Dingfan Chen, Mario Fritz, Raouf Kerkouche
14 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; 2 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 5 failures of our instrument; 7 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/2211.04446.json · badge: /api/ran/2211.04446.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 |
|---|---|---|
| DingfanChen/Private-Set | canonical (classifier label) classifier basis not recorded on the link |
14 ran · 7 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| VGG11 | Ran ran; our contract draft was wrong, not the code |
DingfanChen/Private-Set/utils/networks.py pointer only (licence: MIT); the stored copy get_code serves, from ndhg1213/CMIDD, is pointer only (licence: NONE) · get_code("8e1b179ef1f0fe03") 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 ndhg1213/CMIDD, 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. |
| VGG11BN | Ran ran; our contract draft was wrong, not the code |
DingfanChen/Private-Set/utils/networks.py pointer only (licence: MIT); the stored copy get_code serves, from ndhg1213/CMIDD, is pointer only (licence: NONE) · get_code("cfab0fafbf988aa4") 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 ndhg1213/CMIDD, 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. |
| VGG13 | Ran ran; our contract draft was wrong, not the code |
DingfanChen/Private-Set/utils/networks.py pointer only (licence: MIT); the stored copy get_code serves, from ndhg1213/CMIDD, is pointer only (licence: NONE) · get_code("07962bf28fe347a0") 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 ndhg1213/CMIDD, 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. |
| accuracy | Ran ran on a synthesized input |
DingfanChen/Private-Set/continual_learning/cl_utils.py code served (permissive licence) · get_code("d47cff53890c0a35") 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 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.
|
| augment | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
DingfanChen/Private-Set/utils/augmentation.py code served (permissive licence) · get_code("4ac684d789a25255") 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 4, dtype family float, shape (2, 3, 4, 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.
|
| dist_matrix | Ran ran, honoured the contract we drafted |
DingfanChen/Private-Set/continual_learning/mean_embedding.py code served (permissive licence) · get_code("9fe8d3a1ab728f44") 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.
|
| distance_wb | Ran ran, honoured the contract we drafted |
DingfanChen/Private-Set/utils/ops.py pointer only (licence: MIT); the stored copy get_code serves, from saehyung-lee/dcc, is pointer only (licence: NONE) · get_code("6e9c65aaa7c1b5da") 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 saehyung-lee/dcc, 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. |
| epoch | Ran ran on a synthesized input |
DingfanChen/Private-Set/utils/ops.py code served (permissive licence) · get_code("68185a4f54101d97") 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.
|
| get_loops | Ran ran on a synthesized input |
DingfanChen/Private-Set/utils/misc.py code served (permissive licence) · get_code("cd8360d133b0589f") 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 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_privacy_spent | Ran ran on a synthesized input |
DingfanChen/Private-Set/rdp_accountant.py code served (permissive licence) · get_code("2a4aad919ee70e6f") 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.
|
| match_loss | Ran ran on a synthesized input |
DingfanChen/Private-Set/utils/ops.py code served (permissive licence) · get_code("c23bd1ead394b471") 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.
|
| meddistance | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
DingfanChen/Private-Set/continual_learning/mean_embedding.py code served (permissive licence) · get_code("10cef6fcc2e68d3b") 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.
|
| pixel_norm | Ran ran on a synthesized input |
DingfanChen/Private-Set/utils/gan_models.py code served (permissive licence) · get_code("2923c1cac02c9741") 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.
|
| rand_scale | Ran ran on a synthesized input |
DingfanChen/Private-Set/utils/augmentation.py code served (permissive licence) · get_code("018d0e459aac197e") 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 4, dtype family float, shape (2, 3, 4, 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.
