SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.02507 · 2023

Stimulative Training++: Go Beyond The Performance Limits of Residual Networks

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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 1 has no contract verdict; 6 failures of our instrument; 2 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/2305.02507.json · badge: /api/ran/2305.02507.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
sunshine-ye/nips22-st canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
CutoutDefault Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sunshine-ye/nips22-st/aug_lib.py
pointer only (licence: MIT); the stored copy get_code serves, from jackbrocp/entaugment, is pointer only (licence: NONE) · get_code("e4c841a535ce14d5")
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 jackbrocp/entaugment, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
sunshine-ye/nips22-st/models/pyramidnet_randwidth.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
sunshine-ye/nips22-st/models/resnet_randdepth.py
pointer only (licence: MIT); the stored copy get_code serves, from chenxiangma/auglocal, is pointer only (licence: NONE) · get_code("6af95ebe99af2e36")
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 chenxiangma/auglocal, 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.

get_logger Ran
ran on a synthesized input
sunshine-ye/nips22-st/utils/setlogger.py
code served (permissive licence) · get_code("84a10f5778846b16")
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 Logger. 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 logging
import tempfile
import os

# Create a temporary file path for the logger
temp_dir = tempfile.gettempdir()
log_file_path = os.path.join(temp_dir, "test_logger.log")

ARGS = {
    "file_path": log_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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_divisible Ran
ran, honoured the contract we drafted
sunshine-ye/nips22-st/models/randwidth_ops.py
code served (permissive licence) · get_code("012a56f3a60ed47b")
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 int, ndim 0, dtype family int, 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 numpy as np

# Analyze the function: make_divisible(v, divisor=1, min_value=1)
# The function takes:
# - v: a numeric value (int or float)
# - divisor: a numeric value (default 1)
# - min_value: a numeric value or None (default 1)
# It performs arithmetic operations and returns a numeric value

# Construct test arguments
v = 17
divisor = 8
min_value = 4

ARGS = {
    "v": v,
    "divisor": divisor,
    "min_value": min_value
}
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 int, ndim 0, dtype family int, 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
mixup_target Ran
ran; our contract draft was wrong, not the code
sunshine-ye/nips22-st/mixup.py
pointer only (licence: MIT); the stored copy get_code serves, from terrypei/efficientvmamba, is pointer only (licence: NONE) · get_code("8733e0d87f232d11")
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 terrypei/efficientvmamba, 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.

one_hot Ran
ran; our contract draft was wrong, not the code
sunshine-ye/nips22-st/mixup.py
code served (permissive licence) · get_code("4728dc2025227bba")
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. 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

torch.manual_seed(0)

# Create a small input tensor with class indices
# Shape: (2,) - batch of 2 samples with class indices
x = torch.tensor([0, 2], dtype=torch.long)

# Number of classes
num_classes = 4

# On value for one-hot encoding
on_value = 1.0

# Off value for one-hot encoding
off_value = 0.0

# Device - use CPU only
device = 'cpu'

ARGS = {
    'x': x,
    'num_classes': num_classes,
    'on_value': on_value,
    'off_value': off_value,
    '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 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
rand_bbox Ran
ran; our contract draft was wrong, not the code
sunshine-ye/nips22-st/mixup.py
pointer only (licence: MIT); the stored copy get_code serves, from terrypei/efficientvmamba, is pointer only (licence: NONE) · get_code("3913c620f6926f42")
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 terrypei/efficientvmamba, 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.

float_parameter Not yet run
unverified (harvested, no recorded run)
sunshine-ye/nips22-st/aug_lib.py
pointer only (licence: MIT); the stored copy get_code serves, from jackbrocp/entaugment, is pointer only (licence: NONE) · get_code("3434fff9b5d4912e")
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 jackbrocp/entaugment, 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. No invocation recorded.

int_parameter Not yet run
unverified (harvested, no recorded run)
sunshine-ye/nips22-st/aug_lib.py
pointer only (licence: MIT); the stored copy get_code serves, from jackbrocp/entaugment, is pointer only (licence: NONE) · get_code("b3a390f777b2388c")
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 jackbrocp/entaugment, 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. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 8 later) and 0 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
conv3x3 686 other papers
476 dated earlier, 5 the same month, 198 later, 7 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
float_parameter 15 other papers
12 dated earlier, 3 later
1409.4842 (2014-09)
Going deeper with convolutions
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
and 12 more not named here
rand_bbox 14 other papers
7 dated earlier, 7 later
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
2206.13559 (2022-06)
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
and 11 more not named here
one_hot 12 other papers
6 dated earlier, 6 later · 1 only as an assembly brick
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2212.00776 (2022-12)
ResFormer: Scaling ViTs with Multi-Resolution Training
and 9 more not named here
int_parameter 8 other papers
7 dated earlier, 1 later
1409.4842 (2014-09)
Going deeper with convolutions
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
and 5 more not named here
mixup_target 7 other papers
3 dated earlier, 4 later
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2212.00776 (2022-12)
ResFormer: Scaling ViTs with Multi-Resolution Training
2301.03580 (2023-01)
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
and 4 more not named here
make_divisible 3 other papers
1 dated earlier, 2 later
2006.07989 (2020-06)
GradAug: A New Regularization Method for Deep Neural Networks
2308.13772 (2023-08)
Boosting Residual Networks with Group Knowledge
aaai_28322 (2024 (year only))
Boosting Residual Networks with Group Knowledge
CutoutDefault 2 other papers
1 dated earlier, 1 later
2210.03501 (2022-10)
Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement
2409.06290 (2024-09)
EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification
get_logger 2 other papers
2 dated earlier
2006.07989 (2020-06)
GradAug: A New Regularization Method for Deep Neural Networks
2105.07085 (2021-05)
MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations

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

Residual networks have shown great success and become indispensable in recent deep neural network models. In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of loafing, and further propose a new training scheme as well as three improved strategies for boosting residual networks beyond their performance limits. Previous research has suggested that residual networks can be considered as ensembles of shallow networks, which implies that the final performance of a residual network is influenced by a group of subnetworks. We identify a previously overlooked problem that is analogous to social loafing, where subnetworks within a residual network are prone to exert less effort when working as part of a group compared to working alone. We define this problem as \textit{network loafing}. Similar to the decreased individual productivity and overall performance as demonstrated in society, network loafing inevitably causes sub-par performance. Inspired by solutions from social psychology, we first propose a novel training scheme called stimulative training, which randomly samples a residual subnetwork and calculates the KL divergence loss between the sampled subnetwork and the given residual network for extra supervision. In order to unleash the potential of stimulative training, we further propose three simple-yet-effective strategies, including a novel KL- loss that only aligns the network logits direction, random smaller inputs for subnetworks, and inter-stage sampling rules. Comprehensive experiments and analysis verify the effectiveness of stimulative training as well as its three improved strategies.

For agents

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

get_harvested_code_for_paper("2305.02507")
get_code_for_paper("2305.02507")
have("2305.02507")

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

curl https://syntology.ai/api/ran/2305.02507.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.02507.svg)](https://syntology.ai/paper/2305.02507)

Connect an agent — have() is free.