SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.02078 · 2021

Improving Neural Network Robustness via Persistency of Excitation

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2106.02078.json · badge: /api/ran/2106.02078.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
kaustubhsridhar/PoE-robustness canonical (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
add_args_to_parser Ran
ran; our contract draft was wrong, not the code
kaustubhsridhar/PoE-robustness/adversarial-training/PGD-AT/robustness/defaults.py
code served (permissive licence) · get_code("078da01e51a28471")
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 ArgumentParser. 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 argparse

ARGS = {
    'arg_list': [
        ['learning_rate', float, 'Learning rate for optimization', 0.001],
        ['batch_size', int, 'Batch size for training', 32],
        ['model_type', ['lstm', 'gru', 'transformer'], 'Type of model to use', 'lstm'],
        ['epochs', int, 'Number of training epochs', 10],
        ['optimizer', ['adam', 'sgd'], 'Optimizer to use', 'adam'],
    ],
    'parser': argparse.ArgumentParser(description='Test parser'),
}
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 ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser 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
model_dataset_from_store Not yet run
unverified (harvested, no recorded run)
kaustubhsridhar/PoE-robustness/adversarial-training/PGD-AT/robustness/model_utils.py
code served (permissive licence) · get_code("c1e41af537b4027c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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
model_dataset_from_store 4 other papers
4 later
2305.14846 (2023-05)
Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup
2305.19101 (2023-05)
Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
2405.08886 (2024-05)
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
and 1 more not named here
add_args_to_parser 3 other papers
3 later
2305.19101 (2023-05)
Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
2306.00183 (2023-06)
Diffused Redundancy in Pre-trained Representations
2308.06887 (2023-08)
Robustified ANNs Reveal Wormholes Between Human Category Percepts

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

Improving adversarial robustness of neural networks remains a major challenge. Fundamentally, training a neural network via gradient descent is a parameter estimation problem. In adaptive control, maintaining persistency of excitation (PoE) is integral to ensuring convergence of parameter estimates in dynamical systems to their true values. We show that parameter estimation with gradient descent can be modeled as a sampling of an adaptive linear time-varying continuous system. Leveraging this model, and with inspiration from Model-Reference Adaptive Control (MRAC), we prove a sufficient condition to constrain gradient descent updates to reference persistently excited trajectories converging to the true parameters. The sufficient condition is achieved when the learning rate is less than the inverse of the Lipschitz constant of the gradient of loss function. We provide an efficient technique for estimating the corresponding Lipschitz constant in practice using extreme value theory. Our experimental results in both standard and adversarial training illustrate that networks trained with the PoE-motivated learning rate schedule have similar clean accuracy but are significantly more robust to adversarial attacks than models trained using current state-of-the-art heuristics.

For agents

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

get_harvested_code_for_paper("2106.02078")
get_code_for_paper("2106.02078")
have("2106.02078")

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

curl https://syntology.ai/api/ran/2106.02078.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.02078.svg)](https://syntology.ai/paper/2106.02078)

Connect an agent — have() is free.