20 of 21 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, 1 violated it and 8 have no contract verdict; 11 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/2008.10599.json · badge: /api/ran/2008.10599.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 |
|---|---|---|
| wpeebles/hessian_penalty | canonical (classifier label) classifier basis: census |
20 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| D_arch | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/BigGAN.py pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from VICO-UoE/IT-GAN, is pointer only (licence: NONE) · get_code("85eb95cce203dfc7") How it ranThe body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from VICO-UoE/IT-GAN, 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. |
| D_arch | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/BigGANdeep.py code served (permissive licence) · get_code("a99a05ac52533be9") 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 dict. 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.
|
| G_arch | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/BigGAN.py pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from VICO-UoE/IT-GAN, is pointer only (licence: NONE) · get_code("e8c308c9283407d7") How it ranThe body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from VICO-UoE/IT-GAN, 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. |
| G_arch | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/BigGANdeep.py code served (permissive licence) · get_code("44d6a6343f6eb182") 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 dict. 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.
|
| fast_gram_schmidt | Ran ran on a synthesized input |
wpeebles/hessian_penalty/biggan_discovery/layers.py code served (permissive licence) · get_code("7a6f2360b5090449") 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 (3, 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.
|
| find_classes | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/datasets.py code served (permissive licence) · get_code("52d10a10fb72fb9f") 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 tuple. 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_current_hessian_penalty_loss_weight | Ran ran on a synthesized input |
wpeebles/hessian_penalty/progan_experiments/training/hessian_penalties.py code served (permissive licence) · get_code("84a7e309cd2bf8f6") 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. 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.
|
| gram_schmidt | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/layers.py pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from mshahbazi72/cGANTransfer, is pointer only (licence: NONE) · get_code("c41836f3e51fa8f1") How it ranThe body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from mshahbazi72/cGANTransfer, 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. |
| hessian_penalty | Ran ran on a synthesized input |
wpeebles/hessian_penalty/hessian_penalty_np.py code served (permissive licence) · get_code("8cd6ed99fbc46c9b") 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.
|
| hessian_penalty | Ran ran on a synthesized input |
wpeebles/hessian_penalty/hessian_penalty_pytorch.py code served (permissive licence) · get_code("3c316ca169bb8f87") 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 0, dtype family float, 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.
|
| is_image_file | Ran ran, violated the contract we drafted |
wpeebles/hessian_penalty/biggan_discovery/datasets.py pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from ermongroup/fairgen, is pointer only (licence: NONE) · get_code("4e6a8faaf8e44abe") How it ranThe body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from ermongroup/fairgen, 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. |
| loss_dcgan_dis | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/losses.py code served (permissive licence) · get_code("982a26492dc6b7fb") 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 tuple, 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.
|
| loss_dcgan_gen | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/losses.py code served (permissive licence) · get_code("6c34831223553b6f") 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 0, dtype family float, 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.
|
| loss_hinge_dis | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/losses.py code served (permissive licence) · get_code("290cd37ab0098d5c") 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 tuple, 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.
|
| make_dataset | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/biggan_discovery/datasets.py pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from ermongroup/fairgen, is pointer only (licence: NONE) · get_code("79e61b6269a450e8") How it ranThe body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from ermongroup/fairgen, 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. |
| multi_layer_second_directional_derivative | Ran ran on a synthesized input |
wpeebles/hessian_penalty/hessian_penalty_pytorch.py code served (permissive licence) · get_code("c0f4937338732adf") 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. 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.
|
| multi_layer_second_directional_derivative | Ran ran on a synthesized input |
wpeebles/hessian_penalty/biggan_discovery/hessian_penalty.py code served (permissive licence) · get_code("eee49efebcd3ff56") 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. 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.
|
| rademacher | Ran ran; our contract draft was wrong, not the code |
wpeebles/hessian_penalty/hessian_penalty_pytorch.py pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from zhihengli-UR/discover_unknown_biases, is pointer only (licence: NONE) · get_code("8de600fe2220e241") How it ranThe body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from zhihengli-UR/discover_unknown_biases, 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. |
| rademacher | Ran ran on a synthesized input |
wpeebles/hessian_penalty/biggan_discovery/hessian_penalty.py code served (permissive licence) · get_code("58800b4db4b14ffd") 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. 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.
|
| second_directional_derivative | Ran ran on a synthesized input |
wpeebles/hessian_penalty/biggan_discovery/hessian_penalty.py code served (permissive licence) · get_code("ea70317070ce2ab5") 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 0, dtype family float, 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.
