SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.03044 · 2023

REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 4 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/2312.03044.json · badge: /api/ran/2312.03044.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
zhao1402072392/rest canonical (classifier label)
classifier basis: census
13 ran · 4 no recorded run
FunctionStatusWhere it lives
ResNet18 Ran
ran; our contract draft was wrong, not the code
zhao1402072392/rest/sparselearning/models.py
pointer only (licence: NONE) · get_code("0b98222d60088756")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

ResNet34 Ran
ran; our contract draft was wrong, not the code
zhao1402072392/rest/sparselearning/models.py
pointer only (licence: NONE) · get_code("69f1881e9527c23c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

ResNet50 Ran
ran; our contract draft was wrong, not the code
zhao1402072392/rest/sparselearning/models.py
pointer only (licence: NONE) · get_code("a44b24a44c793daa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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
zhao1402072392/rest/extractable_resnet.py
pointer only (licence: NONE) · get_code("d9def42110729a85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
zhao1402072392/rest/extractable_resnet.py
pointer only (licence: NONE) · get_code("160bb14bd76201b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

count_model_param_flops Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhao1402072392/rest/flops.py
pointer only (licence: NONE) · get_code("1c6dbb2f211c7f04")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

get_acc Ran
ran, honoured the contract we drafted
zhao1402072392/rest/chart.py
pointer only (licence: NONE) · get_code("a9c02346cafc6306")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

get_acc_list Ran
ran; our contract draft was wrong, not the code
zhao1402072392/rest/chart.py
pointer only (licence: NONE) · get_code("142a262930515741")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

get_accs_for_epoch_across_batches Ran
ran; our contract draft was wrong, not the code
zhao1402072392/rest/analysis_utils.py
pointer only (licence: NONE) · get_code("381380e09fd105f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

get_projections Ran
ran, honoured the contract we drafted
zhao1402072392/rest/random_feature_utils.py
pointer only (licence: NONE) · get_code("9d1aed5c27329c07")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

get_random_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhao1402072392/rest/random_feature_utils.py
pointer only (licence: NONE) · get_code("6bee5175f6c9e4a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

sample_from_sphere Ran
ran, honoured the contract we drafted
zhao1402072392/rest/random_feature_utils.py
pointer only (licence: NONE) · get_code("0a57f8c6ed773a07")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

sanitize_df Ran
ran; our contract draft was wrong, not the code
zhao1402072392/rest/analysis_utils.py
pointer only (licence: NONE) · get_code("8a66892616008c7f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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.

get_all_csv Not yet run
unverified (harvested, no recorded run)
zhao1402072392/rest/chart.py
pointer only (licence: NONE) · get_code("38b084886804dc24")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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. No invocation recorded.

load_log Not yet run
unverified (harvested, no recorded run)
zhao1402072392/rest/analysis_utils.py
pointer only (licence: NONE) · get_code("10e220982fed5f01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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. No invocation recorded.

resnet10vw Not yet run
unverified (harvested, no recorded run)
zhao1402072392/rest/variable_width_resnet.py
pointer only (licence: NONE) · get_code("bed7fe4dae1cc07a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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. No invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
zhao1402072392/rest/extractable_resnet.py
pointer only (licence: NONE) · get_code("3c5da610f0879a76")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhao1402072392/rest 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. No invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 11 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 3 the same month, 9 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
297 dated earlier, 7 the same month, 118 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
198 dated earlier, 8 the same month, 98 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
resnet18 95 other papers
56 dated earlier, 1 the same month, 36 later, 1 same year, order not determinable, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
get_accs_for_epoch_across_batches 4 other papers
2 dated earlier, 2 later
2306.11074 (2023-06)
Simple and Fast Group Robustness by Automatic Feature Reweighting
2310.06161 (2023-10)
Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness
2510.02818 (2025-10)
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
and 1 more not named here
load_log 4 other papers
2 dated earlier, 2 later
2306.11074 (2023-06)
Simple and Fast Group Robustness by Automatic Feature Reweighting
2310.06161 (2023-10)
Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness
2510.02818 (2025-10)
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
and 1 more not named here
sanitize_df 4 other papers
2 dated earlier, 2 later
2306.11074 (2023-06)
Simple and Fast Group Robustness by Automatic Feature Reweighting
2310.06161 (2023-10)
Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness
2510.02818 (2025-10)
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
and 1 more not named here
ResNet34 1 other paper
1 dated earlier
2308.14831 (2023-08)
Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates
get_projections 1 other paper
1 later
2401.14846 (2024-01)
Understanding Domain Generalization: A Noise Robustness Perspective
get_random_features 1 other paper
1 later
2401.14846 (2024-01)
Understanding Domain Generalization: A Noise Robustness Perspective
resnet10vw 1 other paper
1 dated earlier
2104.00170 (2021-04)
Are Bias Mitigation Techniques for Deep Learning Effective?
sample_from_sphere 1 other paper
1 later
2401.14846 (2024-01)
Understanding Domain Generalization: A Noise Robustness Perspective

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 deep neural network (DNN) has been proven effective in various domains. However, they often struggle to perform well on certain minority groups during inference, despite showing strong performance on the majority of data groups. This is because over-parameterized models learned \textit{bias attributes} from a large number of \textit{bias-aligned} training samples. These bias attributes are strongly spuriously correlated with the target variable, causing the models to be biased towards spurious correlations (i.e., \textit{bias-conflicting}). To tackle this issue, we propose a novel \textbf{re}weighted \textbf{s}parse \textbf{t}raining framework, dubbed as \textit{\textbf{REST}}, which aims to enhance the performance of biased data while improving computation and memory efficiency. Our proposed REST framework has been experimentally validated on three datasets, demonstrating its effectiveness in exploring unbiased subnetworks. We found that REST reduces the reliance on spuriously correlated features, leading to better performance across a wider range of data groups with fewer training and inference resources. We highlight that the \textit{REST} framework represents a promising approach for improving the performance of DNNs on biased data, while simultaneously improving computation and memory efficiency. By reducing the reliance on spurious correlations, REST has the potential to enhance the robustness of DNNs and improve their generalization capabilities. Code is released at \url{https://github.com/zhao1402072392/REST}

For agents

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

get_harvested_code_for_paper("2312.03044")
get_code_for_paper("2312.03044")
have("2312.03044")

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

curl https://syntology.ai/api/ran/2312.03044.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.03044.svg)](https://syntology.ai/paper/2312.03044)

Connect an agent — have() is free.