6 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; 3 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2003.03284.json · badge: /api/ran/2003.03284.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 |
|---|---|---|
| cambridge-mlg/cnaps | canonical (classifier label) classifier basis: census |
6 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| conv1x1 | Ran ran; our contract draft was wrong, not the code |
cambridge-mlg/cnaps/src/resnet.py code served (permissive licence) · get_code("d9def42110729a85") 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 Conv2d. 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.
|
| conv3x3 | Ran ran; our contract draft was wrong, not the code |
cambridge-mlg/cnaps/src/resnet.py pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db") 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 lixiaotong97/DSU, 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_log_files | Ran ran on a synthesized input |
cambridge-mlg/cnaps/src/utils.py code served (permissive licence) · get_code("f87065055026fb7b") 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.
|
| mean_pooling | Ran ran on a synthesized input |
cambridge-mlg/cnaps/src/set_encoder.py code served (permissive licence) · get_code("083d7c12137fe0b7") 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 (1, 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.
|
| split_first_dim_linear | Ran ran; our contract draft was wrong, not the code |
cambridge-mlg/cnaps/src/utils.py pointer only (licence: MIT); the stored copy get_code serves, from Anirudh257/strm, is pointer only (licence: NONE) · get_code("36faaa70bb298474") 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 Anirudh257/strm, 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. |
| stack_first_dim | Ran ran on a synthesized input |
cambridge-mlg/cnaps/src/utils.py code served (permissive licence) · get_code("70f3ccf89a0a79b7") 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 (6, 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.
|
| process_cifar | Not yet run unverified (harvested, no recorded run) |
cambridge-mlg/cnaps/src/prepare_extra_datasets.py code served (permissive licence) · get_code("aa122878d6a7b1b3") How it ranno invocation recorded. |
| process_mnist | Not yet run unverified (harvested, no recorded run) |
cambridge-mlg/cnaps/src/prepare_extra_datasets.py code served (permissive licence) · get_code("b3b6db52dd02d932") How it ranno invocation recorded. |
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, 7 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 7 later) and 1 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 |
|---|---|---|---|
| conv3x3 | 686 other papers 197 dated earlier, 17 the same month, 471 later, 1 same year, order not determinable · 31 only as an assembly brick |
1406.2661 (2014-06) Generative Adversarial Networks |
1409.0575 (2014-09) ImageNet Large Scale Visual Recognition Challenge 1412.6572 (2014-12) Explaining and Harnessing Adversarial Examples and 683 more not named here |
| conv1x1 | 431 other papers 59 dated earlier, 12 the same month, 359 later, 1 undated · 38 only as an assembly brick |
1409.1556 (2014-09) Very Deep Convolutional Networks for Large-Scale Image Recognition |
1506.01186 (2015-06) Cyclical Learning Rates for Training Neural Networks 1507.05717 (2015-07) An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition and 428 more not named here |
| mean_pooling | 2 other papers 2 later |
2006.12245 (2020-06) Enhancing Few-Shot Image Classification with Unlabelled Examples |
2107.01105 (2021-07) Memory Efficient Meta-Learning with Large Images |
| process_cifar | 2 other papers 2 later |
2006.12245 (2020-06) Enhancing Few-Shot Image Classification with Unlabelled Examples |
2301.12246 (2023-01) A Closer Look at Few-shot Classification Again |
| split_first_dim_linear | 2 other papers 2 later |
2006.12245 (2020-06) Enhancing Few-Shot Image Classification with Unlabelled Examples |
Thatipelli_Spatio-Temporal_Relation_Modeling_for_Few-Shot_Action_Recognition_CVPR_2022_paper (2022 (year only)) Spatio-temporal Relation Modeling for Few-shot Action Recognition |
| process_mnist | 1 other paper 1 later |
2006.12245 (2020-06) Enhancing Few-Shot Image Classification with Unlabelled Examples |
|
| stack_first_dim | 1 other paper 1 later |
2006.12245 (2020-06) Enhancing Few-Shot Image Classification with Unlabelled 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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, the hierarchical nature of the meta-learning setting presents several challenges that can render conventional batch normalization ineffective, giving rise to the need to rethink normalization in this setting. We evaluate a range of approaches to batch normalization for meta-learning scenarios, and develop a novel approach that we call TaskNorm. Experiments on fourteen datasets demonstrate that the choice of batch normalization has a dramatic effect on both classification accuracy and training time for both gradient based and gradient-free meta-learning approaches. Importantly, TaskNorm is found to consistently improve performance. Finally, we provide a set of best practices for normalization that will allow fair comparison of meta-learning algorithms.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2003.03284")
get_code_for_paper("2003.03284")
have("2003.03284")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2003.03284.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2003.03284)
Connect an agent — have() is free.