Home › Code › perturb

perturb

Syntologyentry name in harvested coderead from the graph 2026-09-24

perturb appears in the code Syntology harvested for 20 papers, as 18 distinct code bodies found in 20 places (a place is one code body under one paper). At least one of them ran in 9 of the papers; 3 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named perturb do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 8 of the 18 distinct code bodies named perturb; 10 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
0ran · violated contract
2ran · our draft was wrong
2ran · fixture could not drive it
3ran
10unverified
3fingerprinted

Licence is a property of each copy, so it is counted per place: 8 of the 20 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

20 papers shown of 20, newest first; 20 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 1 papers added by Syntology; 1 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
The Ensemble Inverse Problem: Applications and Methods added by Syntology 2026-01 (from id) ZhengyanHuan/The-Ensemble-Inverse-Problem--Applications-and-Methods/Sec3p2/dataset.py f88ebac879b99202 unverified no licence file found · pointer only
One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models 4 Mar 2024 TreeLLi/APT/apt/evaluate.py c2be82a99f878e8c ran MIT (permissive)
Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization 18 Dec 2023 bupt-gamma/igm/IGM_code/dataset_gen/BA3_loc.py 425d3f16a4164e4c ran no licence file found · pointer only
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization 30 Oct 2023 XuGW-Kevin/DrM/agents/drm.py 4a4ae05c66dd350a ran MIT (permissive)
Geometry-enhanced Pre-training on Interatomic Potentials 2023-09 (from id) cuitaoyong/gpip/pretraining.py f4e22a0a3a8ec839 ran · our draft was wrong fingerprinted no licence file found · pointer only
AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation 12 Jun 2023 treelli/aroid/src/utils/adversary.py 2ed1c4f9595c38a6 unverified MIT (permissive)
SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples 13 May 2023 deqingfu/scene/perturb.py 82507651b361aacb unverified no licence file found · pointer only
Data Augmentation Alone Can Improve Adversarial Training 24 Jan 2023 treelli/da-alone-improves-at/src/utils/adversary.py c4ff8c6f13f39bc5 unverified MIT (permissive)
Learning sparse features can lead to overfitting in neural networks 24 Jun 2022 pcsl-epfl/regressionsphere/stability.py d9794cc8e3c1bcb9 unverified MIT (permissive)
GraphSVX: Shapley Value Explanations for Graph Neural Networks 18 Apr 2021 AlexDuvalinho/GraphSVX/src/gengraph.py 25b882d4de9cd6bd unverified MIT (permissive)
Encoding Robustness to Image Style via Adversarial Feature Perturbations 18 Sep 2020 azshue/advbn/train_imagenet.py 9fe44f1273732195 unverified no licence file found · pointer only
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder 6 Mar 2020 XavierXiao/Likelihood-Regret/train_pixel.py 356aef4a4b74b441 ran · our draft was wrong MIT (permissive)
End-to-End Pixel-Based Deep Active Inference for Body Perception and Action 28 Dec 2019 cansu97/PixelAI/Benchmark_Perceptual_Offline/run_benchmark.py 4449023f158b9935 ran · honoured contract no licence file found · pointer only
Goal-conditioned Imitation Learning 13 Jun 2019 dingyiming0427/goalgail/baselines/her/her.py 2924888d72c2c274 ran · fixture could not drive it fingerprinted no licence file found · pointer only
On the Robustness of Deep K-Nearest Neighbors 20 Mar 2019 identical code first harvested elsewhere 79c0d47a0e121164 ran · fixture could not drive it fingerprinted licence of this copy not recorded
GNNExplainer: Generating Explanations for Graph Neural Networks 10 Mar 2019 RexYing/gnn-model-explainer/gengraph.py 11e1d48886273577 unverified Apache-2.0 (permissive)
Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks 30 Sep 2018 kenny-co/procedural-advml/utils_attack.py eb58662c9956c611 unverified MIT (permissive)
Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning 13 Mar 2018 fiona-lxd/AdvKnn/attack.py 79c0d47a0e121164 ran · fixture could not drive it fingerprinted MIT (permissive)
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models 24 Feb 2018 snap-stanford/GraphRNN/utils.py 8f7d2c1aa425efe6 unverified MIT (permissive)
arXiv:aaai_29648 haibin65535/ICL/gengraph.py 11e1d48886273577 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections