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; 1 honoured the contract we drafted, 0 violated it and 1 has 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/2008.03813.json · badge: /api/ran/2008.03813.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 |
|---|---|---|
| frank-xwang/CLD-UnsupervisedLearning | canonical (classifier label) classifier basis: census |
6 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| center_crop | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
frank-xwang/CLD-UnsupervisedLearning/lib/custom_transforms.py code served (permissive licence) · get_code("693513ff2d202308") 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, 2, 0) 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.
|
| conv1x1 | Ran ran; our contract draft was wrong, not the code |
frank-xwang/CLD-UnsupervisedLearning/infomin/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 |
frank-xwang/CLD-UnsupervisedLearning/infomin/resnet.py code served (permissive licence) · get_code("160bb14bd76201b4") 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.
|
| get_scheduler | Ran ran on a synthesized input |
frank-xwang/CLD-UnsupervisedLearning/lib/lr_scheduler.py code served (permissive licence) · get_code("d4783c4a6100b3cc") 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 GradualWarmupScheduler. 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.
|
| random_num_generator | Ran ran, honoured the contract we drafted |
frank-xwang/CLD-UnsupervisedLearning/lib/custom_transforms.py code served (permissive licence) · get_code("abf95b2d2f20e322") 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.
|
| to_tensor | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
frank-xwang/CLD-UnsupervisedLearning/lib/custom_transforms.py code served (permissive licence) · get_code("382714b2c227ba48") 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, 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.
|
| accuracy | Not yet run unverified (harvested, no recorded run) |
frank-xwang/CLD-UnsupervisedLearning/main_imagenet_moco_cld.py pointer only (licence: MIT); the stored copy get_code serves, from zbh2047/clipping-algorithms, is pointer only (licence: NONE) · get_code("9b8289076669fe4f") 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 zbh2047/clipping-algorithms, 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. No invocation recorded. |
| resnet18 | Not yet run unverified (harvested, no recorded run) |
frank-xwang/CLD-UnsupervisedLearning/infomin/resnet.py code served (permissive licence) · get_code("2985b79b38118299") 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 (7 with at least one paper dated earlier, 4 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 |
|---|---|---|---|
| conv1x1 | 431 other papers 93 dated earlier, 3 the same month, 334 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 |
| conv3x3 | 312 other papers 49 dated earlier, 3 the same month, 259 later, 1 undated · 31 only as an assembly brick |
1409.1556 (2014-09) Very Deep Convolutional Networks for Large-Scale Image Recognition |
1507.05717 (2015-07) An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition 1512.03385 (2015-12) Deep Residual Learning for Image Recognition and 309 more not named here |
| resnet18 | 95 other papers 17 dated earlier, 2 the same month, 75 later, 1 undated |
1805.00907 (2018-05) Glow: Graph Lowering Compiler Techniques for Neural Networks |
1902.08153 (2019-02) Learned Step Size Quantization 1904.01355 (2019-04) FCOS: Fully Convolutional One-Stage Object Detection and 92 more not named here |
| accuracy | 80 other papers 43 dated earlier, 2 the same month, 35 later |
1307.0414 (2013-07) Challenges in Representation Learning: A report on three machine learning contests |
1412.6553 (2014-12) Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition 1503.02531 (2015-03) Distilling the Knowledge in a Neural Network and 77 more not named here |
| center_crop | 2 other papers 1 dated earlier, 1 later |
1904.01990 (2019-04) Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification |
2105.01289 (2021-05) Representation Learning for Clustering via Building Consensus |
| random_num_generator | 2 other papers 1 dated earlier, 1 later |
1904.01990 (2019-04) Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification |
2105.01289 (2021-05) Representation Learning for Clustering via Building Consensus |
| to_tensor | 2 other papers 1 dated earlier, 1 later |
1904.01990 (2019-04) Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification |
2105.01289 (2021-05) Representation Learning for Clustering via Building Consensus |
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.
Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets. However, natural data could be highly correlated and long-tail distributed. Natural between-instance similarity conflicts with the presumed instance distinction, causing unstable training and poor performance. Our idea is to discover and integrate between-instance similarity into contrastive learning, not directly by instance grouping, but by cross-level discrimination (CLD) between instances and local instance groups. While invariant mapping of each instance is imposed by attraction within its augmented views, between-instance similarity could emerge from common repulsion against instance groups. Our batch-wise and cross-view comparisons also greatly improve the positive/negative sample ratio of contrastive learning and achieve better invariant mapping. To effect both grouping and discrimination objectives, we impose them on features separately derived from a shared representation. In addition, we propose normalized projection heads and unsupervised hyper-parameter tuning for the first time. Our extensive experimentation demonstrates that CLD is a lean and powerful add-on to existing methods such as NPID, MoCo, InfoMin, and BYOL on highly correlated, long-tail, or balanced datasets. It not only achieves new state-of-the-art on self-supervision, semi-supervision, and transfer learning benchmarks, but also beats MoCo v2 and SimCLR on every reported performance attained with a much larger compute. CLD effectively brings unsupervised learning closer to natural data and real-world applications. Our code is publicly available at: https://github.com/frank-xwang/CLD-UnsupervisedLearning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2008.03813")
get_code_for_paper("2008.03813")
have("2008.03813")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2008.03813.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2008.03813)
Connect an agent — have() is free.