SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.00104 · 2018

Learning Disentangled Joint Continuous and Discrete Representations

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 3 have no contract verdict; 0 failures of our instrument; 1 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/1804.00104.json · badge: /api/ran/1804.00104.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
Schlumberger/joint-vae canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
get_dsprites_dataloader Ran
ran on a synthesized input
Schlumberger/joint-vae/utils/dataloaders.py
code served (permissive licence) · get_code("6d2c1302c513a81a")
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 DataLoader. 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 numpy as np
import torch
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
import tempfile
import os

torch.manual_seed(0)

# Create a minimal mock dsprites data file
temp_dir = tempfile.mkdtemp()
path_to_data = os.path.join(temp_dir, 'dsprites_data.npz')

# Create minimal mock data: small array of shape (4, 64, 64) for 4 images of 64x64
mock_imgs = np.random.rand(4, 64, 64).astype(np.float32)
np.savez(path_to_data, imgs=mock_imgs)

ARGS = {
    'batch_size': 2,
    'path_to_data': path_to_data,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
get_fashion_mnist_dataloaders Ran
ran on a synthesized input
Schlumberger/joint-vae/utils/dataloaders.py
code served (permissive licence) · get_code("ba3c4178dccd9c02")
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 float; 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 torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
import tempfile
import os

torch.manual_seed(0)

# Create a minimal mock FashionMNIST dataset to avoid actual downloads
class MockFashionMNIST(Dataset):
    def __init__(self, root, train=True, download=False, transform=None):
        self.train = train
        self.transform = transform
        self.data = torch.randint(0, 256, (10, 28, 28), dtype=torch.uint8)
        self.targets = torch.randint(0, 10, (10,))
    
    def __len__(self):
        return len(self.data)
    
    def __getitem__(self, idx):
        img = self.data[idx]
        if self.transform:
            img = self.transform(img)
        return img, self.targets[idx].item()

# Monkey-patch datasets.FashionMNIST to use our mock
import torchvision.datasets as datasets_module
original_fashion_mnist = datasets_module.FashionMNIST
datasets_module.FashionMNIST = MockFashionMNIST

# Create a temporary directory for the path_to_data
temp_dir = tempfile.mkdtemp()

ARGS = {
    'batch_size': 2,
    'path_to_data': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — 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 float — 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
reorder_img Ran
ran on a synthesized input
Schlumberger/joint-vae/viz/visualize.py
code served (permissive licence) · get_code("6d5ba5e6bc0a68ec")
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 3, dtype family float, shape (3, 70, 36) 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)

# Create a small original image tensor
# Shape: (channels, height, width)
# The function expects this to be a grid image created by make_grid
# with padding applied, so it will be larger than img_size
channels, height, width = 3, 32, 32
padding = 2

# Create a grid-like image with 2 rows of images
# Each image is 32x32, with padding of 2 between them
# Total dimensions: 3 channels, (2 * 32 + 3 * 2) height, (1 * 32 + 2 * 2) width
# = (3, 70, 36) for a 2x1 grid
grid_height = 2 * (height + padding) + padding  # 70
grid_width = width + 2 * padding  # 36

orig_img = torch.randn(channels, grid_height, grid_width)

# Define a reorder list - permutation of row indices
reorder = [1, 0]  # Swap the two rows

# Define image size following pytorch convention
img_size = (channels, height, width)

ARGS = {
    "orig_img": orig_img,
    "reorder": reorder,
    "by_row": True,
    "img_size": img_size,
    "padding": padding
}
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 3, dtype family float, shape (3, 70, 36) — shape (3, 70, 36) 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_mnist_dataloaders Not yet run
unverified (harvested, no recorded run)
Schlumberger/joint-vae/utils/dataloaders.py
code served (permissive licence) · get_code("bdf803549274d512")
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, 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 4 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

We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed discrete distribution and controlling the amount of information encoded in each latent unit, we show how continuous and categorical factors of variation can be discovered automatically from data. Experiments show that the framework disentangles continuous and discrete generative factors on various datasets and outperforms current disentangling methods when a discrete generative factor is prominent.

For agents

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

get_harvested_code_for_paper("1804.00104")
get_code_for_paper("1804.00104")
have("1804.00104")

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

curl https://syntology.ai/api/ran/1804.00104.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.00104.svg)](https://syntology.ai/paper/1804.00104)

Connect an agent — have() is free.