SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.09638 · 2021

Signed Bipartite Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 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/2108.09638.json · badge: /api/ran/2108.09638.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
huangjunjie-cs/SBGNN canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
load_data Ran
ran; our contract draft was wrong, not the code
huangjunjie-cs/SBGNN/sbgnn.py
code served (permissive licence) · get_code("4e1576308411933f")
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 tuple. 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 os
import tempfile
import numpy as np

# Create temporary directory and files for the function to read
temp_dir = tempfile.mkdtemp()
experiments_data_dir = os.path.join(temp_dir, 'experiments-data')
os.makedirs(experiments_data_dir, exist_ok=True)

# Create training file
train_file_path = os.path.join(experiments_data_dir, 'test_dataset_training.txt')
with open(train_file_path, 'w') as f:
    f.write('node_a\tnode_b\tscore\n')
    f.write('0\t1\t1\n')
    f.write('1\t2\t0\n')

# Create validation file
val_file_path = os.path.join(experiments_data_dir, 'test_dataset_validation.txt')
with open(val_file_path, 'w') as f:
    f.write('node_a\tnode_b\tscore\n')
    f.write('2\t3\t1\n')

# Create testing file
test_file_path = os.path.join(experiments_data_dir, 'test_dataset_testing.txt')
with open(test_file_path, 'w') as f:
    f.write('node_a\tnode_b\tscore\n')
    f.write('3\t4\t0\n')
    f.write('4\t5\t1\n')

# Change to temp directory so relative path works
original_dir = os.getcwd()
os.chdir(temp_dir)

ARGS = {
    'dataset_name': 'test_dataset'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
load_edgelists Ran
ran; our contract draft was wrong, not the code
huangjunjie-cs/SBGNN/sbgnn.py
code served (permissive licence) · get_code("aa5ac38336622ebb")
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 tuple, 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.

from collections import defaultdict

# Construct a simple edge list for a bipartite graph
# Format: (node_a, node_b, sign) where sign is 1 (positive) or -1 (negative)
edge_lists = [
    ('a1', 'b1', 1),
    ('a1', 'b2', -1),
    ('a2', 'b1', 1),
    ('a2', 'b3', -1),
    ('a3', 'b2', 1),
]

ARGS = {
    'edge_lists': edge_lists,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

Signed networks are such social networks having both positive and negative links. A lot of theories and algorithms have been developed to model such networks (e.g., balance theory). However, previous work mainly focuses on the unipartite signed networks where the nodes have the same type. Signed bipartite networks are different from classical signed networks, which contain two different node sets and signed links between two node sets. Signed bipartite networks can be commonly found in many fields including business, politics, and academics, but have been less studied. In this work, we firstly define the signed relationship of the same set of nodes and provide a new perspective for analyzing signed bipartite networks. Then we do some comprehensive analysis of balance theory from two perspectives on several real-world datasets. Specifically, in the peer review dataset, we find that the ratio of balanced isomorphism in signed bipartite networks increased after rebuttal phases. Guided by these two perspectives, we propose a novel Signed Bipartite Graph Neural Networks (SBGNNs) to learn node embeddings for signed bipartite networks. SBGNNs follow most GNNs message-passing scheme, but we design new message functions, aggregation functions, and update functions for signed bipartite networks. We validate the effectiveness of our model on four real-world datasets on Link Sign Prediction task, which is the main machine learning task for signed networks. Experimental results show that our SBGNN model achieves significant improvement compared with strong baseline methods, including feature-based methods and network embedding methods.

For agents

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

get_harvested_code_for_paper("2108.09638")
get_code_for_paper("2108.09638")
have("2108.09638")

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

curl https://syntology.ai/api/ran/2108.09638.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.09638.svg)](https://syntology.ai/paper/2108.09638)

Connect an agent — have() is free.