SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.03225 · 2021

Efficient Lottery Ticket Finding: Less Data is More

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 4 failures of our instrument; 7 no recorded run), measured 2026-11-21; 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/2106.03225.json · badge: /api/ran/2106.03225.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
VITA-Group/PrAC-LTH canonical (classifier label)
classifier basis: census
7 ran · 7 no recorded run
FunctionStatusWhere it lives
check_sparsity Ran
ran, honoured the contract we drafted
VITA-Group/PrAC-LTH/utils/pruner.py
code served (permissive licence) · get_code("092c59fab4392ba6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float, 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=8, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(in_channels=8, out_channels=16, kernel_size=3, padding=1)
        
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        return x

model = SimpleModel()

# Set some weights to zero to create sparsity
with torch.no_grad():
    model.conv1.weight[0:2, :, :, :] = 0
    model.conv2.weight[0:4, :, :, :] = 0

ARGS = {
    'model': model
}
Setup block drafted by
a language model, Claude Sonnet 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 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
VITA-Group/PrAC-LTH/models/resnet.py
code served (permissive licence) · get_code("d9def42110729a85")
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)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "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
VITA-Group/PrAC-LTH/models/resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
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
extract_mask Ran
ran; our contract draft was wrong, not the code
VITA-Group/PrAC-LTH/utils/pruner.py
code served (permissive licence) · get_code("cccbdd267d4f7850")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned dict. 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 copy

torch.manual_seed(0)

# Create a simple model dictionary that contains some parameters with 'mask' in the key
# and some without, to test the extraction functionality

model_dict = {
    'layer1.weight': torch.randn(4, 3),
    'layer1.bias': torch.randn(4),
    'layer1.mask': torch.ones(4, 3),
    'layer2.weight': torch.randn(5, 4),
    'layer2.mask': torch.zeros(5, 4),
    'output.weight': torch.randn(2, 5),
    'pruning_mask': torch.tensor([1, 0, 1, 0]),
    'batch_norm.running_mean': torch.randn(4),
}

ARGS = {
    'model_dict': model_dict
}
Setup block drafted by
a language model, Claude Sonnet 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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
make_layers Ran
ran; our contract draft was wrong, not the code
VITA-Group/PrAC-LTH/models/vgg.py
pointer only (licence: MIT); the stored copy get_code serves, from s-huu/TurningWeaknessIntoStrength, is pointer only (licence: NONE) · get_code("eba3f5bcc6a06d36")
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 s-huu/TurningWeaknessIntoStrength, 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.

reverse_mask Ran
ran on a synthesized input
VITA-Group/PrAC-LTH/utils/pruner.py
code served (permissive licence) · get_code("f79e6eaadbfc874c")
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 dict. 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 numpy as np

torch.manual_seed(0)

# Construct a mask_dict with numeric values (tensors or arrays)
# The function iterates over keys and computes 1 - mask_dict[key]
# This works with tensors, numpy arrays, or numeric types

mask_dict = {
    'layer1': torch.tensor([[0.0, 1.0], [0.5, 0.3]]),
    'layer2': torch.tensor([[1.0, 0.0], [0.8, 0.2]]),
    'layer3': np.array([0.0, 0.5, 1.0, 0.1])
}

ARGS = {
    'mask_dict': mask_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
tiny_imagenet_dataloaders Ran
ran on a synthesized input
VITA-Group/PrAC-LTH/dataset.py
code served (permissive licence) · get_code("08b70ee63cdd4e70")
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 os
import numpy as np
import tempfile
import shutil
from pathlib import Path
from PIL import Image

# Create a temporary directory structure that mimics tiny-imagenet-200
temp_dir = tempfile.mkdtemp()
data_dir = os.path.join(temp_dir, 'datasets', 'tiny-imagenet-200')
train_dir = os.path.join(data_dir, 'train')
val_dir = os.path.join(data_dir, 'val')

# Create directory structure
os.makedirs(train_dir, exist_ok=True)
os.makedirs(val_dir, exist_ok=True)

# Create dummy class directories and images for training set
for class_idx in range(3):
    class_dir = os.path.join(train_dir, f'class_{class_idx}')
    os.makedirs(class_dir, exist_ok=True)
    # Create 10 small dummy images per class
    for img_idx in range(10):
        img = Image.new('RGB', (64, 64), color=(73, 109, 137))
        img.save(os.path.join(class_dir, f'img_{img_idx}.jpg'))

# Create dummy class directories and images for validation set
for class_idx in range(3):
    class_dir = os.path.join(val_dir, f'class_{class_idx}')
    os.makedirs(class_dir, exist_ok=True)
    # Create 5 small dummy images per class
    for img_idx in range(5):
        img = Image.new('RGB', (64, 64), color=(73, 109, 137))
        img.save(os.path.join(class_dir, f'img_{img_idx}.jpg'))

