SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.13098 · 2023

Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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 7 have no contract verdict; 6 failures of our instrument; 1 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/2304.13098.json · badge: /api/ran/2304.13098.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
intelligent-computing-lab-yale/snncka canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
TET_loss Ran
ran; our contract draft was wrong, not the code
intelligent-computing-lab-yale/snncka/functions.py
code served (permissive licence) · get_code("e63c09a8d741cb95")
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) and returned Tensor, 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)

# outputs: tensor with shape (batch, T, ...) where T is time steps
# The function indexes outputs[:, t, ...] for each t in range(T)
# and passes it to criterion along with labels
batch_size = 2
T = 3  # number of time steps
num_classes = 4

outputs = torch.randn(batch_size, T, num_classes)

# labels: passed to criterion(outputs[:, t, ...], labels)
# For a typical classification criterion like CrossEntropyLoss,
# labels should have shape (batch_size,) with class indices
labels = torch.randint(0, num_classes, (batch_size,))

# criterion: called as criterion(outputs[:, t, ...], labels)
# outputs[:, t, ...] has shape (batch_size, num_classes)
# Standard choice is CrossEntropyLoss
criterion = nn.CrossEntropyLoss()

# means: used in torch.zeros_like(outputs).fill_(means)
# fill_ expects a scalar value
means = 0.5

# lamb: scalar parameter for weighting
lamb = 0.3

ARGS = {
    "outputs": outputs,
    "labels": labels,
    "criterion": criterion,
    "means": means,
    "lamb": lamb,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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
add_dimention Ran
ran; our contract draft was wrong, not the code
intelligent-computing-lab-yale/snncka/models/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from bollossom/GAC, is pointer only (licence: NONE) · get_code("13a0e034c03001ab")
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 bollossom/GAC, 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
intelligent-computing-lab-yale/snncka/models/ann_resnet.py
code served (permissive licence) · get_code("5424e5b21df4db41")
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) and returned Conv2d. 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

torch.manual_seed(0)

ARGS = {
    "in_planes": 64,
    "out_planes": 128,
    "stride": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
intelligent-computing-lab-yale/snncka/models/ann_resnet.py
code served (permissive licence) · get_code("76fdd94bb075ca26")
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) and returned Conv2d. 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

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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_logger Ran
ran; our contract draft was wrong, not the code
intelligent-computing-lab-yale/snncka/functions.py
pointer only (licence: MIT); the stored copy get_code serves, from hzc1208/lmht_snn, is pointer only (licence: NONE) · get_code("210ba8a40d178d14")
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 hzc1208/lmht_snn, 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.

mix_loss Ran
ran on a synthesized input
intelligent-computing-lab-yale/snncka/functions.py
code served (permissive licence) · get_code("64e29f37d8524f28")
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 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 outputs tensor: (batch_size=2, T=3, feature_dim=4)
outputs = torch.randn(2, 3, 4)

# Create labels tensor: (batch_size=2,) - for classification
labels = torch.randint(0, 2, (2,))

# Create criterion - MSELoss or CrossEntropyLoss
criterion = nn.CrossEntropyLoss()

# Create means - a scalar value used to fill the comparison tensor
means = 0.5

# Create lamb - mixing parameter between 0 and 1
lamb = 0.3

ARGS = {
    "outputs": outputs,
    "labels": labels,
    "criterion": criterion,
    "means": means,
    "lamb": lamb
}
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 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
normalizex Ran
ran; our contract draft was wrong, not the code
intelligent-computing-lab-yale/snncka/models/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from bollossom/GAC, is pointer only (licence: NONE) · get_code("a93504b7fd3c8d98")
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 bollossom/GAC, 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.

pgd_attack Ran
ran on a synthesized input
intelligent-computing-lab-yale/snncka/main_cka.py
code served (permissive licence) · get_code("1cd06c5112c03ed6")
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
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that accepts input and produces output
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        # Function expects outputs to be potentially 3D (batch, seq, classes)
        # or 2D (batch, classes). Let's return 2D to keep it simple.
        return self.linear(x)

