12 of 13 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; 2 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 2 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/1908.03265.json · badge: /api/ran/1908.03265.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 |
|---|---|---|
| LiyuanLucasLiu/RAdam | canonical (classifier label) classifier basis: census |
5 ran · 0 no recorded run |
| kpe/params-flow | community (classifier label) classifier basis not recorded on the link |
5 ran · 1 no recorded run |
| 201419/Optimizer-PyTorch | community (classifier label) classifier basis not recorded on the link |
2 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| colorize | Ran ran; our contract draft was wrong, not the code |
LiyuanLucasLiu/RAdam/cifar_imagenet/utils/visualize.py code served (permissive licence) · get_code("c87e7665fde6cdfc") 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 Tensor, ndim 3, dtype family float, shape (3, 4, 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.
|
| create_one_cycle_lr_scheduler | Ran ran on a synthesized input |
kpe/params-flow/params_flow/utils/learn_scheduler.py code served (permissive licence) · get_code("d97f2e791492ba33") 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 LearningRateScheduler. 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.
|
| gauss | Ran ran on a synthesized input |
LiyuanLucasLiu/RAdam/cifar_imagenet/utils/visualize.py code served (permissive licence) · get_code("d66f0a3cbb86204c") 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 Tensor, ndim 2, dtype family float, shape (2, 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.
|
| gelu | Ran ran on a synthesized input |
kpe/params-flow/params_flow/activations.py code served (permissive licence) · get_code("e6d5b83d23a4800c") 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 EagerTensor, ndim 2, dtype family float, shape (2, 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.
|
| gelu_exact | Ran ran on a synthesized input |
kpe/params-flow/params_flow/activations.py code served (permissive licence) · get_code("3dbb04436d7c7aa9") 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 EagerTensor, ndim 2, dtype family float, shape (2, 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.
|
| get_activation | Ran ran on a synthesized input |
kpe/params-flow/params_flow/activations.py code served (permissive licence) · get_code("528aa6f214e15748") 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 function. 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.
|
| get_mean_and_std | Ran ran on a synthesized input |
LiyuanLucasLiu/RAdam/cifar_imagenet/utils/misc.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from KaiSUN1/SeAl, is pointer only (licence: NONE) · get_code("2c92cec199cf12cd") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from KaiSUN1/SeAl, 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. |
| make_image | Ran ran on a synthesized input |
LiyuanLucasLiu/RAdam/cifar_imagenet/utils/visualize.py code served (permissive licence) · get_code("1394422d51c4b126") 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, 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.
|
| plot_overlap | Ran ran; our contract draft was wrong, not the code |
LiyuanLucasLiu/RAdam/cifar_imagenet/utils/logger.py code served (permissive licence) · get_code("50afa2863ffd9fde") 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 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.
|
| scaled_sign | Ran ran, honoured the contract we drafted |
201419/Optimizer-PyTorch/errorfeedbacksgd.py code served (permissive licence) · get_code("d979441c66cfc515") 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 2, dtype family float, shape (2, 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.
|
| unpack_archive | Ran ran on a synthesized input |
kpe/params-flow/params_flow/utils/fetch_unpack.py code served (permissive licence) · get_code("335085134ae18f02") 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.
|
| unscaled_sign | Ran ran, honoured the contract we drafted |
201419/Optimizer-PyTorch/errorfeedbacksgd.py code served (permissive licence) · get_code("f45a2479358fd34b") 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 2, dtype family float, shape (2, 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.
|
| fetch_url | Not yet run unverified (harvested, no recorded run) |
kpe/params-flow/params_flow/utils/fetch_unpack.py code served (permissive licence) · get_code("1c47760cdb987d2d") How it ranno invocation recorded. |
Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 5 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 |
|---|---|---|---|
| plot_overlap | 31 other papers 9 dated earlier, 1 the same month, 21 later |
1612.06321 (2016-12) Large-Scale Image Retrieval with Attentive Deep Local Features |
1805.07925 (2018-05) Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks 1806.04606 (2018-06) Knowledge Distillation by On-the-Fly Native Ensemble and 28 more not named here |
| get_mean_and_std | 21 other papers 9 dated earlier, 1 the same month, 11 later |
1805.07925 (2018-05) Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks |
1806.04606 (2018-06) Knowledge Distillation by On-the-Fly Native Ensemble 1811.05850 (2018-11) Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization and 18 more not named here |
| colorize | 11 other papers 8 dated earlier, 1 the same month, 2 later |
1805.07925 (2018-05) Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks |
1806.04606 (2018-06) Knowledge Distillation by On-the-Fly Native Ensemble 1811.05850 (2018-11) Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization and 8 more not named here |
| gauss | 11 other papers 8 dated earlier, 1 the same month, 2 later |
1805.07925 (2018-05) Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks |
1806.04606 (2018-06) Knowledge Distillation by On-the-Fly Native Ensemble 1811.05850 (2018-11) Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization and 8 more not named here |
| make_image | 11 other papers 8 dated earlier, 1 the same month, 2 later |
1805.07925 (2018-05) Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks |
1806.04606 (2018-06) Knowledge Distillation by On-the-Fly Native Ensemble 1811.05850 (2018-11) Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization and 8 more not named here |
| scaled_sign | 1 other paper 1 dated earlier |
1901.09847 (2019-01) Error Feedback Fixes SignSGD and other Gradient Compression Schemes |
|
| unscaled_sign | 1 other paper 1 dated earlier |
1901.09847 (2019-01) Error Feedback Fixes SignSGD and other Gradient Compression Schemes |
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.
The learning rate warmup heuristic achieves remarkable success in stabilizing training, accelerating convergence and improving generalization for adaptive stochastic optimization algorithms like RMSprop and Adam. Here, we study its mechanism in details. Pursuing the theory behind warmup, we identify a problem of the adaptive learning rate (i.e., it has problematically large variance in the early stage), suggest warmup works as a variance reduction technique, and provide both empirical and theoretical evidence to verify our hypothesis. We further propose RAdam, a new variant of Adam, by introducing a term to rectify the variance of the adaptive learning rate. Extensive experimental results on image classification, language modeling, and neural machine translation verify our intuition and demonstrate the effectiveness and robustness of our proposed method. All implementations are available at: https://github.com/LiyuanLucasLiu/RAdam.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1908.03265")
get_code_for_paper("1908.03265")
have("1908.03265")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1908.03265.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1908.03265)
Connect an agent — have() is free.