SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.07446 · 2024

Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning

arXiv · PDF · Open in the Atlas

Code that ran

9 of 14 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; 9 failures of our instrument; 5 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/2409.07446.json · badge: /api/ran/2409.07446.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.

RepositoryRoleRan
vita-qzh/apart canonical (classifier label)
classifier basis: census
9 ran · 5 no recorded run
FunctionStatusWhere it lives
basic_clean Ran
ran; our contract draft was wrong, not the code
vita-qzh/apart/clip/simple_tokenizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("98f385d847636a3e")
How it ran

The 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 ltpwy/MSCI, 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.

build_transform Ran
ran; our contract draft was wrong, not the code
vita-qzh/apart/utils/data.py
pointer only (licence: MIT); the stored copy get_code serves, from sun-hailong/aaai25-mos, is pointer only (licence: NONE) · get_code("b620954495190c1a")
How it ran

The 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 sun-hailong/aaai25-mos, 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.

build_transform_coda_prompt Ran
ran; our contract draft was wrong, not the code
vita-qzh/apart/utils/data.py
pointer only (licence: MIT); the stored copy get_code serves, from sun-hailong/aaai25-mos, is pointer only (licence: NONE) · get_code("84339af3a90298e2")
How it ran

The 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 sun-hailong/aaai25-mos, 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
vita-qzh/apart/backbone/resnet.py
code served (permissive licence) · get_code("d9def42110729a85")
How it ran

Ran 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
vita-qzh/apart/backbone/resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
How it ran

Ran 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_backbone Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vita-qzh/apart/utils/inc_net.py
code served (permissive licence) · get_code("c76f0fe93ec16368")
How it ran

Ran 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 MockVisionTransformer. 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Mock the required modules that would be imported
class MockVisionTransformer(nn.Module):
    def __init__(self, num_classes, global_pool, drop_path_rate, tuning_config, pool_size, bs):
        super().__init__()
        self.num_classes = num_classes
        self.global_pool = global_pool
        self.drop_path_rate = drop_path_rate
        self.tuning_config = tuning_config
        self.pool_size = pool_size
        self.bs = bs
        self.out_dim = 768
        self.linear = nn.Linear(768, num_classes)
    
    def forward(self, x):
        return self.linear(x)
    
    def eval(self):
        return super().eval()

# Create a mock backbone module
import sys
from types import ModuleType

backbone_module = ModuleType('backbone')
vision_transformer_adapter_pool_a_module = ModuleType('vision_transformer_adapter_pool_a')

def mock_vit_base_patch16_224_adapter(num_classes, global_pool, drop_path_rate, tuning_config, pool_size, bs):
    return MockVisionTransformer(num_classes, global_pool, drop_path_rate, tuning_config, pool_size, bs)

vision_transformer_adapter_pool_a_module.vit_base_patch16_224_adapter = mock_vit_base_patch16_224_adapter
backbone_module.vision_transformer_adapter_pool_a = vision_transformer_adapter_pool_a_module

sys.modules['backbone'] = backbone_module
sys.modules['backbone.vision_transformer_adapter_pool_a'] = vision_transformer_adapter_pool_a_module

ARGS = {
    'args': {
        'backbone_type': 'vit_b16_224_adapter_pool',
        'ffn_num': 2,
        'model_name': 'apart',
        'batchwise_prompt': False,
        'nb_classes': 10,
        'pool_size': 4,
        'batch_size': 2,
    },
    'pretrained': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
backbone, easydict, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockVisionTransformer — a MockVisionTransformer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockVisionTransformer output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_pairs Ran
ran; our contract draft was wrong, not the code
vita-qzh/apart/clip/simple_tokenizer.py
code served (permissive licence) · get_code("d919ae32e5e4e616")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned set. 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.

import torch

torch.manual_seed(0)

# The function get_pairs takes a word parameter
# A word is represented as a tuple of symbols (variable-length strings)
# The function iterates through the word and creates pairs of consecutive symbols

word = ("hello", "world", "test")

ARGS = {
    "word": word
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reduce_proxies Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vita-qzh/apart/backbone/linears.py
pointer only (licence: MIT); the stored copy get_code serves, from sun-hailong/cvpr24-ease, is pointer only (licence: NONE) · get_code("4072283c98270784")
How it ran

The 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 sun-hailong/cvpr24-ease, 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.

whitespace_clean Ran
ran; our contract draft was wrong, not the code
vita-qzh/apart/clip/simple_tokenizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
How it ran

