Dacheng Tao, Chang Xu, Xinqi Zhu
6 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2104.05622.json · badge: /api/ran/2104.05622.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 |
|---|---|---|
| zhuxinqimac/PS-SC | canonical (classifier label) classifier basis: census |
6 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| convert_to_shape | Ran ran; our contract draft was wrong, not the code |
zhuxinqimac/PS-SC/dataset_tool.py code served (permissive licence) · get_code("da94c36a397beb5b") 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 (2, 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_rot_mat | Ran ran, honoured the contract we drafted |
zhuxinqimac/PS-SC/plot_latent_space.py code served (permissive licence) · get_code("ac86c7ae82552d8c") 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 (2, 2) 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.
|
| expand_traversal | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
zhuxinqimac/PS-SC/run_generator_ps_sc.py code served (permissive licence) · get_code("693b845ab6cda741") 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 (7, 5) 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.
|
| sample_grid_z | Ran ran; our contract draft was wrong, not the code |
zhuxinqimac/PS-SC/plot_latent_space.py code served (permissive licence) · get_code("caf3c1796c3d5058") 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 (9, 8) 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.
|
| str_to_intlist | Ran ran, honoured the contract we drafted |
zhuxinqimac/PS-SC/dataset_tool.py code served (permissive licence) · get_code("c9e27a8d2f508edc") 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 int; 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.
|
| truncated_z_sample | Ran ran, honoured the contract we drafted |
zhuxinqimac/PS-SC/run_generate_attr_dataset.py code served (permissive licence) · get_code("b72f0c209b7b64be") 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 (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.
|
| execute_cmdline | Not yet run unverified (harvested, no recorded run) |
zhuxinqimac/PS-SC/dataset_tool.py code served (permissive licence) · get_code("dea74cd7a714496f") How it ranno invocation recorded. |
| get_path_or_url | Not yet run unverified (harvested, no recorded run) |
zhuxinqimac/PS-SC/pretrained_networks.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from DaVran369/face, is pointer only (licence: NOASSERTION) · get_code("28ef046211377170") 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 DaVran369/face, 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. No 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 (2 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_path_or_url | 3 other papers 2 dated earlier, 1 later |
1912.04958 (2019-12) Analyzing and Improving the Image Quality of StyleGAN |
2006.05891 (2020-06) On Noise Injection in Generative Adversarial Networks 2211.13874 (2022-11) FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction |
| truncated_z_sample | 2 other papers 1 dated earlier, 1 later |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis |
2201.12179 (2022-01) Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks |
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.
Capturing interpretable variations has long been one of the goals in disentanglement learning. However, unlike the independence assumption, interpretability has rarely been exploited to encourage disentanglement in the unsupervised setting. In this paper, we examine the interpretability of disentangled representations by investigating two questions: where to be interpreted and what to be interpreted? A latent code is easily to be interpreted if it would consistently impact a certain subarea of the resulting generated image. We thus propose to learn a spatial mask to localize the effect of each individual latent dimension. On the other hand, interpretability usually comes from latent dimensions that capture simple and basic variations in data. We thus impose a perturbation on a certain dimension of the latent code, and expect to identify the perturbation along this dimension from the generated images so that the encoding of simple variations can be enforced. Additionally, we develop an unsupervised model selection method, which accumulates perceptual distance scores along axes in the latent space. On various datasets, our models can learn high-quality disentangled representations without supervision, showing the proposed modeling of interpretability is an effective proxy for achieving unsupervised disentanglement.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.05622")
get_code_for_paper("2104.05622")
have("2104.05622")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.05622.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.05622)
Connect an agent — have() is free.