Björn Nieth, Thomas Altstidl, Leo Schwinn, Björn Eskofier
7 of 9 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; 7 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/2406.13283.json · badge: /api/ran/2406.13283.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.
| Repository | Role | Ran |
|---|---|---|
| BjoernNieth/LS-Dataset-pruning-in-AT | canonical (classifier label) classifier basis: census |
7 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| calc_l2distsq | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
BjoernNieth/LS-Dataset-pruning-in-AT/core/attacks/utils.py pointer only (licence: NONE) · get_code("6d57c3097e379953") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
| perturb_deepfool | Ran ran; our contract draft was wrong, not the code |
BjoernNieth/LS-Dataset-pruning-in-AT/core/attacks/deepfool.py pointer only (licence: NONE) · get_code("8a6e2e06ca96fb3c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
| preact_resnet | Ran ran; our contract draft was wrong, not the code |
BjoernNieth/LS-Dataset-pruning-in-AT/core/models/preact_resnet.py pointer only (licence: NONE) · get_code("a99efdab28da25d8") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
| replicate_input | Ran ran; our contract draft was wrong, not the code |
BjoernNieth/LS-Dataset-pruning-in-AT/core/attacks/utils.py pointer only (licence: NONE) · get_code("096e065144e00e11") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
| replicate_input_withgrad | Ran ran; our contract draft was wrong, not the code |
BjoernNieth/LS-Dataset-pruning-in-AT/core/attacks/utils.py pointer only (licence: NONE) · get_code("706e45721616b050") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
| resnet | Ran ran; our contract draft was wrong, not the code |
BjoernNieth/LS-Dataset-pruning-in-AT/core/models/resnet.py pointer only (licence: NONE) · get_code("faacf3bc6eae58ae") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
| ti_preact_resnet | Ran ran; our contract draft was wrong, not the code |
BjoernNieth/LS-Dataset-pruning-in-AT/core/models/ti_preact_resnet.py pointer only (licence: NONE) · get_code("b83aa0df4382b430") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
| perturb_iterative | Not yet run unverified (harvested, no recorded run) |
BjoernNieth/LS-Dataset-pruning-in-AT/core/attacks/pgd.py pointer only (licence: NONE) · get_code("ec5326fd666c5823") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
| preact_resnetwithswish | Not yet run unverified (harvested, no recorded run) |
BjoernNieth/LS-Dataset-pruning-in-AT/core/models/preact_resnetwithswish.py pointer only (licence: NONE) · get_code("6dfdd3eb06e12783") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, BjoernNieth/LS-Dataset-pruning-in-AT 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. |
Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 6 later) and 2 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| replicate_input | 4 other papers 3 dated earlier, 1 later |
2110.09468 (2021-10) Improving Robustness using Generated Data |
2302.03015 (2023-02) Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness 2405.16260 (2024-05) Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination and 1 more not named here |
| calc_l2distsq | 3 other papers 2 dated earlier, 1 later |
2110.09468 (2021-10) Improving Robustness using Generated Data |
2405.16260 (2024-05) Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination 2606.02267 (2026-06) A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs |
| perturb_deepfool | 3 other papers 1 dated earlier, 2 later |
2110.09468 (2021-10) Improving Robustness using Generated Data |
2606.00738 (2026-06) SORA: Free Second-Order Attacks in Fast Adversarial Training 2606.02267 (2026-06) A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs |
| preact_resnet | 3 other papers 2 dated earlier, 1 later |
2110.09468 (2021-10) Improving Robustness using Generated Data |
2310.07931 (2023-10) D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning 2606.02267 (2026-06) A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs |
| replicate_input_withgrad | 3 other papers 2 dated earlier, 1 later |
2110.09468 (2021-10) Improving Robustness using Generated Data |
2405.16260 (2024-05) Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination 2606.02267 (2026-06) A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs |
| perturb_iterative | 2 other papers 1 dated earlier, 1 later |
2110.09468 (2021-10) Improving Robustness using Generated Data |
2606.02267 (2026-06) A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs |
| ti_preact_resnet | 1 other paper 1 dated earlier |
2403.10073 (2024-03) Revisiting Adversarial Training under Long-Tailed Distributions |
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to realworld systems. Adversarial training has proven to be one of the most promising strategies against these attacks, at the expense of a substantial increase in training time. With the ongoing trend of integrating large-scale synthetic data this is only expected to increase even further. Thus, the need for data-centric approaches that reduce the number of training samples while maintaining accuracy and robustness arises. While data pruning and active learning are prominent research topics in deep learning, they are as of now largely unexplored in the adversarial training literature. We address this gap and propose a new data pruning strategy based on extrapolating data importance scores from a small set of data to a larger set. In an empirical evaluation, we demonstrate that extrapolation-based pruning can efficiently reduce dataset size while maintaining robustness.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.13283")
get_code_for_paper("2406.13283")
have("2406.13283")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.13283.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.13283)
Connect an agent — have() is free.