SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.05211 · 2021

RobustART: Benchmarking Robustness on Architecture Design and Training Techniques

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 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/2109.05211.json · badge: /api/ran/2109.05211.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
DIG-Beihang/RobustART community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
aurra Ran
ran, honoured the contract we drafted
DIG-Beihang/RobustART/RobustART/metrics/calibration_tools.py
code served (permissive licence) · get_code("e0a2af598b5ea528")
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 float64, ndim 0, 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 numpy as np

# The function aurra takes two parameters:
# - confidence: array-like of confidence scores, used with np.argsort
# - correct: array-like of boolean/binary correctness labels, indexed by confidence ranks

# Create small test data
confidence = np.array([0.9, 0.7, 0.85, 0.6, 0.95])
correct = np.array([1, 0, 1, 1, 0])

ARGS = {
    "confidence": confidence,
    "correct": correct
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
calib_err Ran
ran on a synthesized input
DIG-Beihang/RobustART/RobustART/metrics/calibration_tools.py
code served (permissive licence) · get_code("509aa629e46cf950")
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 float32, 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 numpy as np

# Create small test data for calibration error calculation
np.random.seed(0)

# Generate confidence scores (should be between 0 and 1)
confidence = np.array([0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0.95], dtype=np.float32)

# Generate correctness labels (binary: 0 or 1)
correct = np.array([1, 1, 0, 1, 0, 0, 1, 0, 1, 1], dtype=np.float32)

# Define arguments
ARGS = {
    'confidence': confidence,
    'correct': correct,
    'p': '2',
    'beta': 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float32, 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
stable_cumsum Ran
ran, honoured the contract we drafted
DIG-Beihang/RobustART/RobustART/metrics/calibration_tools.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from fanghenshaometeor/ood-kernel-pca-ext, is pointer only (licence: NONE) · get_code("d4acb3120a027622")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from fanghenshaometeor/ood-kernel-pca-ext, 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.

add_noise_for_imagenet_s Not yet run
unverified (harvested, no recorded run)
DIG-Beihang/RobustART/RobustART/noise/utils/add_noise_utils.py
code served (permissive licence) · get_code("e0ffcf377c862618")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
stable_cumsum 29 other papers
5 dated earlier, 24 later · 1 only as an assembly brick
1911.11132 (2019-11)
Scaling Out-of-Distribution Detection for Real-World Settings
2003.08440 (2020-03)
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
2104.08812 (2021-04)
Contrastive Out-of-Distribution Detection for Pretrained Transformers
and 26 more not named here
calib_err 4 other papers
2 dated earlier, 2 later
1907.07174 (2019-07)
Natural Adversarial Examples
2105.07581 (2021-05)
Vision Transformers are Robust Learners
aaai_20752 (2022 (year only))
Provable Guarantees for Understanding Out-of-Distribution Detection
and 1 more not named here
aurra 2 other papers
2 dated earlier
1907.07174 (2019-07)
Natural Adversarial Examples
2105.07581 (2021-05)
Vision Transformers are Robust Learners

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

Deep neural networks (DNNs) are vulnerable to adversarial noises, which motivates the benchmark of model robustness. Existing benchmarks mainly focus on evaluating defenses, but there are no comprehensive studies of how architecture design and training techniques affect robustness. Comprehensively benchmarking their relationships is beneficial for better understanding and developing robust DNNs. Thus, we propose RobustART, the first comprehensive Robustness investigation benchmark on ImageNet regarding ARchitecture design (49 human-designed off-the-shelf architectures and 1200+ networks from neural architecture search) and Training techniques (10+ techniques, e.g., data augmentation) towards diverse noises (adversarial, natural, and system noises). Extensive experiments substantiated several insights for the first time, e.g., (1) adversarial training is effective for the robustness against all noises types for Transformers and MLP-Mixers; (2) given comparable model sizes and aligned training settings, CNNs > Transformers > MLP-Mixers on robustness against natural and system noises; Transformers > MLP-Mixers > CNNs on adversarial robustness; (3) for some light-weight architectures, increasing model sizes or using extra data cannot improve robustness. Our benchmark presents: (1) an open-source platform for comprehensive robustness evaluation; (2) a variety of pre-trained models to facilitate robustness evaluation; and (3) a new view to better understand the mechanism towards designing robust DNNs. We will continuously develop to this ecosystem for the community.

For agents

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

get_harvested_code_for_paper("2109.05211")
get_code_for_paper("2109.05211")
have("2109.05211")

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

curl https://syntology.ai/api/ran/2109.05211.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.05211.svg)](https://syntology.ai/paper/2109.05211)

Connect an agent — have() is free.