The 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 ltpwy/MSCI, 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.

build_model Not yet run
unverified (harvested, no recorded run)
vita-qzh/apart/clip/model.py
pointer only (licence: MIT); the stored copy get_code serves, from Sheldon04/NeRP, is pointer only (licence: NONE) · get_code("c47aa9e5b049a11d")
How it ran

The 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 Sheldon04/NeRP, 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.

load Not yet run
unverified (harvested, no recorded run)
vita-qzh/apart/clip/clip.py
pointer only (licence: MIT); the stored copy get_code serves, from KHU-VLL/RCORE, is pointer only (licence: NOASSERTION) · get_code("c22a78c25372b59f")
How it ran

The 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 KHU-VLL/RCORE, and GitHub could not classify the licence of that repository (NOASSERTION). 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)
vita-qzh/apart/backbone/resnet.py
code served (permissive licence) · get_code("1b21828124579725")
How it ran

no invocation recorded.

vit_base_patch16_224_adapter Not yet run
unverified (harvested, no recorded run)
vita-qzh/apart/backbone/vision_transformer_adapter_pool_a.py
code served (permissive licence) · get_code("bd3fb62877b821fb")
How it ran

no invocation recorded.

vit_base_patch16_224_in21k_adapter Not yet run
unverified (harvested, no recorded run)
vita-qzh/apart/backbone/vision_transformer_adapter_pool_a.py
code served (permissive licence) · get_code("d655a1d1645eae73")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 11 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 8 the same month, 11 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.

FunctionAlso present inEarliest-datedOthers named
conv1x1 431 other papers
381 dated earlier, 2 the same month, 37 later, 10 same year, order not determinable, 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
271 dated earlier, 1 the same month, 29 later, 10 same year, order not determinable, 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
get_pairs 258 other papers
175 dated earlier, 4 the same month, 71 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
154 dated earlier, 4 the same month, 65 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 228 more not named here
basic_clean 218 other papers
154 dated earlier, 4 the same month, 52 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 215 more not named here
build_model 119 other papers
83 dated earlier, 4 the same month, 25 later, 5 same year, order not determinable, 2 undated
1809.11096 (2018-09)
Large Scale GAN Training for High Fidelity Natural Image Synthesis
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2104.14294 (2021-04)
Emerging Properties in Self-Supervised Vision Transformers
and 116 more not named here
resnet18 95 other papers
78 dated earlier, 1 the same month, 12 later, 3 same year, order not determinable, 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
load 88 other papers
54 dated earlier, 3 the same month, 24 later, 6 same year, order not determinable, 1 undated
2203.05557 (2022-03)
Conditional Prompt Learning for Vision-Language Models
2206.01986 (2022-06)
Delving into the Openness of CLIP
2207.12819 (2022-07)
S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
and 85 more not named here
reduce_proxies 7 other papers
4 dated earlier, 3 later · 1 only as an assembly brick
2307.12045 (2023-07)
Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery
2403.12030 (2024-03)
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
2404.06622 (2024-04)
Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
and 4 more not named here
build_transform 2 other papers
1 dated earlier, 1 later
2404.06622 (2024-04)
Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
2412.09441 (2024-12)
MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning
build_transform_coda_prompt 1 other paper
1 later
2412.09441 (2024-12)
MOS: Model Surgery for Pre-Trained Model-Based 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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In our ever-evolving world, new data exhibits a long-tailed distribution, such as e-commerce platform reviews. This necessitates continuous model learning imbalanced data without forgetting, addressing the challenge of long-tailed class-incremental learning (LTCIL). Existing methods often rely on retraining linear classifiers with former data, which is impractical in real-world settings. In this paper, we harness the potent representation capabilities of pre-trained models and introduce AdaPtive Adapter RouTing (APART) as an exemplar-free solution for LTCIL. To counteract forgetting, we train inserted adapters with frozen pre-trained weights for deeper adaptation and maintain a pool of adapters for selection during sequential model updates. Additionally, we present an auxiliary adapter pool designed for effective generalization, especially on minority classes. Adaptive instance routing across these pools captures crucial correlations, facilitating a comprehensive representation of all classes. Consequently, APART tackles the imbalance problem as well as catastrophic forgetting in a unified framework. Extensive benchmark experiments validate the effectiveness of APART. Code is available at: https://github.com/vita-qzh/APART

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.07446")
get_code_for_paper("2409.07446")
have("2409.07446")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2409.07446.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2409.07446.svg)](https://syntology.ai/paper/2409.07446)

Connect an agent — have() is free.