Yisen Wang, James Bailey, Xingjun Ma, Hanxun Huang, Simone Romano, Sarah Erfani
9 of 12 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 5 have no contract verdict; 4 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2006.13554.json · badge: /api/ran/2006.13554.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 |
|---|---|---|
| HanxunH/Active-Passive-Losses | canonical (classifier label) classifier basis: census |
9 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| ResNet18 | Ran ran; our contract draft was wrong, not the code |
HanxunH/Active-Passive-Losses/archive/model.py code served (permissive licence) · get_code("268340d6b6a411c7") 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 |
HanxunH/Active-Passive-Losses/archive/model.py code served (permissive licence) · get_code("18a4a9f249bb889a") 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 |
HanxunH/Active-Passive-Losses/archive/model.py code served (permissive licence) · get_code("30165ab348cc2c93") 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.
|
| accuracy | Ran ran on a synthesized input |
HanxunH/Active-Passive-Losses/archive/utils/utils.py code served (permissive licence) · get_code("53636482246a0fcc") 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.
|
| build_for_cifar100 | Ran ran on a synthesized input |
HanxunH/Active-Passive-Losses/dataset.py code served (permissive licence) · get_code("baf477efd17d8a86") 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 (10, 10) 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.
|
| count_parameters_in_MB | Ran ran on a synthesized input |
HanxunH/Active-Passive-Losses/archive/utils/utils.py code served (permissive licence) · get_code("a42ae792b2745b93") 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 float64, ndim 0, 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.
|
| log_display | Ran ran on a synthesized input |
HanxunH/Active-Passive-Losses/util.py code served (permissive licence) · get_code("5ef20ee93730c46b") 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 str. 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.
|
| other_class | Ran ran on a synthesized input |
HanxunH/Active-Passive-Losses/dataset.py code served (permissive licence) · get_code("542dbec466e02973") 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 int64, ndim 0, dtype family int, shape () 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.
|
| setup_logger | Ran ran; our contract draft was wrong, not the code |
HanxunH/Active-Passive-Losses/util.py code served (permissive licence) · get_code("3a4f8ebc3e6cbd58") 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 Logger. 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.
|
| accuracy | Not yet run unverified (harvested, no recorded run) |
HanxunH/Active-Passive-Losses/util.py code served (permissive licence) · get_code("ed42eca6cf2baf78") How it ranno invocation recorded. |
| load_checkpoint_history | Not yet run unverified (harvested, no recorded run) |
HanxunH/Active-Passive-Losses/collect_exp_results.py code served (permissive licence) · get_code("eaac814ea08816f7") How it ranno invocation recorded. |
| multiclass_noisify | Not yet run unverified (harvested, no recorded run) |
HanxunH/Active-Passive-Losses/dataset.py code served (permissive licence) · get_code("b175d19a7622c5c6") How it ranno invocation recorded. |
Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 5 later) and 6 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 3 dated earlier, 1 the same month, 23 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 |
| ResNet34 | 24 other papers 3 dated earlier, 1 the same month, 20 later |
1605.07146 (2016-05) Wide Residual Networks |
1811.12814 (2018-11) Graph-Based Global Reasoning Networks 2002.12047 (2020-02) FMix: Enhancing Mixed Sample Data Augmentation and 21 more not named here |
| ResNet50 | 14 other papers 2 dated earlier, 12 later |
1605.07146 (2016-05) Wide Residual Networks |
1811.12814 (2018-11) Graph-Based Global Reasoning Networks 2106.06042 (2021-06) FEDBABU: TOWARD ENHANCED REPRESENTATION FOR FEDERATED IMAGE CLASSIFICATION and 11 more not named here |
| accuracy | 2 other papers 2 dated earlier |
1904.12848 (2019-04) Unsupervised Data Augmentation for Consistency Training |
1905.00397 (2019-05) Fast AutoAugment |
| multiclass_noisify | 1 other paper 1 later |
aaai_29668 (2024 (year only)) Robust Node Classification on Graph Data with Graph and Label Noise |
|
| setup_logger | 1 other paper 1 later |
2605.28420 (2026-05) Conveyance: A Versatile Framework for Learning in Structured Class Spaces |
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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross Entropy (CE) loss is not robust to noisy labels. Whilst new loss functions have been designed, they are only partially robust. In this paper, we theoretically show by applying a simple normalization that: any loss can be made robust to noisy labels. However, in practice, simply being robust is not sufficient for a loss function to train accurate DNNs. By investigating several robust loss functions, we find that they suffer from a problem of underfitting. To address this, we propose a framework to build robust loss functions called Active Passive Loss (APL). APL combines two robust loss functions that mutually boost each other. Experiments on benchmark datasets demonstrate that the family of new loss functions created by our APL framework can consistently outperform state-of-the-art methods by large margins, especially under large noise rates such as 60% or 80% incorrect labels.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.13554")
get_code_for_paper("2006.13554")
have("2006.13554")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2006.13554.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2006.13554)
Connect an agent — have() is free.