Andrew Bagdanov, Ming-Ming Cheng, Ke Li, Xialei Liu, Yu-Song Hu, Xu-Sheng Cao
2 of 3 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 0 have no contract verdict; 2 failures of our instrument; 1 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/2210.00266.json · badge: /api/ran/2210.00266.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 |
|---|---|---|
| xialeiliu/Long-Tailed-CIL | canonical (classifier label) classifier basis not recorded on the link |
2 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| last_layer_analysis | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
xialeiliu/Long-Tailed-CIL/src/last_layer_analysis.py code served (permissive licence) · get_code("2e179edce79cd470") 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.
|
| mixup_data | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
xialeiliu/Long-Tailed-CIL/src/approach/LAS_utils.py code served (permissive licence) · get_code("345e624f9cc2e32a") 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 tuple. 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 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.
|
| mixup_criterion | Not yet run unverified (harvested, no recorded run) |
xialeiliu/Long-Tailed-CIL/src/approach/LAS_utils.py code served (permissive licence) · get_code("0016935c9f13abf7") How it ranno invocation recorded. |
Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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 |
|---|---|---|---|
| mixup_data | 12 other papers 5 dated earlier, 6 later, 1 same year, order not determinable |
1908.09699 (2019-08) Gated Convolutional Networks with Hybrid Connectivity for Image Classification |
2102.13280 (2021-02) MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures 2104.00466 (2021-04) Improving Calibration for Long-Tailed Recognition and 9 more not named here |
| last_layer_analysis | 6 other papers 3 dated earlier, 2 later, 1 same year, order not determinable |
2112.04731 (2021-12) Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning |
Shi_Mimicking_the_Oracle_An_Initial_Phase_Decorrelation_Approach_for_Class_CVPR_2022_paper (2022 (year only)) Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning 2201.12559 (2022-01) Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning and 3 more not named here |
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.
In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of long-tailed distributions in the real world. In this work we propose two long-tailed CIL scenarios, which we term ordered and shuffled LT-CIL. Ordered LT-CIL considers the scenario where we learn from head classes collected with more samples than tail classes which have few. Shuffled LT-CIL, on the other hand, assumes a completely random long-tailed distribution for each task. We systematically evaluate existing methods in both LT-CIL scenarios and demonstrate very different behaviors compared to conventional CIL scenarios. Additionally, we propose a two-stage learning baseline with a learnable weight scaling layer for reducing the bias caused by long-tailed distribution in LT-CIL and which in turn also improves the performance of conventional CIL due to the limited exemplars. Our results demonstrate the superior performance (up to 6.44 points in average incremental accuracy) of our approach on CIFAR-100 and ImageNet-Subset. The code is available at https://github.com/xialeiliu/Long-Tailed-CIL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.00266")
get_code_for_paper("2210.00266")
have("2210.00266")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2210.00266.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2210.00266)
Connect an agent — have() is free.