SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.07473 · 2022

Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization

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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2205.07473.json · badge: /api/ran/2205.07473.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
Windere/snn-cvt-dual-phase canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from facebookresearch/barlowtwins
pointer only · get_code("b0f936d4d6ae3b8c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

runTest Ran
ran, honoured the contract we drafted
Windere/snn-cvt-dual-phase/experiments/cifar10/main_ann.py
code served (permissive licence) · get_code("bde7b316f2fa19f9")
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. 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

torch.manual_seed(0)

# Small model that returns a single tensor output
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, output_dim=3):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

# Model that returns dict output (for multi-timestep case)
class DictModel(nn.Module):
    def __init__(self, input_dim=4, output_dim=3, nb_steps=2):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
        self.nb_steps = nb_steps
    
    def forward(self, x):
        output = self.linear(x)
        return {i: output for i in range(self.nb_steps)}

# Simple encoder that processes input
class SimpleEncoder(nn.Module):
    def __init__(self, nb_steps=2):
        super().__init__()
        self.nb_steps = nb_steps
    
    def forward(self, x):
        return x

# Simple evaluator (loss function)
def simple_evaluator(output, labels):
    loss = torch.tensor(0.5)
    return loss

# Create tiny validation loader: list of (patterns, labels) tuples
val_ldr = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([1, 2]))
]

# Create model
model = SimpleModel(input_dim=4, output_dim=3)

# Create evaluator
evaluator = simple_evaluator

# Create args object with device
class Args:
    def __init__(self):
        self.device = 'cpu'

args = Args()

# Create encoder
encoder = SimpleEncoder(nb_steps=2)

ARGS = {
    'val_ldr': val_ldr,
    'model': model,
    'evaluator': evaluator,
    'args': args,
    'encoder': encoder
}
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
runTrain Ran
ran, honoured the contract we drafted
Windere/snn-cvt-dual-phase/experiments/cifar10/main_ann.py
code served (permissive licence) · get_code("f94d67f2da5f3012")
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. 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

torch.manual_seed(0)

# Build a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Build a simple encoder
class SimpleEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

# Build args namespace
class Args:
    def __init__(self):
        self.device = 'cpu'
        self.log_interval = 1
        self.num_epoch = 2
        self.start_epoch = 1
        self.train_batch_size = 2

# Create data loader (list of batches)
train_data = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
]

class DataLoader:
    def __init__(self, data):
        self.data = data
        self.dataset = type('Dataset', (), {'__len__': lambda self: sum(len(batch[0]) for batch in train_data)})()
    
    def __iter__(self):
        return iter(self.data)
    
    def __len__(self):
        return len(self.data)

train_ldr = DataLoader(train_data)

# Create model, optimizer, evaluator
model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
evaluator = nn.CrossEntropyLoss()
encoder = SimpleEncoder()
args = Args()

ARGS = {
    'epoch': 1,
    'train_ldr': train_ldr,
    'optimizer': optimizer,
    'model': model,
    'evaluator': evaluator,
    'args': args,
    'encoder': encoder
}
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

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 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
accuracy 116 other papers
42 dated earlier, 1 the same month, 69 later, 4 same year, order not determinable · 8 only as an assembly brick
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1610.05820 (2016-10)
Membership Inference Attacks Against Machine Learning Models
1905.03696 (2019-05)
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
and 113 more not named here

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) operating with asynchronous discrete events show higher energy efficiency with sparse computation. A popular approach for implementing deep SNNs is ANN-SNN conversion combining both efficient training of ANNs and efficient inference of SNNs. However, the accuracy loss is usually non-negligible, especially under a few time steps, which restricts the applications of SNN on latency-sensitive edge devices greatly. In this paper, we first identify that such performance degradation stems from the misrepresentation of the negative or overflow residual membrane potential in SNNs. Inspired by this, we decompose the conversion error into three parts: quantization error, clipping error, and residual membrane potential representation error. With such insights, we propose a two-stage conversion algorithm to minimize those errors respectively. Besides, We show each stage achieves significant performance gains in a complementary manner. By evaluating on challenging datasets including CIFAR-10, CIFAR- 100 and ImageNet, the proposed method demonstrates the state-of-the-art performance in terms of accuracy, latency and energy preservation. Furthermore, our method is evaluated using a more challenging object detection task, revealing notable gains in regression performance under ultra-low latency when compared to existing spike-based detection algorithms. Codes are available at https://github.com/Windere/snn-cvt-dual-phase.

For agents

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

get_harvested_code_for_paper("2205.07473")
get_code_for_paper("2205.07473")
have("2205.07473")

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

curl https://syntology.ai/api/ran/2205.07473.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.07473.svg)](https://syntology.ai/paper/2205.07473)

Connect an agent — have() is free.