SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.03599 · 2018

Understanding disentangling in $β$-VAE

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 0 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/1804.03599.json · badge: /api/ran/1804.03599.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
yhy258/VariationalAutoEncoders-Pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
kngwyu/pytorch-autoencoders reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
JohanYe/Beta-VAE reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
seymayucer/VAEs reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
adityabingi/Beta-VAE reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
Knight13/beta-VAE-disentanglement reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
average_latent Ran
ran; our contract draft was wrong, not the code
yhy258/VariationalAutoEncoders-Pytorch/beta_vae_analyze.py
pointer only (licence: NONE) · get_code("7874992f2436e410")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yhy258/VariationalAutoEncoders-Pytorch 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.

bernoulli_recons Ran
ran; our contract draft was wrong, not the code
kngwyu/pytorch-autoencoders/pytorch_autoencoders/models/beta_vae.py
code served (permissive licence) · get_code("6f4f58fb5d376a74")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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)

# a: logits (unnormalized predictions), shape (batch_size, features)
# b: targets (binary labels), shape (batch_size, features)
# For binary_cross_entropy_with_logits, a is logits and b is targets in [0, 1]

a = torch.randn(2, 4)  # logits
b = torch.randint(0, 2, (2, 4)).float()  # binary targets

ARGS = {
    'a': a,
    'b': b
}
Setup block drafted by
a language model, Claude Sonnet 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 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
cuda Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
seymayucer/VAEs/train_bvae.py
pointer only (licence: NONE) · get_code("8c252d04248affd7")
How it ran

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

gaussian_recons Ran
ran; our contract draft was wrong, not the code
kngwyu/pytorch-autoencoders/pytorch_autoencoders/models/beta_vae.py
code served (permissive licence) · get_code("4453150fe0694a1d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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
from torch import Tensor

torch.manual_seed(0)

# Create two tensors with distinct shapes for clarity
# a: will be passed through sigmoid, so can be any real values
# b: should be in [0, 1] range since it's compared to sigmoid(a)
a = torch.randn(2, 4)  # batch=2, dim=4
b = torch.rand(2, 4)   # batch=2, dim=4, values in [0, 1]

ARGS = {
    'a': a,
    'b': b
}
Setup block drafted by
a language model, Claude Sonnet 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 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
get_attr_latent Ran
ran; our contract draft was wrong, not the code
yhy258/VariationalAutoEncoders-Pytorch/beta_vae_analyze.py
pointer only (licence: NONE) · get_code("07ff2bc113f3b015")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yhy258/VariationalAutoEncoders-Pytorch 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_mu_and_latents Ran
ran; our contract draft was wrong, not the code
JohanYe/Beta-VAE/utils.py
pointer only (licence: NONE) · get_code("ed6056e453ff80ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JohanYe/Beta-VAE 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.

isqrt Ran
ran, honoured the contract we drafted
JohanYe/Beta-VAE/utils.py
pointer only (licence: NONE) · get_code("e301429b60813846")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JohanYe/Beta-VAE 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.

lr_schedule Ran
ran, honoured the contract we drafted
adityabingi/Beta-VAE/vae.py
code served (permissive licence) · get_code("2dbc820f27054078")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float, 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.

ARGS = {
    'epoch': 16,
    'previous_lr': 0.001
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
parse_arguments Ran
ran; our contract draft was wrong, not the code
Knight13/beta-VAE-disentanglement/src/training_script.py
pointer only (licence: NONE) · get_code("5713ebe8202169a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Knight13/beta-VAE-disentanglement 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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 6 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
cuda 2 other papers
2 later
2309.16515 (2023-09)
Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping
2406.19298 (2024-06)
Compositional Image Decomposition with Diffusion Models
isqrt 1 other paper
1 later
2205.07015 (2022-05)
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments
lr_schedule 1 other paper
1 dated earlier
1606.05908 (2016-06)
Tutorial on Variational Autoencoders

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

We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the underlying generative factors of variation of data emerge when optimising the modified ELBO bound in $β$-VAE, as training progresses. From these insights, we propose a modification to the training regime of $β$-VAE, that progressively increases the information capacity of the latent code during training. This modification facilitates the robust learning of disentangled representations in $β$-VAE, without the previous trade-off in reconstruction accuracy.

For agents

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

get_harvested_code_for_paper("1804.03599")
get_code_for_paper("1804.03599")
have("1804.03599")

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

curl https://syntology.ai/api/ran/1804.03599.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.03599.svg)](https://syntology.ai/paper/1804.03599)

Connect an agent — have() is free.