SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.04560 · 2023

Talk like a Graph: Encoding Graphs for Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 0 have no contract verdict; 5 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/2310.04560.json · badge: /api/ran/2310.04560.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
google-research/talk-like-a-graph canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
ChristianaKang11/google-graphqa canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
add_edge_weight Ran
ran; our contract draft was wrong, not the code
ChristianaKang11/google-graphqa/graph_task.py
pointer only (licence: NONE) · get_code("80a181995f066599")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChristianaKang11/google-graphqa 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.

generate_graphs Ran
ran; our contract draft was wrong, not the code
google-research/talk-like-a-graph/talk_like_a_graph/graph_generators.py
code served (permissive licence) · get_code("9a4d3555abd9511d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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 random
import networkx as nx
import numpy as np

ARGS = {
    'number_of_graphs': 3,
    'algorithm': 'er',
    'directed': False,
    'random_seed': 1234,
    'er_min_sparsity': 0.2,
    'er_max_sparsity': 0.8
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
networkx, numpy — 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
has_edge_weights Ran
ran; our contract draft was wrong, not the code
ChristianaKang11/google-graphqa/graph_task.py
pointer only (licence: NONE) · get_code("8d3fe6e5fe601ad1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ChristianaKang11/google-graphqa 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.

randomize_directions Ran
ran; our contract draft was wrong, not the code
google-research/talk-like-a-graph/talk_like_a_graph/graph_generators.py
code served (permissive licence) · get_code("89a2b6113ddd5c4c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned DiGraph. 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 networkx as nx
import random

# Set random seed for reproducibility
random.seed(42)

# Create a simple undirected graph
graph = nx.Graph()
graph.add_edges_from([
    (0, 1),
    (1, 2),
    (2, 3),
    (3, 0),
    (1, 3)
])

ARGS = {
    'graph': graph
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
networkx — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DiGraph — a DiGraph output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DiGraph output the recorded ndim 1 and dtype family int 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
remove_graph_data Ran
ran; our contract draft was wrong, not the code
google-research/talk-like-a-graph/talk_like_a_graph/graph_generators.py
code served (permissive licence) · get_code("2a7b9056d8a8ba8b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Graph. 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 networkx as nx

# Create a graph with nodes that have 'block' attributes and graph-level data
graph = nx.Graph()

# Add nodes with 'block' attribute
graph.add_node(0, block='block_0', other_attr='value_0')
graph.add_node(1, block='block_1', other_attr='value_1')
graph.add_node(2, block='block_2', other_attr='value_2')

# Add some edges
graph.add_edge(0, 1)
graph.add_edge(1, 2)

# Add graph-level data
graph.graph['metadata'] = 'some_metadata'
graph.graph['config'] = {'param1': 10, 'param2': 20}
graph.graph['name'] = 'test_graph'

ARGS = {'graph': graph}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
networkx — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph — a Graph output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Graph output the recorded ndim 1 and dtype family int 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 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.

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

Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the relationships between entities in a complex system, and to identify hidden patterns and trends. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with large language models (LLMs) remains an understudied problem. In this work, we perform the first comprehensive study of encoding graph-structured data as text for consumption by LLMs. We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered. These novel results provide valuable insight on strategies for encoding graphs as text. Using these insights we illustrate how the correct choice of encoders can boost performance on graph reasoning tasks inside LLMs by 4.8% to 61.8%, depending on the task.

For agents

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

get_harvested_code_for_paper("2310.04560")
get_code_for_paper("2310.04560")
have("2310.04560")

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

curl https://syntology.ai/api/ran/2310.04560.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.04560.svg)](https://syntology.ai/paper/2310.04560)

Connect an agent — have() is free.