SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.09752 · 2021

Graph2Pix: A Graph-Based Image to Image Translation Framework

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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; 4 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/2108.09752.json · badge: /api/ran/2108.09752.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
catlab-team/graph2pix canonical (classifier label)
classifier basis: census
3 ran · 4 no recorded run
FunctionStatusWhere it lives
define_D Ran
ran; our contract draft was wrong, not the code
catlab-team/graph2pix/models/networks.py
code served (permissive licence) · get_code("4c3ac760c14bce27")
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 MultiscaleDiscriminator. 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 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 numpy as np

torch.manual_seed(0)

ARGS = {
    'input_nc': 3,
    'ndf': 64,
    'n_layers_D': 3,
    'norm': 'instance',
    'use_sigmoid': False,
    'num_D': 3,
    'getIntermFeat': False,
    'gpu_ids': []
}
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 MultiscaleDiscriminator — a MultiscaleDiscriminator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiscaleDiscriminator 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_input_output_names Ran
ran on a synthesized input
catlab-team/graph2pix/run_engine.py
code served (permissive licence) · get_code("a15f6e4b138ff37d")
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, 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 numpy as np

class MockDimsCHW:
    def __init__(self, c, h, w):
        self._c = c
        self._h = h
        self._w = w
    
    def C(self):
        return self._c
    
    def H(self):
        return self._h
    
    def W(self):
        return self._w

class MockTRTEngine:
    def __init__(self):
        self.bindings = [
            {
                'name': 'input_layer',
                'is_input': True,
                'dims': MockDimsCHW(3, 224, 224),
                'dtype': 0  # Float32
            },
            {
                'name': 'output_layer',
                'is_input': False,
                'dims': MockDimsCHW(1000, 1, 1),
                'dtype': 0  # Float32
            }
        ]
    
    def get_nb_bindings(self):
        return len(self.bindings)
    
    def get_binding_dimensions(self, b):
        class DimsWrapper:
            def __init__(self, dims_chw):
                self.dims_chw = dims_chw
            
            def to_DimsCHW(self):
                return self.dims_chw
        
        return DimsWrapper(self.bindings[b]['dims'])
    
    def get_binding_name(self, b):
        return self.bindings[b]['name']
    
    def get_binding_data_type(self, b):
        return self.bindings[b]['dtype']
    
    def binding_is_input(self, b):
        return self.bindings[b]['is_input']

ARGS = {
    'trt_engine': MockTRTEngine()
}
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 list, ndim 1, dtype family float — a list 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
get_norm_layer Ran
ran; our contract draft was wrong, not the code
catlab-team/graph2pix/models/networks.py
code served (permissive licence) · get_code("29bb0088c8c38ae4")
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) and returned partial. 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 functools

torch.manual_seed(0)

ARGS = {
    'norm_type': 'instance'
}
Setup block drafted by
a language model, Claude Haiku 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 partial — a partial output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a partial 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
convert_to_datatype Not yet run
unverified (harvested, no recorded run)
catlab-team/graph2pix/run_engine.py
code served (permissive licence) · get_code("bc2a177fe251445f")
How it ran

no invocation recorded.

create_memory Not yet run
unverified (harvested, no recorded run)
catlab-team/graph2pix/run_engine.py
code served (permissive licence) · get_code("7c0dff70f4e176df")
How it ran

no invocation recorded.

create_model Not yet run
unverified (harvested, no recorded run)
catlab-team/graph2pix/models/models.py
code served (permissive licence) · get_code("1f5d33b5045ac695")
How it ran

no invocation recorded.

define_G Not yet run
unverified (harvested, no recorded run)
catlab-team/graph2pix/models/networks.py
code served (permissive licence) · get_code("29de80c9fa169dd4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 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 5 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
get_norm_layer 8 other papers
4 dated earlier, 4 later
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
1805.04487 (2018-05)
Non-Stationary Texture Synthesis by Adversarial Expansion
1808.07535 (2018-08)
Learning Hierarchical Semantic Image Manipulation through Structured Representations
and 5 more not named here
define_D 1 other paper
1 later
2207.02774 (2022-07)
Local Relighting of Real Scenes

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 this paper, we propose a graph-based image-to-image translation framework for generating images. We use rich data collected from the popular creativity platform Artbreeder (http://artbreeder.com), where users interpolate multiple GAN-generated images to create artworks. This unique approach of creating new images leads to a tree-like structure where one can track historical data about the creation of a particular image. Inspired by this structure, we propose a novel graph-to-image translation model called Graph2Pix, which takes a graph and corresponding images as input and generates a single image as output. Our experiments show that Graph2Pix is able to outperform several image-to-image translation frameworks on benchmark metrics, including LPIPS (with a 25% improvement) and human perception studies (n=60), where users preferred the images generated by our method 81.5% of the time. Our source code and dataset are publicly available at https://github.com/catlab-team/graph2pix.

For agents

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

get_harvested_code_for_paper("2108.09752")
get_code_for_paper("2108.09752")
have("2108.09752")

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

curl https://syntology.ai/api/ran/2108.09752.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.09752.svg)](https://syntology.ai/paper/2108.09752)

Connect an agent — have() is free.