7 of 8 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; 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/2203.06717.json · badge: /api/ran/2203.06717.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 |
|---|---|---|
| DingXiaoH/RepLKNet-pytorch | canonical (classifier label) classifier basis not recorded on the link |
3 ran · 0 no recorded run |
| megvii-research/replknet | canonical (classifier label) classifier basis not recorded on the link |
1 ran · 0 no recorded run |
| shkarupa-alex/tfreplknet | community (classifier label) classifier basis not recorded on the link |
3 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| benchmark_torch | Ran ran on a synthesized input |
megvii-research/replknet/main_benchmark.py code served (permissive licence) · get_code("dbf2077cabf601ed") 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 float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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.
|
| conv_bn | Ran ran on a synthesized input |
DingXiaoH/RepLKNet-pytorch/replknet.py code served (permissive licence) · get_code("16475b9bcc0dad35") 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.
|
| convert_name | Ran ran on a synthesized input |
shkarupa-alex/tfreplknet/convert_weights.py code served (permissive licence) · get_code("16c6217306c29734") 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.
|
| get_bn | Ran ran; our contract draft was wrong, not the code |
DingXiaoH/RepLKNet-pytorch/replknet.py code served (permissive licence) · get_code("b4613da968a83fc8") 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 BatchNorm2d. 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_conv2d | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
DingXiaoH/RepLKNet-pytorch/replknet.py pointer only (licence: MIT); the stored copy get_code serves, from qhfan/fat, is pointer only (licence: NONE) · get_code("31a9326964e3158c") 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 qhfan/fat, 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. |
| preprocess_input_bl | Ran ran on a synthesized input |
shkarupa-alex/tfreplknet/tfreplknet/prep.py code served (permissive licence) · get_code("d8971d3d6d5dede6") 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 4, dtype family float, shape (2, 4, 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.
|
| preprocess_input_xl | Ran ran on a synthesized input |
shkarupa-alex/tfreplknet/tfreplknet/prep.py code served (permissive licence) · get_code("253d978d04cd92c2") 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 4, dtype family float, shape (2, 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.
|
| convert_weight | Not yet run unverified (harvested, no recorded run) |
shkarupa-alex/tfreplknet/convert_weights.py code served (permissive licence) · get_code("37dddb08e5c51831") How it ranno invocation recorded. |
Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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 |
|---|---|---|---|
| get_bn | 4 other papers 4 later |
2304.02330 (2023-04) SMPConv: Self-moving Point Representations for Continuous Convolution |
2305.19412 (2023-05) Are Large Kernels Better Teachers than Transformers for ConvNets? 2407.08972 (2024-07) Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness and 1 more not named here |
| get_conv2d | 1 other paper 1 later |
2306.00396 (2023-06) Lightweight Vision Transformer with Bidirectional Interaction |
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.
We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small kernels could be a more powerful paradigm. We suggested five guidelines, e.g., applying re-parameterized large depth-wise convolutions, to design efficient high-performance large-kernel CNNs. Following the guidelines, we propose RepLKNet, a pure CNN architecture whose kernel size is as large as 31x31, in contrast to commonly used 3x3. RepLKNet greatly closes the performance gap between CNNs and ViTs, e.g., achieving comparable or superior results than Swin Transformer on ImageNet and a few typical downstream tasks, with lower latency. RepLKNet also shows nice scalability to big data and large models, obtaining 87.8% top-1 accuracy on ImageNet and 56.0% mIoU on ADE20K, which is very competitive among the state-of-the-arts with similar model sizes. Our study further reveals that, in contrast to small-kernel CNNs, large-kernel CNNs have much larger effective receptive fields and higher shape bias rather than texture bias. Code & models at https://github.com/megvii-research/RepLKNet.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.06717")
get_code_for_paper("2203.06717")
have("2203.06717")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.06717.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.06717)
Connect an agent — have() is free.