SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.00370 · 2019

Variational Adversarial Active 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 4 have no contract verdict; 5 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/1904.00370.json · badge: /api/ran/1904.00370.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
sinhasam/vaal canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
johntiger1/vaal_querying community (classifier label)
classifier basis not recorded on the link
6 ran · 5 no recorded run
FunctionStatusWhere it lives
compute_reward Ran
ran on a synthesized input
johntiger1/vaal_querying/rl_mnist.py
code served (permissive licence) · get_code("e504dc7831b960c5")
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. 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)

# Create a small args object with the required attributes
class Args:
    def __init__(self):
        self.num_classes = 5

# Create the arguments for compute_reward
curr_state = torch.randn(2, 10)  # batch_size=2, feature_dim=10 (larger than num_classes)
time_step = 0
prev_reward = torch.zeros(3)  # buffer to store previous rewards
args = Args()

ARGS = {
    "curr_state": curr_state,
    "time_step": time_step,
    "prev_reward": prev_reward,
    "args": args
}
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 tuple — a tuple output has no array shape of its own; none is 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
discount_rewards Ran
ran on a synthesized input
johntiger1/vaal_querying/rl/sample_cartpole.py
code served (permissive licence) · get_code("afbf4de704d925aa")
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 (4,) 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)

# The function takes a tensor of rewards and applies discount factor
# It expects a 1D tensor of rewards
r = torch.tensor([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "r": r
}
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 1, dtype family float, shape (4,) — shape (4,) 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
make_layers Ran
ran; our contract draft was wrong, not the code
sinhasam/vaal/vgg.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from s-huu/TurningWeaknessIntoStrength, is pointer only (licence: NONE) · get_code("eba3f5bcc6a06d36")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from s-huu/TurningWeaknessIntoStrength, 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.

make_layers Ran
ran on a synthesized input
johntiger1/vaal_querying/vgg.py
code served (permissive licence) · get_code("42d0e545c4c042c5")
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 Sequential. 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)

# cfg is a list containing either integers (channel counts) or 'M' (for MaxPool)
cfg = [64, 'M', 128, 128, 'M', 256, 256, 'M']

# batch_norm is a boolean flag
batch_norm = True

ARGS = {
    'cfg': cfg,
    'batch_norm': batch_norm,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
mode_collapse_penalty Ran
ran on a synthesized input
johntiger1/vaal_querying/rl_mnist.py
code served (permissive licence) · get_code("707a46843f0fb843")
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 0, dtype family float, 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 torch

torch.manual_seed(0)

# The function expects two distributions (probability distributions)
# represented as tensors. Based on the function body, it:
# 1. Computes element-wise difference between p_dist and q_dist
# 2. Squares each element
# 3. Sums all elements
# 
# These should be probability distributions, so they should be normalized
# tensors with values between 0 and 1 that sum to 1.

# Create two small probability distributions
p_dist = torch.tensor([0.4, 0.3, 0.2, 0.1], dtype=torch.float32)
q_dist = torch.tensor([0.25, 0.25, 0.25, 0.25], dtype=torch.float32)

ARGS = {
    "p_dist": p_dist,
    "q_dist": q_dist,
}
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 0, dtype family float, 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
vgg11 Ran
ran; our contract draft was wrong, not the code
sinhasam/vaal/vgg.py
code served (permissive licence) · get_code("c872dddd472f0138")
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 VGG. 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 vgg11 function signature is:
# def vgg11(pretrained=False, progress=True, **kwargs):
# 
# It accepts:
# - pretrained (bool)
# - progress (bool)
# - **kwargs (additional keyword arguments passed to _vgg and VGG)
#
# Looking at the body:
# - pretrained defaults to False
# - progress defaults to True
# - kwargs can include num_classes and init_weights for VGG
# - The function calls _vgg which creates a VGG model