|
| proj | Not yet run unverified (harvested, no recorded run) |
wpeebles/hessian_penalty/biggan_discovery/layers.py pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from mshahbazi72/cGANTransfer, is pointer only (licence: NONE) · get_code("4015ab1f3ab9b881") How it ranThe body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from mshahbazi72/cGANTransfer, 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. No invocation recorded. |
Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 15 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 1 the same month, 15 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 |
|---|---|---|---|
| find_classes | 30 other papers 12 dated earlier, 18 later |
1406.2661 (2014-06) Generative Adversarial Networks |
1612.06321 (2016-12) Large-Scale Image Retrieval with Attentive Deep Local Features 1809.04729 (2018-09) A Less Biased Evaluation of Out-of-distribution Sample Detectors and 27 more not named here |
| gram_schmidt | 28 other papers 7 dated earlier, 21 later · 5 only as an assembly brick |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis |
1811.10597 (2018-11) GAN Dissection: Visualizing and Understanding Generative Adversarial Networks 1910.05852 (2019-10) Implicit competitive regularization in GANs and 25 more not named here |
| proj | 28 other papers 7 dated earlier, 21 later · 5 only as an assembly brick |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis |
1811.10597 (2018-11) GAN Dissection: Visualizing and Understanding Generative Adversarial Networks 1910.05852 (2019-10) Implicit competitive regularization in GANs and 25 more not named here |
| is_image_file | 22 other papers 10 dated earlier, 1 the same month, 11 later |
1406.2661 (2014-06) Generative Adversarial Networks |
1603.08511 (2016-03) Colorful Image Colorization 1805.08318 (2018-05) Self-Attention Generative Adversarial Networks and 19 more not named here |
| G_arch | 18 other papers 4 dated earlier, 14 later · 3 only as an assembly brick |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis |
1811.10597 (2018-11) GAN Dissection: Visualizing and Understanding Generative Adversarial Networks 1912.05270 (2019-12) MineGAN: effective knowledge transfer from GANs to target domains with few images and 15 more not named here |
| D_arch | 15 other papers 4 dated earlier, 11 later |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis |
1811.10597 (2018-11) GAN Dissection: Visualizing and Understanding Generative Adversarial Networks 1912.05270 (2019-12) MineGAN: effective knowledge transfer from GANs to target domains with few images and 12 more not named here |
| loss_hinge_dis | 11 other papers 3 dated earlier, 8 later |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis |
1912.00953 (2019-12) LOGAN: Latent Optimisation for Generative Adversarial Networks 1912.05270 (2019-12) MineGAN: effective knowledge transfer from GANs to target domains with few images and 8 more not named here |
| loss_dcgan_dis | 10 other papers 2 dated earlier, 8 later |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis |
1912.05270 (2019-12) MineGAN: effective knowledge transfer from GANs to target domains with few images 2108.07668 (2021-08) Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation and 7 more not named here |
| make_dataset | 10 other papers 4 dated earlier, 6 later |
1406.2661 (2014-06) Generative Adversarial Networks |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis 1912.05270 (2019-12) MineGAN: effective knowledge transfer from GANs to target domains with few images and 7 more not named here |
| G_arch | 9 other papers 1 dated earlier, 8 later |
1912.05270 (2019-12) MineGAN: effective knowledge transfer from GANs to target domains with few images |
2108.07668 (2021-08) Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation aaai_20247 (2022 (year only)) An Adversarial Framework for Generating Unseen Images by Activation Maximization and 6 more not named here |
| loss_dcgan_gen | 9 other papers 1 dated earlier, 8 later |
1809.11096 (2018-09) Large Scale GAN Training for High Fidelity Natural Image Synthesis |
2108.07668 (2021-08) Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation aaai_20247 (2022 (year only)) An Adversarial Framework for Generating Unseen Images by Activation Maximization and 6 more not named here |
| D_arch | 8 other papers 1 dated earlier, 7 later |
1912.05270 (2019-12) MineGAN: effective knowledge transfer from GANs to target domains with few images |
2108.07668 (2021-08) Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation aaai_20247 (2022 (year only)) An Adversarial Framework for Generating Unseen Images by Activation Maximization and 5 more not named here |
| rademacher | 2 other papers 2 later |
2104.14556 (2021-04) Discover the Unknown Biased Attribute of an Image Classifier |
2108.07668 (2021-08) Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation |
| get_current_hessian_penalty_loss_weight | 1 other paper 1 later |
2108.07668 (2021-08) Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation |
|
| rademacher | 1 other paper 1 later |
2108.07668 (2021-08) Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation |
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.
Existing disentanglement methods for deep generative models rely on hand-picked priors and complex encoder-based architectures. In this paper, we propose the Hessian Penalty, a simple regularization term that encourages the Hessian of a generative model with respect to its input to be diagonal. We introduce a model-agnostic, unbiased stochastic approximation of this term based on Hutchinson's estimator to compute it efficiently during training. Our method can be applied to a wide range of deep generators with just a few lines of code. We show that training with the Hessian Penalty often causes axis-aligned disentanglement to emerge in latent space when applied to ProGAN on several datasets. Additionally, we use our regularization term to identify interpretable directions in BigGAN's latent space in an unsupervised fashion. Finally, we provide empirical evidence that the Hessian Penalty encourages substantial shrinkage when applied to over-parameterized latent spaces.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2008.10599")
get_code_for_paper("2008.10599")
have("2008.10599")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2008.10599.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2008.10599)
Connect an agent — have() is free.