# Create model instance
model = SimpleModel()

# Create small tensors: batch_size=2, feature_dim=4
data = torch.randn(2, 4, requires_grad=False)

# Create labels: batch_size=2, num_classes=3
label = torch.tensor([0, 1])

# Device: CPU only
device = 'cpu'

# Criterion: CrossEntropyLoss expects (batch, num_classes) output and (batch,) labels
criterion = nn.CrossEntropyLoss()

# Optional parameters with defaults
eps = 0.01
iters = 20

ARGS = {
    'model': model,
    'data': data,
    'label': label,
    'device': device,
    'criterion': criterion,
    'eps': eps,
    'iters': iters
}
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
resnet20 Ran
ran on a synthesized input
intelligent-computing-lab-yale/snncka/models/ann_resnet.py
code served (permissive licence) · get_code("9828e98d9495e916")
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 ResNet. 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

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
    'progress': True,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
test Ran
ran on a synthesized input
intelligent-computing-lab-yale/snncka/main_ann.py
code served (permissive licence) · get_code("8654ec9c4f1b5798")
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. 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, 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)

# Define a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 3)  # Input dim 4, output dim 3 (for 3 classes)
    
    def forward(self, x):
        return self.fc(x)

# Create model instance
model = SimpleModel()

# Create a simple test loader (list of (inputs, targets) tuples)
test_loader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 1])),
]

# Set device to CPU
device = torch.device('cpu')

ARGS = {
    'model': model,
    'test_loader': test_loader,
    'device': device,
}
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
test Ran
ran on a synthesized input
intelligent-computing-lab-yale/snncka/main_cka.py
code served (permissive licence) · get_code("923ba0c4d3b292e9")
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. 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, 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)

# Build a small model that satisfies the function's usage
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 5)  # 5 classes for classification
    
    def forward(self, x):
        return self.linear(x)

# Build a test loader (list of (inputs, targets) tuples)
test_loader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 3])),
]

# Define the arguments dictionary
ARGS = {
    'model': SimpleModel(),
    'test_loader': test_loader,
    'device': 'cpu',
    'attack': False,
}
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
test Ran
ran on a synthesized input
intelligent-computing-lab-yale/snncka/main_snn.py
code served (permissive licence) · get_code("54dc7295010194cd")
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. 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, 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)

# Define a minimal model that satisfies the function's usage
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        # Function calls outputs.mean(1), so output should have shape (batch, num_classes, ...)
        # and then mean_out = outputs.mean(1) should give (batch, num_classes)
        # So we need outputs to be 3D: (batch, something, num_classes)
        out = self.linear(x)  # (batch, 3)
        # Reshape to (batch, 2, 3) so mean(1) gives (batch, 3)
        batch_size = out.shape[0]
        return out.unsqueeze(1).expand(batch_size, 2, 3)

model = SimpleModel()

# Create a test loader with tiny batches
# Each item is (inputs, targets)
# inputs should be shape (batch, 4) based on model's linear layer
# targets should be shape (batch,) with class indices
test_loader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 0])),
]

# Device - CPU only
device = 'cpu'

ARGS = {
    'model': model,
    'test_loader': test_loader,
    'device': device,
}
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
train Ran
ran on a synthesized input
intelligent-computing-lab-yale/snncka/main_ann.py
code served (permissive licence) · get_code("a25ba18da07f26f4")
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 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 torch.nn as nn
from torch.optim import SGD
from torch.cuda.amp import GradScaler

torch.manual_seed(0)

# Define a minimal model that takes images and outputs class predictions
class TinyModel(nn.Module):
    def __init__(self, num_classes=10):
        super().__init__()
        self.fc = nn.Linear(4, num_classes)
    
    def forward(self, x):
        # Flatten input and pass through linear layer
        x = x.view(x.size(0), -1)
        return self.fc(x)