# Create split file
npy_files_dir = os.path.join(temp_dir, 'npy_files')
os.makedirs(npy_files_dir, exist_ok=True)
split_file = os.path.join(npy_files_dir, 'tiny-imagenet-train-val.npy')
# Create a permutation array: 90000 for train, 10000 for val
split_permutation = np.random.permutation(100000)
np.save(split_file, split_permutation)

ARGS = {
    'batch_size': 4,
    'data_dir': data_dir,
    'dataset': False,
    'split_file': split_file,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — 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
accuracy Not yet run
unverified (harvested, no recorded run)
VITA-Group/PrAC-LTH/main_imp.py
code served (permissive licence) · get_code("f0c9a29156911331")
How it ran

no invocation recorded.

cifar100_dataloaders Not yet run
unverified (harvested, no recorded run)
VITA-Group/PrAC-LTH/dataset.py
code served (permissive licence) · get_code("0a0dbd36d312037d")
How it ran

no invocation recorded.

cifar10_dataloaders Not yet run
unverified (harvested, no recorded run)
VITA-Group/PrAC-LTH/dataset.py
code served (permissive licence) · get_code("92f75b060170e96e")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
VITA-Group/PrAC-LTH/main_imp.py
code served (permissive licence) · get_code("1e3f9a051b5a9b47")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
VITA-Group/PrAC-LTH/main_PrAC_imp.py
code served (permissive licence) · get_code("9e433381278f45b4")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
VITA-Group/PrAC-LTH/main_PrAC_imp.py
code served (permissive licence) · get_code("1b33d96e5ca7e277")
How it ran

no invocation recorded.

validate_PIE Not yet run
unverified (harvested, no recorded run)
VITA-Group/PrAC-LTH/main_PrAC_imp.py
code served (permissive licence) · get_code("a4adec80d8be98c2")
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, 8 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 8 later) and 6 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
132 dated earlier, 5 the same month, 288 later, 5 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
80 dated earlier, 2 the same month, 226 later, 3 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
accuracy 71 other papers
49 dated earlier, 1 the same month, 19 later, 2 same year, order not determinable · 2 only as an assembly brick
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1705.07204 (2017-05)
Ensemble Adversarial Training: Attacks and Defenses
1802.10399 (2018-02)
Compressing Neural Networks using the Variational Information Bottleneck
and 68 more not named here
make_layers 59 other papers
27 dated earlier, 32 later
1411.4038 (2014-11)
Fully Convolutional Networks for Semantic Segmentation
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1511.05950 (2015-11)
Staleness-aware Async-SGD for Distributed Deep Learning
and 56 more not named here
extract_mask 2 other papers
2 later
2206.04762 (2022-06)
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
2407.02068 (2024-07)
LPViT: Low-Power Semi-structured Pruning for Vision Transformers
train 2 other papers
2 later
2111.00162 (2021-11)
You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership
2202.04736 (2022-02)
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
validate 2 other papers
2 later
2111.00162 (2021-11)
You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership
2202.04736 (2022-02)
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
check_sparsity 1 other paper
1 later
2206.04762 (2022-06)
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training

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 2026-11-21.

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 lottery ticket hypothesis (LTH) reveals the existence of winning tickets (sparse but critical subnetworks) for dense networks, that can be trained in isolation from random initialization to match the latter's accuracies. However, finding winning tickets requires burdensome computations in the train-prune-retrain process, especially on large-scale datasets (e.g., ImageNet), restricting their practical benefits. This paper explores a new perspective on finding lottery tickets more efficiently, by doing so only with a specially selected subset of data, called Pruning-Aware Critical set (PrAC set), rather than using the full training set. The concept of PrAC set was inspired by the recent observation, that deep networks have samples that are either hard to memorize during training, or easy to forget during pruning. A PrAC set is thus hypothesized to capture those most challenging and informative examples for the dense model. We observe that a high-quality winning ticket can be found with training and pruning the dense network on the very compact PrAC set, which can substantially save training iterations for the ticket finding process. Extensive experiments validate our proposal across diverse datasets and network architectures. Specifically, on CIFAR-10, CIFAR-100, and Tiny ImageNet, we locate effective PrAC sets at 35.32%~78.19% of their training set sizes. On top of them, we can obtain the same competitive winning tickets for the corresponding dense networks, yet saving up to 82.85%~92.77%, 63.54%~74.92%, and 76.14%~86.56% training iterations, respectively. Crucially, we show that a PrAC set found is reusable across different network architectures, which can amortize the extra cost of finding PrAC sets, yielding a practical regime for efficient lottery ticket finding.

For agents

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

get_harvested_code_for_paper("2106.03225")
get_code_for_paper("2106.03225")
have("2106.03225")

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

curl https://syntology.ai/api/ran/2106.03225.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.03225.svg)](https://syntology.ai/paper/2106.03225)

Connect an agent — have() is free.