SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1707.05776 · 2017

Optimizing the Latent Space of Generative Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 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/1707.05776.json · badge: /api/ran/1707.05776.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
tneumann/minimal_glo reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
build_gauss_kernel Ran
ran, honoured the contract we drafted
tneumann/minimal_glo/glo.py
code served (permissive licence) · get_code("13ffe0806ff12380")
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 4, dtype family float, shape (1, 1, 5, 5) as a later run recorded it. 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, 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 numpy as np
import torch
from torch.autograd import Variable

torch.manual_seed(0)

ARGS = {
    "size": 5,
    "sigma": 1.0,
    "n_channels": 1,
    "cuda": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (1, 1, 5, 5) — shape (1, 1, 5, 5) 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
check_data_path Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from clvrai/relation-network-tensorflow
pointer only · get_code("3bd1e4d8ee61bea8")
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.

conv_gauss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tneumann/minimal_glo/glo.py
code served (permissive licence) · get_code("af9dbac1a25cc9cd")
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 4, dtype family float, shape (2, 3, 8, 8) 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
import torch.nn.functional as fnn

torch.manual_seed(0)

# Create a small image tensor
# Shape: (batch, channels, height, width)
img = torch.randn(2, 3, 8, 8)

# Create a Gaussian kernel
# The function expects kernel.shape to be (n_channels, _, kw, kh)
# We need n_channels to match the image channels (3)
# The kernel should be a depthwise kernel, so we create it with shape (3, 1, 5, 5)
kernel = torch.randn(3, 1, 5, 5)

ARGS = {
    "img": img,
    "kernel": kernel,
}
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 4, dtype family float, shape (2, 3, 8, 8) — shape (2, 3, 8, 8) 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
laplacian_pyramid Ran
ran; our contract draft was wrong, not the code
tneumann/minimal_glo/glo.py
code served (permissive licence) · get_code("00acc4d76c4e2baa")
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 list. 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 torch
import torch.nn as nn
import torch.nn.functional as fnn

torch.manual_seed(0)

# Build a Gaussian kernel
def build_gauss_kernel(channels=3, kernel_size=5, sigma=1.0):
    """Build a Gaussian kernel for convolution"""
    x = torch.arange(kernel_size).float() - kernel_size // 2
    gauss = torch.exp(-x.pow(2.0) / (2 * sigma ** 2))
    kernel_1d = gauss / gauss.sum()
    kernel_2d = kernel_1d.unsqueeze(1) * kernel_1d.unsqueeze(0)
    kernel = kernel_2d.unsqueeze(0).unsqueeze(0).repeat(channels, 1, 1, 1)
    return kernel

# Create a small test image tensor: batch_size=2, channels=3, height=4, width=4
img = torch.randn(2, 3, 4, 4)

# Create a Gaussian kernel: out_channels=3, in_channels/groups=1, kw=5, kh=5
kernel = build_gauss_kernel(channels=3, kernel_size=5, sigma=1.0)

# Set max_levels parameter
max_levels = 2

ARGS = {
    "img": img,
    "kernel": kernel,
    "max_levels": max_levels,
}
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 list — a list 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

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 (1 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
check_data_path 3 other papers
2 dated earlier, 1 later
1206.5538 (2012-06)
Representation Learning: A Review and New Perspectives
1706.01427 (2017-06)
A simple neural network module for relational reasoning
1708.06734 (2017-08)
Representation Learning by Learning to Count

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

Generative Adversarial Networks (GANs) have achieved remarkable results in the task of generating realistic natural images. In most successful applications, GAN models share two common aspects: solving a challenging saddle point optimization problem, interpreted as an adversarial game between a generator and a discriminator functions; and parameterizing the generator and the discriminator as deep convolutional neural networks. The goal of this paper is to disentangle the contribution of these two factors to the success of GANs. In particular, we introduce Generative Latent Optimization (GLO), a framework to train deep convolutional generators using simple reconstruction losses. Throughout a variety of experiments, we show that GLO enjoys many of the desirable properties of GANs: synthesizing visually-appealing samples, interpolating meaningfully between samples, and performing linear arithmetic with noise vectors; all of this without the adversarial optimization scheme.

For agents

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

get_harvested_code_for_paper("1707.05776")
get_code_for_paper("1707.05776")
have("1707.05776")

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

curl https://syntology.ai/api/ran/1707.05776.json

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

[![Syntology run record](https://syntology.ai/api/ran/1707.05776.svg)](https://syntology.ai/paper/1707.05776)

Connect an agent — have() is free.