# Build the model
model = TinyModel(num_classes=10)

# Define device (CPU only)
device = 'cpu'

# Create a tiny train loader with 3 batches
# Each batch: (images of shape [2, 1, 4], labels of shape [2])
train_loader = [
    (torch.randn(2, 1, 4), torch.randint(0, 10, (2,))),
    (torch.randn(2, 1, 4), torch.randint(0, 10, (2,))),
    (torch.randn(2, 1, 4), torch.randint(0, 10, (2,))),
]

# Define loss criterion
criterion = nn.CrossEntropyLoss(reduction='mean')

# Define optimizer
optimizer = SGD(model.parameters(), lr=0.01)

# Define epoch number
epoch = 1

# Define scaler for AMP
scaler = GradScaler()

# Define args with amp disabled (to avoid CUDA requirement)
class Args:
    def __init__(self):
        self.amp = False

args = Args()

ARGS = {
    'model': model,
    'device': device,
    'train_loader': train_loader,
    'criterion': criterion,
    'optimizer': optimizer,
    'epoch': epoch,
    'scaler': scaler,
    'args': args,
}
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 1, 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
build_cifar Not yet run
unverified (harvested, no recorded run)
intelligent-computing-lab-yale/snncka/data_loaders.py
code served (permissive licence) · get_code("f554a0f699717ecb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 6 later) and 8 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
conv1x1 431 other papers
251 dated earlier, 3 the same month, 168 later, 8 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
161 dated earlier, 1 the same month, 142 later, 7 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
get_logger 10 other papers
3 dated earlier, 7 later
2106.06716 (2021-06)
DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation
2205.08987 (2022-05)
Trading Positional Complexity vs Deepness in Coordinate Networks
2207.00012 (2022-07)
Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN
and 7 more not named here
normalizex 3 other papers
1 dated earlier, 2 later
2202.11946 (2022-02)
Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting
2308.06582 (2023-08)
Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks
aaai_27804 (2024 (year only))
Enhancing the Robustness of Spiking Neural Networks with Stochastic Gating Mechanisms
TET_loss 2 other papers
1 dated earlier, 1 later
2202.11946 (2022-02)
Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting
2308.06582 (2023-08)
Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks
add_dimention 2 other papers
1 dated earlier, 1 later
2202.11946 (2022-02)
Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting
2308.06582 (2023-08)
Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks

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

Spiking Neural Networks (SNNs) are recognized as the candidate for the next-generation neural networks due to their bio-plausibility and energy efficiency. Recently, researchers have demonstrated that SNNs are able to achieve nearly state-of-the-art performance in image recognition tasks using surrogate gradient training. However, some essential questions exist pertaining to SNNs that are little studied: Do SNNs trained with surrogate gradient learn different representations from traditional Artificial Neural Networks (ANNs)? Does the time dimension in SNNs provide unique representation power? In this paper, we aim to answer these questions by conducting a representation similarity analysis between SNNs and ANNs using Centered Kernel Alignment (CKA). We start by analyzing the spatial dimension of the networks, including both the width and the depth. Furthermore, our analysis of residual connections shows that SNNs learn a periodic pattern, which rectifies the representations in SNNs to be ANN-like. We additionally investigate the effect of the time dimension on SNN representation, finding that deeper layers encourage more dynamics along the time dimension. We also investigate the impact of input data such as event-stream data and adversarial attacks. Our work uncovers a host of new findings of representations in SNNs. We hope this work will inspire future research to fully comprehend the representation power of SNNs. Code is released at https://github.com/Intelligent-Computing-Lab-Yale/SNNCKA.

For agents

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

get_harvested_code_for_paper("2304.13098")
get_code_for_paper("2304.13098")
have("2304.13098")

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

curl https://syntology.ai/api/ran/2304.13098.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.13098.svg)](https://syntology.ai/paper/2304.13098)

Connect an agent — have() is free.