5 of 7 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 2 have no contract verdict; 2 failures of our instrument; 2 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/2105.07085.json · badge: /api/ran/2105.07085.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 |
|---|---|---|
| taoyang1122/MutualNet | canonical (classifier label) classifier basis: census |
5 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| conv_module_name_filter | Ran ran; our contract draft was wrong, not the code |
taoyang1122/MutualNet/utils/model_profiling.py code served (permissive licence) · get_code("32f1f27f7d19f6ad") 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_logger | Ran ran on a synthesized input |
taoyang1122/MutualNet/utils/setlogger.py code served (permissive licence) · get_code("84a10f5778846b16") 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.
|
| get_params | Ran ran on a synthesized input |
taoyang1122/MutualNet/utils/model_profiling.py code served (permissive licence) · get_code("e2db4aa1fd031021") 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.
|
| make_divisible | Ran ran, honoured the contract we drafted |
taoyang1122/MutualNet/models/slimmable_ops.py pointer only (licence: MIT); the stored copy get_code serves, from JiahuiYu/slimmable_networks, is pointer only (licence: NOASSERTION) · get_code("3356d3566f053dcc") 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 JiahuiYu/slimmable_networks, and GitHub could not classify the licence of that repository (NOASSERTION). 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. |
| run_forward | Ran ran; our contract draft was wrong, not the code |
taoyang1122/MutualNet/utils/model_profiling.py code served (permissive licence) · get_code("6149e2d484175e99") 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 int, ndim 0, dtype family int, 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.
|
| ComputeBN | Not yet run unverified (harvested, no recorded run) |
taoyang1122/MutualNet/ComputePostBN.py code served (permissive licence) · get_code("9da92d862a6c3325") How it ranno invocation recorded. |
| flush_scalar_meters | Not yet run unverified (harvested, no recorded run) |
taoyang1122/MutualNet/utils/meters.py code served (permissive licence) · get_code("2e315531666ca1ad") How it ranno invocation recorded. |
Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (2 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 |
|---|---|---|---|
| make_divisible | 4 other papers 4 dated earlier |
1812.08928 (2018-12) Slimmable Neural Networks |
1903.05134 (2019-03) Universally Slimmable Networks and Improved Training Techniques 2012.03153 (2020-12) Any-Width Networks and 1 more not named here |
| conv_module_name_filter | 2 other papers 2 later |
2106.06560 (2021-06) HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers |
2310.03337 (2023-10) Denoising Diffusion Step-aware Models |
| get_logger | 2 other papers 1 dated earlier, 1 later |
2006.07989 (2020-06) GradAug: A New Regularization Method for Deep Neural Networks |
2305.02507 (2023-05) Stimulative Training++: Go Beyond The Performance Limits of Residual Networks |
| get_params | 2 other papers 2 later |
2106.06560 (2021-06) HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers |
2310.03337 (2023-10) Denoising Diffusion Step-aware Models |
| run_forward | 1 other paper 1 later |
2310.03337 (2023-10) Denoising Diffusion Step-aware Models |
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.
Most existing deep neural networks are static, which means they can only do inference at a fixed complexity. But the resource budget can vary substantially across different devices. Even on a single device, the affordable budget can change with different scenarios, and repeatedly training networks for each required budget would be incredibly expensive. Therefore, in this work, we propose a general method called MutualNet to train a single network that can run at a diverse set of resource constraints. Our method trains a cohort of model configurations with various network widths and input resolutions. This mutual learning scheme not only allows the model to run at different width-resolution configurations but also transfers the unique knowledge among these configurations, helping the model to learn stronger representations overall. MutualNet is a general training methodology that can be applied to various network structures (e.g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e.g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets. Since we only train the model once, it also greatly reduces the training cost compared to independently training several models. Surprisingly, MutualNet can also be used to significantly boost the performance of a single network, if dynamic resource constraint is not a concern. In summary, MutualNet is a unified method for both static and adaptive, 2D and 3D networks. Codes and pre-trained models are available at \url{https://github.com/taoyang1122/MutualNet}.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2105.07085")
get_code_for_paper("2105.07085")
have("2105.07085")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2105.07085.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2105.07085)
Connect an agent — have() is free.