SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.09635 · 2021

Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 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/2111.09635.json · badge: /api/ran/2111.09635.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
nota-github/autobot_aaai23 canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_args Ran
ran; our contract draft was wrong, not the code
nota-github/autobot_aaai23/utils/parser.py
code served (permissive licence) · get_code("5ee893000f6773c7")
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 Namespace. 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
import sys
import os
import tempfile

torch.manual_seed(0)

# Create temporary directories for the test
temp_dir = tempfile.mkdtemp()
output_dir = os.path.join(temp_dir, 'result', 'test')
checkpoint_dir = os.path.join(temp_dir, 'checkpoints')
os.makedirs(output_dir, exist_ok=True)
os.makedirs(os.path.join(checkpoint_dir, 'cifar10'), exist_ok=True)

# Create a dummy model file
dummy_model_path = os.path.join(checkpoint_dir, 'cifar10', 'resnet_56.pt')
torch.save({'state_dict': {}}, dummy_model_path)

# Create data directories
data_dir = os.path.join(temp_dir, 'data', 'cifar10')
os.makedirs(data_dir, exist_ok=True)

ARGS = {
    'args': [
        '--output_dir', output_dir,
        '--loaded_model_path', checkpoint_dir,
        '--batch_size', '64',
        '--nb_batches', '200',
        '--lr', '0.6',
        '--momentum', '0.9',
        '--beta', '6',
        '--gamma', '0.4',
        '--gpu', '0',
        '--num_workers', '4',
        '--dataset', 'cifar10',
        '--arch', 'resnet_56',
        '--seed', '1',
        '--lr_finetuning', '0.02',
        '--epoch_finetuning', '200',
        '--wd', '0.002',
    ]
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Neural networks performance has been significantly improved in the last few years, at the cost of an increasing number of floating point operations per second (FLOPs). However, more FLOPs can be an issue when computational resources are limited. As an attempt to solve this problem, pruning filters is a common solution, but most existing pruning methods do not preserve the model accuracy efficiently and therefore require a large number of finetuning epochs. In this paper, we propose an automatic pruning method that learns which neurons to preserve in order to maintain the model accuracy while reducing the FLOPs to a predefined target. To accomplish this task, we introduce a trainable bottleneck that only requires one single epoch with 25.6% (CIFAR-10) or 7.49% (ILSVRC2012) of the dataset to learn which filters to prune. Experiments on various architectures and datasets show that the proposed method can not only preserve the accuracy after pruning but also outperform existing methods after finetuning. We achieve a 52.00% FLOPs reduction on ResNet-50, with a Top-1 accuracy of 47.51% after pruning and a state-of-the-art (SOTA) accuracy of 76.63% after finetuning on ILSVRC2012. Code available at https://github.com/nota-github/autobot_AAAI23.

For agents

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

get_harvested_code_for_paper("2111.09635")
get_code_for_paper("2111.09635")
have("2111.09635")

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

curl https://syntology.ai/api/ran/2111.09635.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.09635.svg)](https://syntology.ai/paper/2111.09635)

Connect an agent — have() is free.