuple[torch.Tensor], torch.Tensor]
# It checks if x is a tuple with length 1, extracts the tensor, then flattens dimensions 0 and 1

# Case 1: Pass a tuple containing a single tensor
# The tensor should have at least 2 dimensions to flatten(0, 1)
# Using shape (2, 3, 4) - batch=2, dim1=3, dim2=4
tensor_in_tuple = (torch.randn(2, 3, 4),)

ARGS = {
    "x": tensor_in_tuple
}
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 (6, 4) — shape (6, 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

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

The remarkable success of Vision Transformers in Artificial Neural Networks (ANNs) has led to a growing interest in incorporating the self-attention mechanism and transformer-based architecture into Spiking Neural Networks (SNNs). While existing methods propose spiking self-attention mechanisms that are compatible with SNNs, they lack reasonable scaling methods, and the overall architectures proposed by these methods suffer from a bottleneck in effectively extracting local features. To address these challenges, we propose a novel spiking self-attention mechanism named Dual Spike Self-Attention (DSSA) with a reasonable scaling method. Based on DSSA, we propose a novel spiking Vision Transformer architecture called SpikingResformer, which combines the ResNet-based multi-stage architecture with our proposed DSSA to improve both performance and energy efficiency while reducing parameters. Experimental results show that SpikingResformer achieves higher accuracy with fewer parameters and lower energy consumption than other spiking Vision Transformer counterparts. Notably, our SpikingResformer-L achieves 79.40% top-1 accuracy on ImageNet with 4 time-steps, which is the state-of-theart result in the SNN field. Codes are available at https://github.com/xyshi2000/SpikingResformer

For agents

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

get_harvested_code_for_paper("2403.14302")
get_code_for_paper("2403.14302")
have("2403.14302")

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

curl https://syntology.ai/api/ran/2403.14302.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.14302.svg)](https://syntology.ai/paper/2403.14302)

Connect an agent — have() is free.