SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01101 · 2024

Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained Models

arXiv · PDF · Open in the Atlas

Code that ran

8 of 16 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; 8 failures of our instrument; 8 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/2403.01101.json · badge: /api/ran/2403.01101.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
ZiTingW/asvp canonical (classifier label)
classifier basis: census
8 ran · 8 no recorded run
FunctionStatusWhere it lives
acquire_new_sample Ran
ran; our contract draft was wrong, not the code
ZiTingW/asvp/samplings/sampling_strategy.py
code served (permissive licence) · get_code("2d6498a587337e7f")
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 list, 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.

import torch
import numpy as np

torch.manual_seed(0)

# Create small tensors for embeddings
# emb_lab: labeled embeddings - shape (num_labeled, embedding_dim)
# emb_un: unlabeled embeddings - shape (num_unlabeled, embedding_dim)
emb_lab = [torch.randn(4) for _ in range(2)]  # 2 labeled samples, dim 4
emb_un = [torch.randn(4) for _ in range(3)]   # 3 unlabeled samples, dim 4

# Create a candidate name list matching the number of unlabeled samples
candnamelist = ['sample_0', 'sample_1', 'sample_2']

# Budget for number of samples to acquire
budget = 2

ARGS = {
    'budget': budget,
    'candnamelist': candnamelist,
    'emb_lab': emb_lab,
    'emb_un': emb_un
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
build_wideresnet Ran
ran; our contract draft was wrong, not the code
ZiTingW/asvp/wideresnet.py
code served (permissive licence) · get_code("e77d24d05a4e0945")
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 WideResNet. 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
import logging

logging.basicConfig(level=logging.INFO)

torch.manual_seed(0)

ARGS = {
    "depth": 28,
    "widen_factor": 2,
    "num_classes": 10,
    "dropout": 0.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type WideResNet — a WideResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a WideResNet 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
cal_similarity_matrix Ran
ran; our contract draft was wrong, not the code
ZiTingW/asvp/samplings/sampling_strategy.py
code served (permissive licence) · get_code("377c87f799043fa1")
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 Tensor, ndim 2, dtype family float, shape (2, 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.

import torch

torch.manual_seed(0)

# Create two small tensors with distinct dimensions
# x: batch_size=2, feature_dim=4
# y: batch_size=3, feature_dim=4
x = torch.randn(2, 4)
y = torch.randn(3, 4)

ARGS = {
    "x": x,
    "y": y,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
conv1x1 Ran
ran; our contract draft was wrong, not the code
ZiTingW/asvp/cifar_resnet_1.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
ZiTingW/asvp/cifar_resnet_1.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_augmentation Ran
ran; our contract draft was wrong, not the code
ZiTingW/asvp/dataset_model.py
code served (permissive licence) · get_code("34ff5261d4afdfc0")
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 Compose. 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
import torchvision.transforms as transforms


class Args:
    def __init__(self, dataset_name, network):
        self.dataset_name = dataset_name
        self.network = network


# Test case 1: CIFAR10 with res18 training
ARGS = {
    'args': Args(dataset_name='cifar10', network='res18'),
    'train': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
mish Ran
ran; our contract draft was wrong, not the code
ZiTingW/asvp/wideresnet.py
pointer only (licence: MIT); the stored copy get_code serves, from zhouzihao11/CCL, is pointer only (licence: NONE) · get_code("0a7c46eb67c0c21b")
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 zhouzihao11/CCL, 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.

random_select Ran
ran; our contract draft was wrong, not the code
ZiTingW/asvp/samplings/sampling_strategy.py
code served (permissive licence) · get_code("2ee652aad421911f")
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 list, ndim 1, dtype family int; 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.

import numpy as np

# The function random_select takes:
# - budget: an integer representing how many samples to select
# - unlbl_idx: a list/array of unlabeled indices from which to randomly select

# From reading the function body:
# - budget is used as the size parameter for np.random.randint
# - unlbl_idx is used with len() to get its length
# - The function generates random integers in range [0, len(unlbl_idx) - 1]

# Create a small unlabeled index list
unlbl_idx = [10, 20, 30, 40, 50]  # 5 unlabeled indices

# Set budget to be less than len(unlbl_idx)
budget = 3

ARGS = {
    "budget": budget,
    "unlbl_idx": unlbl_idx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
ActiveFT_sampling Not yet run
unverified (harvested, no recorded run)
ZiTingW/asvp/samplings/ActiveFT_large.py
code served (permissive licence) · get_code("837c0c109950edce")
How it ran

no invocation recorded.

cal_margin Not yet run
unverified (harvested, no recorded run)
ZiTingW/asvp/utils.py
code served (permissive licence) · get_code("a1029bcd6705dd33")
How it ran

no invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
ZiTingW/asvp/dataset_model.py
code served (permissive licence) · get_code("9e23617191c77742")
How it ran

no invocation recorded.

get_network Not yet run
unverified (harvested, no recorded run)
ZiTingW/asvp/dataset_model.py
code served (permissive licence) · get_code("38cab0512e17b5ae")
How it ran

no invocation recorded.

get_output_emb Not yet run
unverified (harvested, no recorded run)
ZiTingW/asvp/utils.py
code served (permissive licence) · get_code("48673224d1ac5369")
How it ran

no invocation recorded.

get_pre_prob Not yet run
unverified (harvested, no recorded run)
ZiTingW/asvp/utils.py
code served (permissive licence) · get_code("036dbc7c1406eda7")
How it ran

no invocation recorded.

optimize_dist Not yet run
unverified (harvested, no recorded run)
ZiTingW/asvp/samplings/ActiveFT_large.py
code served (permissive licence) · get_code("898aaed7fcdee3c5")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
ZiTingW/asvp/cifar_resnet_1.py
code served (permissive licence) · get_code("173186b53d3ab9a3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 4 later) and 12 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
330 dated earlier, 13 the same month, 77 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
226 dated earlier, 11 the same month, 64 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
mish 15 other papers
11 dated earlier, 2 later, 2 same year, order not determinable
1908.00821 (2019-08)
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2105.14148 (2021-05)
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
and 12 more not named here
resnet18 6 other papers
3 dated earlier, 1 the same month, 2 later
1802.10026 (2018-02)
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
2206.07290 (2022-06)
Differentiable Top-k Classification Learning
2301.11578 (2023-01)
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
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.

Repositories linked to this paper

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

Abstract

Fine-tuning the pre-trained model with active learning holds promise for reducing annotation costs. However, this combination introduces significant computational costs, particularly with the growing scale of pre-trained models. Recent research has proposed proxy-based active learning, which pre-computes features to reduce computational costs. Yet, this approach often incurs a significant loss in active learning performance, sometimes outweighing the computational cost savings. This paper demonstrates that not all sample selection differences result in performance degradation. Furthermore, we show that suitable training methods can mitigate the decline of active learning performance caused by certain selection discrepancies. Building upon detailed analysis, we propose a novel method, aligned selection via proxy, which improves proxy-based active learning performance by updating pre-computed features and selecting a proper training method. Extensive experiments validate that our method improves the total cost of efficient active learning while maintaining computational efficiency. The code is available at \url{https://github.com/ZiTingW/asvp}.

For agents

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

get_harvested_code_for_paper("2403.01101")
get_code_for_paper("2403.01101")
have("2403.01101")

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

curl https://syntology.ai/api/ran/2403.01101.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.01101.svg)](https://syntology.ai/paper/2403.01101)

Connect an agent — have() is free.