15 of 17 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 11 have no contract verdict; 4 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/2006.09461.json · badge: /api/ran/2006.09461.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 |
|---|---|---|
| ajiljalal/csgm-robust-neurips | canonical (classifier label) classifier basis: census |
15 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| find_overlap_idx | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/create_scripts.py code served (permissive licence) · get_code("86c8f09d190ff0de") 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. 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_figsize | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/metrics_utils.py code served (permissive licence) · get_code("857ba6b23095a4f0") 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.
|
| get_full_input | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/celebA_input.py code served (permissive licence) · get_code("68230c4c69e10d9c") 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.
|
| get_image_nums | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/view_estimated_celebA.py code served (permissive licence) · get_code("8ad7897be275437c") 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.
|
| get_l2_loss | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/utils.py code served (permissive licence) · get_code("3f8654a051989cdf") 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 float32, 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.
|
| get_measurement_loss | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/utils.py code served (permissive licence) · get_code("9b90a29baade3892") 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.
|
| get_setting_specific_name | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/create_scripts.py code served (permissive licence) · get_code("09306559529f51d8") 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.
|
| int_or_float | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/metrics_utils.py code served (permissive licence) · get_code("3a73f73ee48b894d") 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. 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.
|
| model_input | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/celebA_input.py code served (permissive licence) · get_code("b798a88c68cffe05") 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.
|
| scale | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/celebA_utils.py code served (permissive licence) · get_code("97498d6181a0d2bd") 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.
|
| score_2afc_dataset | Ran ran; our contract draft was wrong, not the code |
ajiljalal/csgm-robust-neurips/src/lpips/dist_model.py code served (permissive licence) · get_code("514dd3c0eee3691c") 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.
|
| score_jnd_dataset | Ran ran; our contract draft was wrong, not the code |
ajiljalal/csgm-robust-neurips/src/lpips/dist_model.py code served (permissive licence) · get_code("581c80d602289d6d") 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.
|
| spatial_average | Ran ran; our contract draft was wrong, not the code |
ajiljalal/csgm-robust-neurips/src/lpips/networks_basic.py code served (permissive licence) · get_code("29e5e72bcd006dcd") 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 4, dtype family float, shape (2, 4, 1, 1) 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.
|
| transpose | Ran ran on a synthesized input |
ajiljalal/csgm-robust-neurips/src/celebA_utils.py code served (permissive licence) · get_code("a6f71674cdc73691") 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.
|
| upsample | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
ajiljalal/csgm-robust-neurips/src/lpips/networks_basic.py pointer only (licence: MIT); the stored copy get_code serves, from cychungg/hairfusion, is pointer only (licence: NONE) · get_code("351677a36e1961df") 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 cychungg/hairfusion, 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. |
| get_lpips_score | Not yet run unverified (harvested, no recorded run) |
ajiljalal/csgm-robust-neurips/src/utils.py code served (permissive licence) · get_code("f4a3a0cbedef7288") How it ranno invocation recorded. |
| sample_generator_images | Not yet run unverified (harvested, no recorded run) |
ajiljalal/csgm-robust-neurips/src/celebA_input.py code served (permissive licence) · get_code("29a7a66a98bbc2ed") How it ranno invocation recorded. |
Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 9 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 8 later) and 8 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 |
|---|---|---|---|
| spatial_average | 19 other papers 4 dated earlier, 15 later |
1801.03924 (2018-01) The Unreasonable Effectiveness of Deep Features as a Perceptual Metric |
1912.04958 (2019-12) Analyzing and Improving the Image Quality of StyleGAN 2002.09219 (2020-02) Stochastic Latent Residual Video Prediction and 16 more not named here |
| score_2afc_dataset | 15 other papers 4 dated earlier, 11 later |
1912.04958 (2019-12) Analyzing and Improving the Image Quality of StyleGAN |
2002.09219 (2020-02) Stochastic Latent Residual Video Prediction 2005.00953 (2020-05) Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution and 12 more not named here |
| upsample | 10 other papers 3 dated earlier, 7 later |
1912.04958 (2019-12) Analyzing and Improving the Image Quality of StyleGAN |
2002.09219 (2020-02) Stochastic Latent Residual Video Prediction 2005.05999 (2020-05) Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing and 7 more not named here |
| score_jnd_dataset | 6 other papers 2 dated earlier, 4 later |
1912.04958 (2019-12) Analyzing and Improving the Image Quality of StyleGAN |
2002.09219 (2020-02) Stochastic Latent Residual Video Prediction 2007.06600 (2020-07) Closed-Form Factorization of Latent Semantics in GANs and 3 more not named here |
| find_overlap_idx | 2 other papers 2 dated earlier |
1703.03208 (2017-03) Compressed Sensing using Generative Models |
1807.01442 (2018-07) Modeling Sparse Deviations for Compressed Sensing using Generative Models |
| get_figsize | 2 other papers 1 dated earlier, 1 later |
1807.01442 (2018-07) Modeling Sparse Deviations for Compressed Sensing using Generative Models |
2106.12182 (2021-06) Fairness for Image Generation with Uncertain Sensitive Attributes |
| int_or_float | 2 other papers 1 dated earlier, 1 later |
1807.01442 (2018-07) Modeling Sparse Deviations for Compressed Sensing using Generative Models |
2106.12182 (2021-06) Fairness for Image Generation with Uncertain Sensitive Attributes |
| get_image_nums | 1 other paper 1 later |
2106.12182 (2021-06) Fairness for Image Generation with Uncertain Sensitive Attributes |
|
| get_l2_loss | 1 other paper 1 later |
2106.12182 (2021-06) Fairness for Image Generation with Uncertain Sensitive Attributes |
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 goal of compressed sensing is to estimate a high dimensional vector from an underdetermined system of noisy linear equations. In analogy to classical compressed sensing, here we assume a generative model as a prior, that is, we assume the vector is represented by a deep generative model $G: \mathbb{R}^k \rightarrow \mathbb{R}^n$. Classical recovery approaches such as empirical risk minimization (ERM) are guaranteed to succeed when the measurement matrix is sub-Gaussian. However, when the measurement matrix and measurements are heavy-tailed or have outliers, recovery may fail dramatically. In this paper we propose an algorithm inspired by the Median-of-Means (MOM). Our algorithm guarantees recovery for heavy-tailed data, even in the presence of outliers. Theoretically, our results show our novel MOM-based algorithm enjoys the same sample complexity guarantees as ERM under sub-Gaussian assumptions. Our experiments validate both aspects of our claims: other algorithms are indeed fragile and fail under heavy-tailed and/or corrupted data, while our approach exhibits the predicted robustness.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.09461")
get_code_for_paper("2006.09461")
have("2006.09461")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2006.09461.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2006.09461)
Connect an agent — have() is free.