Yibo Yang, Philip Torr, Dacheng Tao, Zhouchen Lin, Bernard Ghanem, Xiangtai Li, Haobo Yuan, Jianlong Wu, Lefei Zhang
1 of 1 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; 1 failure 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/2308.01746.json · badge: /api/ran/2308.01746.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 |
|---|---|---|
| NeuralCollapseApplications/FSCIL | canonical (classifier label) classifier basis not recorded on the link |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| get_test_loader_cfg | Ran ran; our contract draft was wrong, not the code |
NeuralCollapseApplications/FSCIL/mmfscil/apis/fscil.py pointer only (licence: NONE); the stored copy get_code serves, from xiaojieli0903/mamba-fscil, is pointer only (licence: NONE) · get_code("742767e6f63f427e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, NeuralCollapseApplications/FSCIL 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. |
Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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 |
|---|---|---|---|
| get_test_loader_cfg | 1 other paper 1 later |
2407.06136 (2024-07) Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning |
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.
Class incremental learning (CIL) seeks to learn a model with new classes being encountered incrementally. How to enable learnability for new classes while keeping the capability well on old classes has been a crucial challenge for this task. Beyond the normal case, long-tail class incremental learning (LTCIL) and few-shot class incremental learning (FSCIL) are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world implementations and further exacerbate the well-known problem of catastrophic forgetting. Existing methods are specifically proposed for one of the three tasks, trying to induce enough margin between the new-class and old-class prototypes and prevent a drastic drift of backbone features when each new session comes in. However, this would inevitably cause a misalignment between the feature and prototype of old classes, which explains the origin of catastrophic forgetting. In this paper, inspired by neural collapse that reveals an optimal feature-classifier geometric structure in classification, we offer a unified solution to the misalignment dilemma in the three tasks. Concretely, we propose neural collapse terminus that is a fixed structure with the maximal equiangular inter-class separation for the whole label space. It serves as a consistent target throughout the incremental training to avoid dividing the feature space incrementally. For CIL and LTCIL, we further propose a prototype evolving scheme to drive the backbone features into our neural collapse terminus smoothly. Our method also works for FSCIL with only minor adaptations. Theoretical analysis indicates that our method holds the neural collapse optimality in an incremental fashion regardless of data imbalance or data scarcity. We also design a generalized case where we do not know the total number of classes and whether the data distribution is normal, long-tail, or few-shot for each coming session, to test the generalizability of our method. Extensive experiments with multiple datasets are conducted to demonstrate the effectiveness of our unified solution to all the three tasks and the generalized case. Code address: https://github.com/NeuralCollapseApplications/UniCIL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2308.01746")
get_code_for_paper("2308.01746")
have("2308.01746")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2308.01746.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2308.01746)
Connect an agent — have() is free.