3 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 3 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/2106.04928.json · badge: /api/ran/2106.04928.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 |
|---|---|---|
| zfancy/iad | canonical (classifier label) classifier basis: census |
3 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| ResNet18 | Ran ran; our contract draft was wrong, not the code |
zfancy/iad/models/resnet.py code served (permissive licence) · get_code("d92ef68ca445d801") 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 ResNet. 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.
|
| ResNet34 | Ran ran; our contract draft was wrong, not the code |
zfancy/iad/models/resnet.py code served (permissive licence) · get_code("9aac0eec28d31210") 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 ResNet. 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.
|
| ResNet50 | Ran ran; our contract draft was wrong, not the code |
zfancy/iad/models/resnet.py code served (permissive licence) · get_code("fbee4d09475f9bc3") 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 ResNet. 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.
|
| PGD | Not yet run unverified (harvested, no recorded run) |
zfancy/iad/attack_generator.py code served (permissive licence) · get_code("6c62112efeaf8abe") How it ranno invocation recorded. |
| cwloss | Not yet run unverified (harvested, no recorded run) |
zfancy/iad/attack_generator.py code served (permissive licence) · get_code("d2682eaa7c907946") How it ranno invocation recorded. |
| eval_clean | Not yet run unverified (harvested, no recorded run) |
zfancy/iad/attack_generator.py code served (permissive licence) · get_code("4f81fb9d82756432") How it ranno 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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 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 |
|---|---|---|---|
| ResNet18 | 7 other papers 3 dated earlier, 4 later |
1807.06906 (2018-07) Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search |
1905.09747 (2019-05) Adversarially Robust Distillation 2011.03083 (2020-11) A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs and 4 more not named here |
| cwloss | 6 other papers 1 dated earlier, 5 later · 2 only as an assembly brick |
2010.01736 (2020-10) Geometry-aware Instance-reweighted Adversarial Training |
2210.03543 (2022-10) A2: Efficient Automated Attacker for Boosting Adversarial Training 2303.00250 (2023-03) Combating Exacerbated Heterogeneity for Robust Models in Federated Learning and 3 more not named here |
| ResNet34 | 3 other papers 2 dated earlier, 1 later |
1807.06906 (2018-07) Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search |
1905.09747 (2019-05) Adversarially Robust Distillation 2312.13555 (2023-12) CR-SAM: Curvature Regularized Sharpness-Aware Minimization |
| ResNet50 | 3 other papers 1 dated earlier, 2 later |
1905.09747 (2019-05) Adversarially Robust Distillation |
2201.13329 (2022-01) Can Adversarial Training Be Manipulated By Non-Robust Features? 2312.13555 (2023-12) CR-SAM: Curvature Regularized Sharpness-Aware Minimization |
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.
In ordinary distillation, student networks are trained with soft labels (SLs) given by pretrained teacher networks, and students are expected to improve upon teachers since SLs are stronger supervision than the original hard labels. However, when considering adversarial robustness, teachers may become unreliable and adversarial distillation may not work: teachers are pretrained on their own adversarial data, and it is too demanding to require that teachers are also good at every adversarial data queried by students. Therefore, in this paper, we propose reliable introspective adversarial distillation (IAD) where students partially instead of fully trust their teachers. Specifically, IAD distinguishes between three cases given a query of a natural data (ND) and the corresponding adversarial data (AD): (a) if a teacher is good at AD, its SL is fully trusted; (b) if a teacher is good at ND but not AD, its SL is partially trusted and the student also takes its own SL into account; (c) otherwise, the student only relies on its own SL. Experiments demonstrate the effectiveness of IAD for improving upon teachers in terms of adversarial robustness.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.04928")
get_code_for_paper("2106.04928")
have("2106.04928")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.04928.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.04928)
Connect an agent — have() is free.