SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.00526 · 2023

Are Graph Neural Networks Optimal Approximation Algorithms?

arXiv · PDF · Open in the Atlas

Code that ran

6 of 13 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; 7 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/2310.00526.json · badge: /api/ran/2310.00526.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
penlu/bespoke-gnn4do canonical (classifier label)
classifier basis: census
6 ran · 7 no recorded run
FunctionStatusWhere it lives
e1_projector Ran
ran, violated the contract we drafted
penlu/bespoke-gnn4do/problem/baselines.py
pointer only (licence: NONE) · get_code("49aa42235df7ad05")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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.

featurize_batch Ran
ran; our contract draft was wrong, not the code
penlu/bespoke-gnn4do/model/training.py
pointer only (licence: NONE) · get_code("f9504b4360b1518c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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_kamis_score Ran
ran, honoured the contract we drafted
penlu/bespoke-gnn4do/kamis.py
pointer only (licence: NONE) · get_code("929c874577947a6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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.

max_cut_sdp Ran
ran; our contract draft was wrong, not the code
penlu/bespoke-gnn4do/problem/baselines.py
pointer only (licence: NONE) · get_code("893ec2c23d74dbf8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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.

random_orthogonal_matrix Ran
ran, honoured the contract we drafted
penlu/bespoke-gnn4do/utils/graph_utils.py
pointer only (licence: NONE) · get_code("3409de43caa9035a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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.

vertex_cover_obj Ran
ran; our contract draft was wrong, not the code
penlu/bespoke-gnn4do/problem/losses.py
pointer only (licence: NONE) · get_code("944467b97937b163")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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.

gen_graph Not yet run
unverified (harvested, no recorded run)
penlu/bespoke-gnn4do/utils/graph_utils.py
pointer only (licence: NONE) · get_code("f902914db1ae1dbd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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. No invocation recorded.

get_validation_score Not yet run
unverified (harvested, no recorded run)
penlu/bespoke-gnn4do/kamis.py
pointer only (licence: NONE) · get_code("0139feb1ee03cd3b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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. No invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
penlu/bespoke-gnn4do/model/saving.py
pointer only (licence: NONE) · get_code("87983881cde22896")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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. No invocation recorded.

max_cut_obj Not yet run
unverified (harvested, no recorded run)
penlu/bespoke-gnn4do/problem/losses.py
pointer only (licence: NONE) · get_code("84ae23bf65494964")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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. No invocation recorded.

predict Not yet run
unverified (harvested, no recorded run)
penlu/bespoke-gnn4do/model/training.py
pointer only (licence: NONE) · get_code("0c645b2295bbb309")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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. No invocation recorded.

random_rotation Not yet run
unverified (harvested, no recorded run)
penlu/bespoke-gnn4do/utils/graph_utils.py
pointer only (licence: NONE) · get_code("f19e1cf876592813")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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. No invocation recorded.

vertex_cover_constraint Not yet run
unverified (harvested, no recorded run)
penlu/bespoke-gnn4do/problem/losses.py
pointer only (licence: NONE) · get_code("98b652e02b8b5fe2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, penlu/bespoke-gnn4do 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. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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

In this work we design graph neural network architectures that capture optimal approximation algorithms for a large class of combinatorial optimization problems, using powerful algorithmic tools from semidefinite programming (SDP). Concretely, we prove that polynomial-sized message-passing algorithms can represent the most powerful polynomial time algorithms for Max Constraint Satisfaction Problems assuming the Unique Games Conjecture. We leverage this result to construct efficient graph neural network architectures, OptGNN, that obtain high-quality approximate solutions on landmark combinatorial optimization problems such as Max-Cut, Min-Vertex-Cover, and Max-3-SAT. Our approach achieves strong empirical results across a wide range of real-world and synthetic datasets against solvers and neural baselines. Finally, we take advantage of OptGNN's ability to capture convex relaxations to design an algorithm for producing bounds on the optimal solution from the learned embeddings of OptGNN.

For agents

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

get_harvested_code_for_paper("2310.00526")
get_code_for_paper("2310.00526")
have("2310.00526")

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

curl https://syntology.ai/api/ran/2310.00526.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.00526.svg)](https://syntology.ai/paper/2310.00526)

Connect an agent — have() is free.