SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.01402 · 2022

GALAXY: Graph-based Active Learning at the Extreme

arXiv · PDF · Open in the Atlas

Code that ran

8 of 13 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 8 have no contract verdict; 0 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/2202.01402.json · badge: /api/ran/2202.01402.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
jifanz/GALAXY canonical (classifier label)
classifier basis not recorded on the link
8 ran · 5 no recorded run
FunctionStatusWhere it lives
addNoise Ran
ran on a synthesized input
jifanz/GALAXY/src/bait/dataset.py
code served (permissive licence) · get_code("b0847d1659daee3b")
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 1, dtype family float, shape (6,) 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
import numpy as np

torch.manual_seed(0)

# Create a small tensor of labels
# The function calls .numpy() on labels, so it must be a torch tensor
# Max label value should be at least 2 (since noiseLabels=[1,2] by default)
# and we want to test with some variety, so let's use labels from 0-3
labels = torch.tensor([0, 1, 2, 3, 1, 2], dtype=torch.long)

ARGS = {
    "labels": labels,
    "noiseLabels": [1, 2],
    "noiseCeil": 0.5
}
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 Tensor, ndim 1, dtype family float, shape (6,) — shape (6,) 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
bisection_query Ran
ran on a synthesized input
jifanz/GALAXY/src/s2algorithm.py
code served (permissive licence) · get_code("e3a6a001b0bf99b9")
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 tuple, 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

class Node:
    def __init__(self, idx):
        self.idx = idx

class Graph:
    def __init__(self, has_path=True):
        self.has_path = has_path
        self.not_queried = [Node(0), Node(1), Node(2)]
    
    def shortest_shortest_path(self):
        if self.has_path:
            # Return a path with more than 2 nodes
            path = [Node(10), Node(11), Node(12), Node(13)]
            return (5, path)
        else:
            # Return None path
            return (None, None)

# Create a graph instance with a valid path
graph = Graph(has_path=True)

ARGS = {
    "graph": graph
}
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 tuple, ndim 1, dtype family int — a tuple 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
get_net Ran
ran on a synthesized input
jifanz/GALAXY/src/bait/model.py
code served (permissive licence) · get_code("98b6004d6b335def")
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 type. 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 = {
    'name': 'MNIST'
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
s2query Ran
ran on a synthesized input
jifanz/GALAXY/src/s2algorithm.py
code served (permissive licence) · get_code("b5956e564ee9813e")
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 int, ndim 0, dtype family int, shape () 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 numpy as np

class Node:
    def __init__(self, idx):
        self.idx = idx

class Graph:
    def __init__(self, has_path=True):
        self.has_path = has_path
        self.not_queried = [Node(0), Node(1), Node(2)]
    
    def shortest_shortest_path(self):
        if self.has_path:
            # Return a path with length > 2
            path = [Node(10), Node(11), Node(12), Node(13)]
            return (0, path)
        else:
            # Return None for path to trigger not_queried selection
            return (float('inf'), None)

# Create test graph with a valid path
graph = Graph(has_path=True)

ARGS = {
    "graph": graph
}
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 int, ndim 0, dtype family int, shape () — shape () 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
to_one_hot Ran
ran on a synthesized input
jifanz/GALAXY/src/utils.py
code served (permissive licence) · get_code("66cbf99986b3da82")
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, 5) as a later run recorded it. 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, 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)

# Analyze the function:
# - label: needs .size(0) method (tensor), indexed with torch.arange and label % num
# - num: integer for modulo and one-hot dimension

# Create a small label tensor with batch size 2
label = torch.tensor([0, 3], dtype=torch.long)

# num should be larger than max label value to avoid all modulo collisions
num = 5

ARGS = {
    "label": label,
    "num": num
}
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, 5) — shape (2, 5) 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
train_logistic Ran
ran on a synthesized input
jifanz/GALAXY/src/model.py
code served (permissive licence) · get_code("6eb8ac0511ca08d1")
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 LogisticRegression. 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small training data
batch_size = 2
in_features = 4

train_features = torch.randn(batch_size, in_features)
train_labels = torch.randint(0, 2, (batch_size,)).float()

