9 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; 1 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 3 failures of our instrument; 0 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/2006.04924.json · badge: /api/ran/2006.04924.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 |
|---|---|---|
| Muzammal-Naseer/NRP | canonical (classifier label) classifier basis: classifier_2025 |
2 ran · 0 no recorded run |
| mshane911/NRP | community (classifier label) classifier basis not recorded on the link |
7 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| get_image_paths | Ran ran on a synthesized input |
mshane911/NRP/utils.py code served (permissive licence) · get_code("a0ec6a05ea3a7598") How it ranRan 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 list, ndim 1, 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.
|
| get_labs | Ran ran, honoured the contract we drafted |
Muzammal-Naseer/NRP/bypass_nrp.py code served (permissive licence) · get_code("5fa2b4ae2c9f9b0c") How it ranRan 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 ndarray, ndim 2, dtype family float, shape (2, 1000) 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.
|
| make_layer | Ran ran; our contract draft was wrong, not the code |
mshane911/NRP/modules/module_util.py pointer only (licence: MIT); the stored copy get_code serves, from haoyuc/A2N, is pointer only (licence: NONE) · get_code("c04a23de0531da4a") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from haoyuc/A2N, 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. |
| model_cnn_1layer | Ran ran on a synthesized input |
mshane911/NRP/model_defs.py code served (permissive licence) · get_code("c04566214aef8894") How it ranRan 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 Sequential. 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.
|
| model_mlp_any | Ran ran on a synthesized input |
mshane911/NRP/model_defs.py code served (permissive licence) · get_code("536b44e648824359") How it ranRan 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 Sequential. 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.
|
| model_mlp_uniform | Ran ran on a synthesized input |
mshane911/NRP/model_defs.py code served (permissive licence) · get_code("1d4d589798bf1c33") How it ranRan 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 Sequential. 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.
|
| normalize | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
Muzammal-Naseer/NRP/ssp.py code served (permissive licence) · get_code("80be5f7ad7ab3dcc") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) 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.
|
| read_img | Ran ran on a synthesized input |
mshane911/NRP/utils.py code served (permissive licence) · get_code("349ac8f433eb384a") How it ranRan 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 ndarray, ndim 3, dtype family float, shape (4, 3, 3) 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.
|
| tensor2img | Ran ran; our contract draft was wrong, not the code |
mshane911/NRP/utils.py code served (permissive licence) · get_code("ce86475983f046ab") How it ranRan 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 ndarray, ndim 3, dtype family int, shape (4, 5, 3) 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.
|
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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 3 later) and 3 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 |
|---|---|---|---|
| make_layer | 31 other papers 6 dated earlier, 25 later · 6 only as an assembly brick |
1809.00219 (2018-09) ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks |
1905.02716 (2019-05) EDVR: Video Restoration with Enhanced Deformable Convolutional Networks 1905.10485 (2019-05) Generative Latent Flow and 28 more not named here |
| normalize | 2 other papers 1 dated earlier, 1 later |
1904.00887 (2019-04) Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks |
2103.14641 (2021-03) On Generating Transferable Targeted Perturbations |
| tensor2img | 2 other papers 1 dated earlier, 1 later |
1905.02716 (2019-05) EDVR: Video Restoration with Enhanced Deformable Convolutional Networks |
2502.05749 (2025-02) UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control |
| model_cnn_1layer | 1 other paper 1 dated earlier |
2002.12920 (2020-02) Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond |
|
| model_mlp_any | 1 other paper 1 dated earlier |
2002.12920 (2020-02) Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond |
|
| model_mlp_uniform | 1 other paper 1 dated earlier |
2002.12920 (2020-02) Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond |
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.
Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock towards their real-world deployment. Transferability of adversarial examples demand generalizable defenses that can provide cross-task protection. Adversarial training that enhances robustness by modifying target model's parameters lacks such generalizability. On the other hand, different input processing based defenses fall short in the face of continuously evolving attacks. In this paper, we take the first step to combine the benefits of both approaches and propose a self-supervised adversarial training mechanism in the input space. By design, our defense is a generalizable approach and provides significant robustness against the \textbf{unseen} adversarial attacks (\eg by reducing the success rate of translation-invariant \textbf{ensemble} attack from 82.6\% to 31.9\% in comparison to previous state-of-the-art). It can be deployed as a plug-and-play solution to protect a variety of vision systems, as we demonstrate for the case of classification, segmentation and detection. Code is available at: {\small\url{https://github.com/Muzammal-Naseer/NRP}}.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.04924")
get_code_for_paper("2006.04924")
have("2006.04924")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2006.04924.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2006.04924)
Connect an agent — have() is free.