ARGS = {
    'pretrained': False,
    'progress': True,
}
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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
vgg11 Ran
ran; our contract draft was wrong, not the code
johntiger1/vaal_querying/vgg.py
code served (permissive licence) · get_code("f6e25e358233c4bb")
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 VGG. 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 = {
    'pretrained': False,
    'progress': True,
}
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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
vgg11_bn Ran
ran; our contract draft was wrong, not the code
sinhasam/vaal/vgg.py
code served (permissive licence) · get_code("fb01d604c8bf7aa2")
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 VGG. 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 = {
    'pretrained': False,
    'progress': True,
}
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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
vgg11_bn Ran
ran; our contract draft was wrong, not the code
johntiger1/vaal_querying/vgg.py
code served (permissive licence) · get_code("2a49eb37cf4d8847")
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 VGG. 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 load_state_dict_from_url function since we can't download
def load_state_dict_from_url(url, progress=True):
    return {}

# Patch it into the module namespace
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'load_state_dict_from_url', load_state_dict_from_url)

# Define ARGS dict with all parameters for vgg11_bn
ARGS = {
    'pretrained': False,
    'progress': True,
}
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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
learn Not yet run
unverified (harvested, no recorded run)
johntiger1/vaal_querying/rl/sample_cartpole.py
code served (permissive licence) · get_code("c770702517776776")
How it ran

no invocation recorded.

plot_ci_bootstrap Not yet run
unverified (harvested, no recorded run)
johntiger1/vaal_querying/plotting_ci.py
code served (permissive licence) · get_code("55c4c9fb61cb3fc2")
How it ran

no invocation recorded.

plot_ci_manual Not yet run
unverified (harvested, no recorded run)
johntiger1/vaal_querying/plotting_ci.py
code served (permissive licence) · get_code("ae0107b83504f1a1")
How it ran

no invocation recorded.

plot_ci_normal_dist Not yet run
unverified (harvested, no recorded run)
johntiger1/vaal_querying/plotting_ci.py
code served (permissive licence) · get_code("0f3d4e81e8992278")
How it ran

no invocation recorded.

run_episode Not yet run
unverified (harvested, no recorded run)
johntiger1/vaal_querying/rl/sample_cartpole.py
code served (permissive licence) · get_code("baf11f4c9088b555")
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 12 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 3 later) and 9 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
make_layers 59 other papers
8 dated earlier, 1 the same month, 50 later
1411.4038 (2014-11)
Fully Convolutional Networks for Semantic Segmentation
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1511.05950 (2015-11)
Staleness-aware Async-SGD for Distributed Deep Learning
and 56 more not named here
vgg11 8 other papers
8 later
1905.04538 (2019-05)
Disentangling Content and Style via Unsupervised Geometry Distillation
2005.03823 (2020-05)
Blind Backdoors in Deep Learning Models
2007.07435 (2020-07)
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
and 5 more not named here
vgg11_bn 7 other papers
7 later
2005.03823 (2020-05)
Blind Backdoors in Deep Learning Models
2007.07435 (2020-07)
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
2010.11742 (2020-10)
Learning Black-Box Attackers with Transferable Priors and Query Feedback
and 4 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

Active learning aims to develop label-efficient algorithms by sampling the most representative queries to be labeled by an oracle. We describe a pool-based semi-supervised active learning algorithm that implicitly learns this sampling mechanism in an adversarial manner. Unlike conventional active learning algorithms, our approach is task agnostic, i.e., it does not depend on the performance of the task for which we are trying to acquire labeled data. Our method learns a latent space using a variational autoencoder (VAE) and an adversarial network trained to discriminate between unlabeled and labeled data. The mini-max game between the VAE and the adversarial network is played such that while the VAE tries to trick the adversarial network into predicting that all data points are from the labeled pool, the adversarial network learns how to discriminate between dissimilarities in the latent space. We extensively evaluate our method on various image classification and semantic segmentation benchmark datasets and establish a new state of the art on $\text{CIFAR10/100}$, $\text{Caltech-256}$, $\text{ImageNet}$, $\text{Cityscapes}$, and $\text{BDD100K}$. Our results demonstrate that our adversarial approach learns an effective low dimensional latent space in large-scale settings and provides for a computationally efficient sampling method. Our code is available at https://github.com/sinhasam/vaal.

For agents

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

get_harvested_code_for_paper("1904.00370")
get_code_for_paper("1904.00370")
have("1904.00370")

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

curl https://syntology.ai/api/ran/1904.00370.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.00370.svg)](https://syntology.ai/paper/1904.00370)

Connect an agent — have() is free.