SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.01384 · ICLR · 2023

DAVA: Disentangling Adversarial Variational Autoencoder

Roger Wattenhofer, Benjamin Estermann

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 1 no recorded run), measured 2026-11-22; 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/2303.01384.json · badge: /api/ran/2303.01384.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
besterma/dava canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
pipe_accuracy Ran
ran; our contract draft was wrong, not the code
besterma/dava/pipe/pipe_metric.py
code served (permissive licence) · get_code("7da2b16c46313169")
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 tuple. 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
from torch.utils.data import TensorDataset
import numpy as np

torch.manual_seed(0)

# Create small test datasets
# Images are 64x64 as expected by ConvDiscriminator
batch_size = 2
num_channels = 3
num_samples_train = 10
num_samples_eval = 6
num_samples_test = 4

# Create dummy image data (batch_size, num_channels, 64, 64)
train_images = torch.randn(num_samples_train, num_channels, 64, 64)
train_labels = torch.randint(0, 2, (num_samples_train, 1)).float()
train_dataset = TensorDataset(train_images, train_labels)

eval_images = torch.randn(num_samples_eval, num_channels, 64, 64)
eval_labels = torch.randint(0, 2, (num_samples_eval, 1)).float()
eval_dataset = TensorDataset(eval_images, eval_labels)

test_images = torch.randn(num_samples_test, num_channels, 64, 64)
test_labels = torch.randint(0, 2, (num_samples_test, 1)).float()
test_dataset = TensorDataset(test_images, test_labels)

# Create random state object
random_state = np.random.RandomState(42)

ARGS = {
    'train_dataset': train_dataset,
    'eval_dataset': eval_dataset,
    'test_dataset': test_dataset,
    'num_channels': num_channels,
    'batch_size': batch_size,
    'random_state': random_state,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
pipe_overall_accuracy Not yet run
unverified (harvested, no recorded run)
besterma/dava/pipe/pipe_metric.py
code served (permissive licence) · get_code("fd69e0779c0fe487")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

The use of well-disentangled representations offers many advantages for downstream tasks, e.g. an increased sample efficiency, or better interpretability. However, the quality of disentangled interpretations is often highly dependent on the choice of dataset-specific hyperparameters, in particular the regularization strength. To address this issue, we introduce DAVA, a novel training procedure for variational auto-encoders. DAVA completely alleviates the problem of hyperparameter selection. We compare DAVA to models with optimal hyperparameters. Without any hyperparameter tuning, DAVA is competitive on a diverse range of commonly used datasets. Underlying DAVA, we discover a necessary condition for unsupervised disentanglement, which we call PIPE. We demonstrate the ability of PIPE to positively predict the performance of downstream models in abstract reasoning. We also thoroughly investigate correlations with existing supervised and unsupervised metrics. The code is available at github.com/besterma/dava.

For agents

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

get_harvested_code_for_paper("2303.01384")
get_code_for_paper("2303.01384")
have("2303.01384")

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

curl https://syntology.ai/api/ran/2303.01384.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.01384.svg)](https://syntology.ai/paper/2303.01384)

Connect an agent — have() is free.