Qian Wang, Ningping Mou, Xinli Yue, Lingchen Zhao
5 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 0 have no contract verdict; 4 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/2403.10073.json · badge: /api/ran/2403.10073.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 |
|---|---|---|
| NISPLab/AT-BSL | canonical (classifier label) classifier basis: census |
5 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| BSL | Ran ran; our contract draft was wrong, not the code |
NISPLab/AT-BSL/at_bsl_loss.py pointer only (licence: NONE) · get_code("54780edfe377217b") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, NISPLab/AT-BSL 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. |
| ResNet18 | Ran ran; our contract draft was wrong, not the code |
NISPLab/AT-BSL/models/resnet.py pointer only (licence: NONE) · get_code("0f23e7e681845fe0") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, NISPLab/AT-BSL 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. |
| eval_adv_test_whitebox | Ran ran, honoured the contract we drafted |
NISPLab/AT-BSL/pgd_attack.py pointer only (licence: NONE) · get_code("151b4b69a6a02555") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, NISPLab/AT-BSL 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. |
| pgd_loss | Ran ran; our contract draft was wrong, not the code |
NISPLab/AT-BSL/at_bsl_loss.py pointer only (licence: NONE) · get_code("12252555e7643066") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, NISPLab/AT-BSL 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 |
NISPLab/AT-BSL/models/ti_preact_resnet.py pointer only (licence: NONE); the stored copy get_code serves, from BjoernNieth/LS-Dataset-pruning-in-AT, is 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, NISPLab/AT-BSL 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. |
| load_tinyimagenet | Not yet run unverified (harvested, no recorded run) |
NISPLab/AT-BSL/datasets/tiny_imagenet.py pointer only (licence: NONE) · get_code("f2dd3330391f0d13") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, NISPLab/AT-BSL 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 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, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 4 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 |
|---|---|---|---|
| ResNet18 | 27 other papers 15 dated earlier, 12 later |
1605.07146 (2016-05) Wide Residual Networks |
1901.09847 (2019-01) Error Feedback Fixes SignSGD and other Gradient Compression Schemes 1910.09652 (2019-10) Kernelized Wasserstein Natural Gradient and 24 more not named here |
| ti_preact_resnet | 1 other paper 1 later |
2406.13283 (2024-06) Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation |
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.
Deep neural networks are vulnerable to adversarial attacks, leading to erroneous outputs. Adversarial training has been recognized as one of the most effective methods to counter such attacks. However, existing adversarial training techniques have predominantly been evaluated on balanced datasets, whereas real-world data often exhibit a long-tailed distribution, casting doubt on the efficacy of these methods in practical scenarios. In this paper, we delve into the performance of adversarial training under long-tailed distributions. Through an analysis of the prior method "RoBal"(Wu et al., CVPR'21), we discover that utilizing Balanced Softmax Loss (BSL) alone can obtain comparable performance to the complete RoBal approach while significantly reducing the training overhead. Then, we reveal that adversarial training under long-tailed distributions also suffers from robust overfitting similar to uniform distributions. We explore utilizing data augmentation to mitigate this issue and unexpectedly discover that, unlike results obtained with balanced data, data augmentation not only effectively alleviates robust overfitting but also significantly improves robustness. We further identify that the improvement is attributed to the increased diversity of training data. Extensive experiments further corroborate that data augmentation alone can significantly improve robustness. Finally, building on these findings, we demonstrate that compared to RoBal, the combination of BSL and data augmentation leads to a +6.66% improvement in model robustness under AutoAttack on CIFAR-10-LT. Our code is available at: https://github.com/NISPLab/AT-BSL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.10073")
get_code_for_paper("2403.10073")
have("2403.10073")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2403.10073.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2403.10073)
Connect an agent — have() is free.