ARGS = {
    "train_features": train_features,
    "train_labels": train_labels,
    "half": False,
    "plot": False,
    "num_epoch": 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LogisticRegression — a LogisticRegression output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LogisticRegression 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
train_mlp Ran
ran on a synthesized input
jifanz/GALAXY/src/model.py
code served (permissive licence) · get_code("1b185a681d4660a3")
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 MLPClassification. 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small dummy tensors for training
# train_features: shape (batch, channels, height, width) for images
# The model expects flattened input of size 3*32*32 = 3072
batch_size = 2
num_classes = 3

# Create random image features (2 samples, 3 channels, 32x32)
train_features = torch.randn(batch_size, 3, 32, 32)

# Create random labels for multi-class (0, 1, or 2)
train_labels = torch.randint(0, num_classes, (batch_size,))

ARGS = {
    "train_features": train_features,
    "train_labels": train_labels,
    "plot": False,
    "num_epoch": 2,
    "batch_size": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MLPClassification — a MLPClassification output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MLPClassification 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
train_shallow Ran
ran on a synthesized input
jifanz/GALAXY/src/model.py
code served (permissive licence) · get_code("1fccb315ac2b373c")
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 ShallowNet. 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.

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

torch.manual_seed(0)

# Create small sample data
batch_size = 2
num_features = 4

train_features = torch.randn(batch_size, num_features)
train_labels = torch.randint(0, 2, (batch_size,)).float()

ARGS = {
    'train_features': train_features,
    'train_labels': train_labels,
    'half': False,
    'plot': False,
    'num_epoch': 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ShallowNet — a ShallowNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ShallowNet 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
channel_f2l Not yet run
unverified (harvested, no recorded run)
jifanz/GALAXY/src/utils.py
code served (permissive licence) · get_code("95f52c73b6403ed0")
How it ran

no invocation recorded.

channel_l2f Not yet run
unverified (harvested, no recorded run)
jifanz/GALAXY/src/utils.py
code served (permissive licence) · get_code("8ddc55cc5bccaa1c")
How it ran

no invocation recorded.

create_linear_from_list Not yet run
unverified (harvested, no recorded run)
jifanz/GALAXY/src/linear_graph.py
code served (permissive licence) · get_code("cf3be30fafec6ae2")
How it ran

no invocation recorded.

create_rotating_linear_from_list Not yet run
unverified (harvested, no recorded run)
jifanz/GALAXY/src/linear_graph.py
code served (permissive licence) · get_code("45fea8b50fe1bae0")
How it ran

no invocation recorded.

get_MNIST Not yet run
unverified (harvested, no recorded run)
jifanz/GALAXY/src/bait/dataset.py
code served (permissive licence) · get_code("fb5187ca3ce56206")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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.

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

Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a small fraction of the overall dataset -- most of the data may be viewed as an out-of-distribution or irrelevant class. This leads to extreme class-imbalance, and our theory and methods focus on this core issue. We propose a new strategy for active learning called GALAXY (Graph-based Active Learning At the eXtrEme), which blends ideas from graph-based active learning and deep learning. GALAXY automatically and adaptively selects more class-balanced examples for labeling than most other methods for active learning. Our theory shows that GALAXY performs a refined form of uncertainty sampling that gathers a much more class-balanced dataset than vanilla uncertainty sampling. Experimentally, we demonstrate GALAXY's superiority over existing state-of-art deep active learning algorithms in unbalanced vision classification settings generated from popular datasets.

For agents

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

get_harvested_code_for_paper("2202.01402")
get_code_for_paper("2202.01402")
have("2202.01402")

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

curl https://syntology.ai/api/ran/2202.01402.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.01402.svg)](https://syntology.ai/paper/2202.01402)

Connect an agent — have() is free.