SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.04296 · 2020

High-Fidelity Synthesis with Disentangled Representation

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2001.04296.json · badge: /api/ran/2001.04296.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
1Konny/idgan canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
rosinality/id-gan-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
d_logistic_loss Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from phymhan/stylegan2-pytorch
pointer only · get_code("3651db4e5ae8d189")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

d_r1_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rosinality/id-gan-pytorch/train_gan.py
code served (permissive licence) · get_code("0693ac46c6c25e65")
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
from torch import nn, autograd, optim

torch.manual_seed(0)

# Create a small batch of fake images with requires_grad=True
batch_size = 2
img_channels = 3
img_height = 4
img_width = 4

real_img = torch.randn(
    batch_size, img_channels, img_height, img_width,
    requires_grad=True,
    dtype=torch.float32
)

# Create a discriminator-like model that outputs predictions
class SimpleDiscriminator(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 8, kernel_size=3, padding=1)
        self.pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Linear(8, 1)
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.pool(x)
        x = x.view(x.shape[0], -1)
        x = self.fc(x)
        return x

discriminator = SimpleDiscriminator()
real_pred = discriminator(real_img)

ARGS = {
    "real_pred": real_pred,
    "real_img": real_img,
}
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
data_sampler Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from phymhan/stylegan2-pytorch
pointer only · get_code("dbb756dcd778f52f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

kl_loss Ran
ran, honoured the contract we drafted
rosinality/id-gan-pytorch/train_vae.py
code served (permissive licence) · get_code("6a6e7e5aadc14e95")
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)

# Construct valid arguments for kl_loss function
# The function expects:
# - mean: a tensor that supports .pow(2) operation
# - logvar: a tensor that supports torch.exp() operation
# Both tensors are used with .sum(1).mean(0), so they need shape (batch, dim)

batch_size = 2
dim = 4

mean = torch.randn(batch_size, dim)
logvar = torch.randn(batch_size, dim)

ARGS = {
    "mean": mean,
    "logvar": logvar,
}
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
recon_loss Ran
ran, honoured the contract we drafted
rosinality/id-gan-pytorch/train_vae.py
code served (permissive licence) · get_code("37c03b5191a499f8")
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
import torch.nn as nn

torch.manual_seed(0)

# The function takes two tensors: out and target
# Both are used with F.mse_loss which expects same shape
# target.shape[0] is accessed to get batch size
# So we need two tensors of the same shape

batch_size = 2
feature_dim = 4

out = torch.randn(batch_size, feature_dim)
target = torch.randn(batch_size, feature_dim)

ARGS = {
    'out': out,
    'target': target
}
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
str2bool Ran
ran, violated the contract we drafted
1Konny/idgan/dvae_main.py
pointer only (licence: NONE) · get_code("f017532fc389cbfe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1Konny/idgan 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
str2bool 82 other papers
30 dated earlier, 2 the same month, 50 later
1510.03055 (2015-10)
A Diversity-Promoting Objective Function for Neural Conversation Models
1703.06490 (2017-03)
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
1710.10467 (2017-10)
Generalized End-to-End Loss for Speaker Verification
and 79 more not named here
data_sampler 13 other papers
1 dated earlier, 12 later
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
2106.11485 (2021-06)
Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis
and 10 more not named here
d_logistic_loss 12 other papers
2 dated earlier, 10 later
1910.05852 (2019-10)
Implicit competitive regularization in GANs
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN
2106.11485 (2021-06)
Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis
and 9 more not named here
d_r1_loss 3 other papers
3 later
2106.11485 (2021-06)
Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis
2203.16521 (2022-03)
CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs
2203.17266 (2022-03)
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

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

Learning disentangled representation of data without supervision is an important step towards improving the interpretability of generative models. Despite recent advances in disentangled representation learning, existing approaches often suffer from the trade-off between representation learning and generation performance i.e. improving generation quality sacrifices disentanglement performance). We propose an Information-Distillation Generative Adversarial Network (ID-GAN), a simple yet generic framework that easily incorporates the existing state-of-the-art models for both disentanglement learning and high-fidelity synthesis. Our method learns disentangled representation using VAE-based models, and distills the learned representation with an additional nuisance variable to the separate GAN-based generator for high-fidelity synthesis. To ensure that both generative models are aligned to render the same generative factors, we further constrain the GAN generator to maximize the mutual information between the learned latent code and the output. Despite the simplicity, we show that the proposed method is highly effective, achieving comparable image generation quality to the state-of-the-art methods using the disentangled representation. We also show that the proposed decomposition leads to an efficient and stable model design, and we demonstrate photo-realistic high-resolution image synthesis results (1024x1024 pixels) for the first time using the disentangled representations.

For agents

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

get_harvested_code_for_paper("2001.04296")
get_code_for_paper("2001.04296")
have("2001.04296")

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

curl https://syntology.ai/api/ran/2001.04296.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.04296.svg)](https://syntology.ai/paper/2001.04296)

Connect an agent — have() is free.