10 of 10 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 7 have no contract verdict; 3 failures of our instrument; 0 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/2109.13398.json · badge: /api/ran/2109.13398.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 |
|---|---|---|
| cleverhans-lab/unrolling-sgd | canonical (classifier label) classifier basis not recorded on the link |
10 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| Mentr | Ran ran on a synthesized input |
cleverhans-lab/unrolling-sgd/Privacy_risk_score/calculate_PRS.py code served (permissive licence) · get_code("860c6eec0095faf2") 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 1, dtype family float, shape (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.
|
| ResNet18 | Ran ran; our contract draft was wrong, not the code |
cleverhans-lab/unrolling-sgd/ResNet_CIFAR10.py code served (permissive licence) · get_code("3e93275f5bb6e23e") 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 ResNet. 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.
|
| ResNet34 | Ran ran; our contract draft was wrong, not the code |
cleverhans-lab/unrolling-sgd/ResNet_CIFAR10.py code served (permissive licence) · get_code("9a28296ebc73a658") 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 ResNet. 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.
|
| ResNet50 | Ran ran; our contract draft was wrong, not the code |
cleverhans-lab/unrolling-sgd/ResNet_CIFAR10.py code served (permissive licence) · get_code("479285c5bc2b40ba") 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 ResNet. 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.
|
| create_data_loader | Ran ran on a synthesized input |
cleverhans-lab/unrolling-sgd/BERT/bert_helpers.py code served (permissive licence) · get_code("63ae7db4794f4b09") 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 DataLoader. 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.
|
| prob_bins | Ran ran on a synthesized input |
cleverhans-lab/unrolling-sgd/Privacy_risk_score/calculate_PRS.py code served (permissive licence) · get_code("1341a64904d65de6") 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.
|
| safe_log | Ran ran on a synthesized input |
cleverhans-lab/unrolling-sgd/Privacy_risk_score/calculate_PRS.py code served (permissive licence) · get_code("76a2d8f814f3f8ba") 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.
|
| validate | Ran ran on a synthesized input |
cleverhans-lab/unrolling-sgd/Privacy_risk_score/prs_vs_ver.py code served (permissive licence) · get_code("4068f9af45024c22") 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. 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 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.
|
| validate | Ran ran on a synthesized input |
cleverhans-lab/unrolling-sgd/Privacy_risk_score/train_shadow_model.py code served (permissive licence) · get_code("64873e8a11684e38") 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. 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 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.
|
| weights_to_list_fast | Ran ran on a synthesized input |
cleverhans-lab/unrolling-sgd/Privacy_risk_score/Correlation_PRS.py code served (permissive licence) · get_code("30ac71b95fafa32e") 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.
|
Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 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 |
|---|---|---|---|
| ResNet18 | 4 other papers 1 dated earlier, 3 later |
2105.00303 (2021-05) RATT: Leveraging Unlabeled Data to Guarantee Generalization |
2308.04142 (2023-08) Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning 2308.13862 (2023-08) Late Stopping: Avoiding Confidently Learning from Mislabeled Examples and 1 more not named here |
| ResNet34 | 1 other paper 1 later |
2403.00329 (2024-03) Learning with Logical Constraints but without Shortcut Satisfaction |
|
| ResNet50 | 1 other paper 1 later |
2308.13862 (2023-08) Late Stopping: Avoiding Confidently Learning from Mislabeled Examples |
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.
Machine unlearning is the process through which a deployed machine learning model is made to forget about some of its training data points. While naively retraining the model from scratch is an option, it is almost always associated with large computational overheads for deep learning models. Thus, several approaches to approximately unlearn have been proposed along with corresponding metrics that formalize what it means for a model to forget about a data point. In this work, we first taxonomize approaches and metrics of approximate unlearning. As a result, we identify verification error, i.e., the L2 difference between the weights of an approximately unlearned and a naively retrained model, as an approximate unlearning metric that should be optimized for as it subsumes a large class of other metrics. We theoretically analyze the canonical training algorithm, stochastic gradient descent (SGD), to surface the variables which are relevant to reducing the verification error of approximate unlearning for SGD. From this analysis, we first derive an easy-to-compute proxy for verification error (termed unlearning error). The analysis also informs the design of a new training objective penalty that limits the overall change in weights during SGD and as a result facilitates approximate unlearning with lower verification error. We validate our theoretical work through an empirical evaluation on learning with CIFAR-10, CIFAR-100, and IMDB sentiment analysis.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.13398")
get_code_for_paper("2109.13398")
have("2109.13398")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.13398.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.13398)
Connect an agent — have() is free.