|
| DiffAugment | Not yet run unverified (harvested, no recorded run) |
DingfanChen/Private-Set/utils/augmentation.py code served (permissive licence) · get_code("96c702388fb2fc5b") How it ranno invocation recorded. |
| compute_epsilon | Not yet run unverified (harvested, no recorded run) |
DingfanChen/Private-Set/rdp_accountant.py code served (permissive licence) · get_code("9e86773fdea3d6c0") How it ranno invocation recorded. |
| compute_rdp | Not yet run unverified (harvested, no recorded run) |
DingfanChen/Private-Set/rdp_accountant.py code served (permissive licence) · get_code("9bc608b2340472d0") How it ranno invocation recorded. |
| get_dataset | Not yet run unverified (harvested, no recorded run) |
DingfanChen/Private-Set/utils/misc.py code served (permissive licence) · get_code("5211c024ed09fb69") How it ranno invocation recorded. |
| get_network | Not yet run unverified (harvested, no recorded run) |
DingfanChen/Private-Set/utils/misc.py code served (permissive licence) · get_code("9559a2ae8eb12814") How it ranno invocation recorded. |
| one_hot_embedding | Not yet run unverified (harvested, no recorded run) |
DingfanChen/Private-Set/utils/gan_models.py code served (permissive licence) · get_code("397e62c7d01d81f7") How it ranno invocation recorded. |
| one_hot_embedding_torch | Not yet run unverified (harvested, no recorded run) |
DingfanChen/Private-Set/continual_learning/mean_embedding.py code served (permissive licence) · get_code("cb539607c718e848") How it ranno 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, 14 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 11 later) and 7 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 |
|---|---|---|---|
| VGG11BN | 28 other papers 3 dated earlier, 25 later |
2203.01531 (2022-03) CAFE: Learning to Condense Dataset by Aligning Features |
2204.07513 (2022-04) Synthesizing Informative Training Samples with GAN 2210.16774 (2022-10) Dataset Distillation via Factorization and 25 more not named here |
| VGG11 | 27 other papers 3 dated earlier, 24 later |
2203.01531 (2022-03) CAFE: Learning to Condense Dataset by Aligning Features |
2204.07513 (2022-04) Synthesizing Informative Training Samples with GAN 2210.16774 (2022-10) Dataset Distillation via Factorization and 24 more not named here |
| VGG13 | 19 other papers 2 dated earlier, 17 later |
2204.07513 (2022-04) Synthesizing Informative Training Samples with GAN |
2210.16774 (2022-10) Dataset Distillation via Factorization 2301.01197 (2023-01) Backdoor Attacks Against Dataset Distillation and 16 more not named here |
| distance_wb | 11 other papers 2 dated earlier, 9 later |
2202.02916 (2022-02) Dataset Condensation with Contrastive Signals |
2204.07513 (2022-04) Synthesizing Informative Training Samples with GAN 2301.01197 (2023-01) Backdoor Attacks Against Dataset Distillation and 8 more not named here |
| augment | 2 other papers 1 dated earlier, 1 later |
2203.01531 (2022-03) CAFE: Learning to Condense Dataset by Aligning Features |
2302.01068 (2023-02) FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations |
| meddistance | 2 other papers 2 dated earlier |
1605.06796 (2016-05) Interpretable Distribution Features with Maximum Testing Power |
1910.12252 (2019-10) Kernel Stein Tests for Multiple Model Comparison |
| compute_epsilon | 1 other paper 1 later |
2302.01068 (2023-02) FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations |
|
| compute_rdp | 1 other paper 1 later |
2302.01068 (2023-02) FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations |
|
| dist_matrix | 1 other paper 1 dated earlier |
1910.12252 (2019-10) Kernel Stein Tests for Multiple Model Comparison |
|
| epoch | 1 other paper 1 later |
2302.01068 (2023-02) FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations |
|
| get_dataset | 1 other paper 1 later |
2302.01068 (2023-02) FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations |
|
| get_network | 1 other paper 1 later |
2302.01068 (2023-02) FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations |
|
| get_privacy_spent | 1 other paper 1 later |
2302.01068 (2023-02) FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations |
|
| one_hot_embedding | 1 other paper 1 dated earlier |
2006.08265 (2020-06) GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators |
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.
Differentially private data generation techniques have become a promising solution to the data privacy challenge --it enables sharing of data while complying with rigorous privacy guarantees, which is essential for scientific progress in sensitive domains. Unfortunately, restricted by the inherent complexity of modeling highdimensional distributions, existing private generative models are struggling with the utility of synthetic samples. In contrast to existing works that aim at fitting the complete data distribution, we directly optimize for a small set of samples that are representative of the distribution under the supervision of discriminative information from downstream tasks, which is generally an easier task and more suitable for private training. Our work provides an alternative view for differentially private generation of high-dimensional data and introduces a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches. The source code is available at https://github.com/DingfanChen/Private-Set.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2211.04446")
get_code_for_paper("2211.04446")
have("2211.04446")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2211.04446.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2211.04446)
Connect an agent — have() is free.