SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.07514 · 2020

Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 1 has no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2002.07514.json · badge: /api/ran/2002.07514.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
asperti/BalancingVAE canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
lovelyscientist/rna-seq-vae community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
get_expressions Ran
ran on a synthesized input
lovelyscientist/rna-seq-vae/gtex_loader.py
code served (permissive licence) · get_code("f5002f45f9802d08")
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 DataFrame. 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 pandas as pd
import tempfile
import os

# Create a small temporary parquet file for testing
temp_dir = tempfile.mkdtemp()
parquet_path = os.path.join(temp_dir, 'test_expressions.parquet')

# Create a small dataframe with 'Name' as a column
df = pd.DataFrame({
    'Name': ['GENE1', 'GENE2', 'GENE3'],
    'sample1': [1.5, 2.3, 0.8],
    'sample2': [2.1, 1.9, 3.2],
    'sample3': [0.9, 2.5, 1.1]
})

# Save as parquet
df.to_parquet(parquet_path, index=False)

ARGS = {
    'path': parquet_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas, pyarrow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
idx2onehot Ran
ran; our contract draft was wrong, not the code
lovelyscientist/rna-seq-vae/torch_model.py
pointer only (licence: MIT); the stored copy get_code serves, from SAIC-MONTREAL/multimodal-dynamics, is pointer only (licence: NOASSERTION) · get_code("a5ea53bdbdb19025")
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 SAIC-MONTREAL/multimodal-dynamics, 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. A run is recorded.

unpickle Ran
ran; our contract draft was wrong, not the code
asperti/BalancingVAE/computed_gamma.py
pointer only (licence: NONE) · get_code("38ed4e3667407885")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, asperti/BalancingVAE 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.

get_samples Not yet run
unverified (harvested, no recorded run)
lovelyscientist/rna-seq-vae/gtex_loader.py
code served (permissive licence) · get_code("42e0c9a532dc4421")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
idx2onehot 1 other paper
1 later
2101.04454 (2021-01)
Learning Intuitive Physics with Multimodal Generative Models

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 2026-11-21.

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 the loss function of Variational Autoencoders there is a well known tension between two components: the reconstruction loss, improving the quality of the resulting images, and the Kullback-Leibler divergence, acting as a regularizer of the latent space. Correctly balancing these two components is a delicate issue, easily resulting in poor generative behaviours. In a recent work, Dai and Wipf obtained a sensible improvement by allowing the network to learn the balancing factor during training, according to a suitable loss function. In this article, we show that learning can be replaced by a simple deterministic computation, helping to understand the underlying mechanism, and resulting in a faster and more accurate behaviour. On typical datasets such as Cifar and Celeba, our technique sensibly outperforms all previous VAE architectures.

For agents

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

get_harvested_code_for_paper("2002.07514")
get_code_for_paper("2002.07514")
have("2002.07514")

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

curl https://syntology.ai/api/ran/2002.07514.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.07514.svg)](https://syntology.ai/paper/2002.07514)

Connect an agent — have() is free.