Wei-Shi Zheng, Yu-Ming Tang, Yi-Xing Peng
8 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 5 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/2204.08932.json · badge: /api/ran/2204.08932.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 |
|---|---|---|
| TOM-tym/Learn-to-Imagine | canonical (classifier label) classifier basis not recorded on the link |
8 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| closest_to_mean | Ran ran on a synthesized input |
TOM-tym/Learn-to-Imagine/CIFAR100/inclearn/lib/herding.py code served (permissive licence) · get_code("ca7e3b6e42185525") 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 1, dtype family int, 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.
|
| compute_gram_matrix | Ran ran on a synthesized input |
TOM-tym/Learn-to-Imagine/CIFAR100/inclearn/models/Imagine.py code served (permissive licence) · get_code("3d5de0b8dd899437") 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 3, dtype family float, shape (2, 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.
|
| cosine_similarity | Ran ran; our contract draft was wrong, not the code |
TOM-tym/Learn-to-Imagine/CIFAR100/inclearn/lib/distance.py code served (permissive licence) · get_code("f7311a4ad1603f3d") 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, 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.
|
| get_optimizer | Ran ran; our contract draft was wrong, not the code |
TOM-tym/Learn-to-Imagine/CIFAR100/inclearn/lib/factory.py code served (permissive licence) · get_code("9f13ed2fb6c8ca34") 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 Adam. 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.
|
| icarl_selection | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
TOM-tym/Learn-to-Imagine/CIFAR100/inclearn/lib/herding.py pointer only (licence: MIT); the stored copy get_code serves, from JiahuaDong/HFC, is pointer only (licence: NONE) · get_code("bf7ca0703632a724") 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 JiahuaDong/HFC, 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. |
| random | Ran ran on a synthesized input |
TOM-tym/Learn-to-Imagine/CIFAR100/inclearn/lib/herding.py code served (permissive licence) · get_code("1e3aea8df18626bf") 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 1, dtype family int, shape (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.
|
| squared_euclidian_distance | Ran ran; our contract draft was wrong, not the code |
TOM-tym/Learn-to-Imagine/CIFAR100/inclearn/lib/distance.py code served (permissive licence) · get_code("34d0cb89ddcd7cdd") 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, 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.
|
| stable_cosine_distance | Ran ran; our contract draft was wrong, not the code |
TOM-tym/Learn-to-Imagine/CIFAR100/inclearn/lib/distance.py code served (permissive licence) · get_code("cda650e8fe4290fa") 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, 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.
|
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, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 3 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 |
|---|---|---|---|
| stable_cosine_distance | 2 other papers 2 later |
2308.10445 (2023-08) When Prompt-based Incremental Learning Does Not Meet Strong Pretraining |
2308.11073 (2023-08) Audio-Visual Class-Incremental Learning |
| cosine_similarity | 1 other paper 1 later |
2308.10445 (2023-08) When Prompt-based Incremental Learning Does Not Meet Strong Pretraining |
|
| get_optimizer | 1 other paper 1 later |
2308.10445 (2023-08) When Prompt-based Incremental Learning Does Not Meet Strong Pretraining |
|
| icarl_selection | 1 other paper 1 later |
2308.03374 (2023-08) Heterogeneous Forgetting Compensation for Class-Incremental Learning |
|
| squared_euclidian_distance | 1 other paper 1 later |
2308.10445 (2023-08) When Prompt-based Incremental Learning Does Not Meet Strong Pretraining |
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.
Deep neural network (DNN) suffers from catastrophic forgetting when learning incrementally, which greatly limits its applications. Although maintaining a handful of samples (called "exemplars") of each task could alleviate forgetting to some extent, existing methods are still limited by the small number of exemplars since these exemplars are too few to carry enough task-specific knowledge, and therefore the forgetting remains. To overcome this problem, we propose to "imagine" diverse counterparts of given exemplars referring to the abundant semantic-irrelevant information from unlabeled data. Specifically, we develop a learnable feature generator to diversify exemplars by adaptively generating diverse counterparts of exemplars based on semantic information from exemplars and semantically-irrelevant information from unlabeled data. We introduce semantic contrastive learning to enforce the generated samples to be semantic consistent with exemplars and perform semanticdecoupling contrastive learning to encourage diversity of generated samples. The diverse generated samples could effectively prevent DNN from forgetting when learning new tasks. Our method does not bring any extra inference cost and outperforms state-of-the-art methods on two benchmarks CIFAR-100 and ImageNet-Subset by a clear margin.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2204.08932")
get_code_for_paper("2204.08932")
have("2204.08932")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2204.08932.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2204.08932)
Connect an agent — have() is free.