SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.01697 · 2018

Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 3 have no contract verdict; 2 failures of our instrument; 0 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/1807.01697.json · badge: /api/ran/1807.01697.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
neurai-lab/dsp community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
block_function_factory Ran
ran on a synthesized input
neurai-lab/dsp/DSP/DR-TANet-main/TANet_element.py
code served (permissive licence) · get_code("651c85f287f59252")
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 function. 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)

# Create a small convolutional layer
conv = nn.Conv2d(in_channels=3, out_channels=4, kernel_size=3, padding=1)

# Create a batch normalization layer
norm = nn.BatchNorm2d(num_features=4)

# Create a ReLU activation
relu = nn.ReLU()

ARGS = {
    'conv': conv,
    'norm': norm,
    'relu': relu
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
check_validness Ran
ran on a synthesized input
neurai-lab/dsp/DSP/DR-TANet-main/datasets.py
code served (permissive licence) · get_code("97d8813396422bcc")
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 bool, 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 numpy as np
from os.path import join as pjoin, splitext as spt

def check_validness(f):
    return any([i in spt(f)[1] for i in ['jpg', 'png']])

# The function takes a single parameter 'f' which is a file path string
# It uses spt() to split the filename and extension, then checks if 'jpg' or 'png' is in the extension
# We need to provide a valid file path string as argument

ARGS = {
    'f': 'image.jpg'
}
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 bool, 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
clipped_zoom Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from bethgelab/imagecorruptions
pointer only · get_code("9f1bb16740f8d1ed")
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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
neurai-lab/dsp/DSP/DR-TANet-main/TANet_element.py
pointer only (licence: MIT); the stored copy get_code serves, from xiamenwcy/pictorial_net, is pointer only (licence: NONE) · get_code("18fbe72ffac82ee3")
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 xiamenwcy/pictorial_net, 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.

do_efficient_fwd Ran
ran on a synthesized input
neurai-lab/dsp/DSP/DR-TANet-main/TANet_element.py
code served (permissive licence) · get_code("a42696f08aaf3a09")
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, 3) 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
import torch.utils.checkpoint as cp

torch.manual_seed(0)

# Define a simple block function (nn.Module)
class SimpleBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create instances
block_f = SimpleBlock()

# Create a small tensor with requires_grad=True for checkpoint to work
x = torch.randn(2, 4, requires_grad=True)

# efficient flag
efficient = True

ARGS = {
    "block_f": block_f,
    "x": x,
    "efficient": efficient,
}
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, 3) — shape (2, 3) 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
plasma_fractal Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from bethgelab/imagecorruptions
pointer only · get_code("33492980f6e79af5")
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.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 3 later) and 3 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 15 other papers
2 dated earlier, 1 the same month, 12 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1805.04635 (2018-05)
Direction-aware Spatial Context Features for Shadow Detection and Removal
1807.10002 (2018-07)
Deep Pictorial Gaze Estimation
and 12 more not named here
clipped_zoom 2 other papers
2 later
1907.07484 (2019-07)
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
2606.16996 (2026-06)
ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation
plasma_fractal 1 other paper
1 later
1907.07484 (2019-07)
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming

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

In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performance on commonplace corruptions not worst-case adversarial corruptions. We find that there are negligible changes in relative corruption robustness from AlexNet to ResNet classifiers, and we discover ways to enhance corruption robustness. Then we propose a new dataset called Icons-50 which opens research on a new kind of robustness, surface variation robustness. With this dataset we evaluate the frailty of classifiers on new styles of known objects and unexpected instances of known classes. We also demonstrate two methods that improve surface variation robustness. Together our benchmarks may aid future work toward networks that learn fundamental class structure and also robustly generalize.

For agents

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

get_harvested_code_for_paper("1807.01697")
get_code_for_paper("1807.01697")
have("1807.01697")

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

curl https://syntology.ai/api/ran/1807.01697.json

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

[![Syntology run record](https://syntology.ai/api/ran/1807.01697.svg)](https://syntology.ai/paper/1807.01697)

Connect an agent — have() is free.