SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.07500 · 2022

ToupleGDD: A Fine-Designed Solution of Influence Maximization by Deep Reinforcement Learning

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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 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/2210.07500.json · badge: /api/ran/2210.07500.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
Dtrycode/ToupleGDD canonical (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
computeMC Ran
ran on a synthesized input
Dtrycode/ToupleGDD/utils/graph_utils.py
code served (permissive licence) · get_code("f8e0cca0ffb4adcd")
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 float, ndim 0, dtype family float, shape () 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 random
from collections import deque

class SimpleGraph:
    def __init__(self):
        self.edges = {}
        self._children = {}
    
    def add_edge(self, source, target, probability):
        self.edges[(source, target)] = probability
        if source not in self._children:
            self._children[source] = []
        self._children[source].append(target)
    
    def get_children(self, node):
        return self._children.get(node, [])

# Create a simple graph with 5 nodes
graph = SimpleGraph()
# Add edges with activation probabilities
graph.add_edge(0, 1, 0.5)
graph.add_edge(0, 2, 0.7)
graph.add_edge(1, 3, 0.4)
graph.add_edge(2, 3, 0.6)
graph.add_edge(3, 4, 0.8)

# Source nodes
S = [0]

# Number of Monte Carlo trials
R = 10

ARGS = {
    "graph": graph,
    "S": S,
    "R": R
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 float, ndim 0, dtype family float, shape () — shape () 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
get_init_node_embed Ran
ran on a synthesized input
Dtrycode/ToupleGDD/models.py
code served (permissive licence) · get_code("69905611239a82c6")
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 2, dtype family float, shape (5, 101) 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
from collections import deque

torch.manual_seed(0)

class SimpleGraph:
    """Minimal graph implementation for DeepWalkNeg"""
    def __init__(self, num_nodes, edges):
        self.num_nodes = num_nodes
        self.adjacency = {i: [] for i in range(num_nodes)}
        for src, dst in edges:
            self.adjacency[src].append(dst)
    
    def get_children(self, node):
        return self.adjacency.get(node, [])

# Create a small test graph with 5 nodes
graph = SimpleGraph(
    num_nodes=5,
    edges=[(0, 1), (1, 2), (2, 3), (3, 4), (4, 0)]
)

num_epochs = 2
device = 'cpu'

ARGS = {
    'graph': graph,
    'num_epochs': num_epochs,
    'device': device
}
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 2, dtype family float, shape (5, 101) — shape (5, 101) 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
read_graph Ran
ran on a synthesized input
Dtrycode/ToupleGDD/utils/graph_utils.py
code served (permissive licence) · get_code("3d9f075d6bbf9b23")
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 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 tempfile
import os

# Create a temporary file with graph data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_path = temp_file.name

# Write a simple graph in edge list format
# Format: src dst (1-indexed by default)
graph_data = """# Simple graph
1 2
2 3
1 3
3 4
"""

temp_file.write(graph_data)
temp_file.close()

ARGS = {
    'path': temp_path,
    'ind': 1,
    'directed': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 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
workerMC Ran
ran on a synthesized input
Dtrycode/ToupleGDD/utils/graph_utils.py
code served (permissive licence) · get_code("0a442841be334923")
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 float, ndim 0, dtype family float, shape () 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 random
from collections import deque

class SimpleGraph:
    """Stand-in graph class that supports the interface used by computeMC"""
    def __init__(self):
        self.edges = {}
        # Define a simple graph structure
        # Node 0 -> Node 1 (prob 0.5)
        # Node 0 -> Node 2 (prob 0.7)
        # Node 1 -> Node 3 (prob 0.6)
        self.edges[(0, 1)] = 0.5
        self.edges[(0, 2)] = 0.7
        self.edges[(1, 3)] = 0.6
        self._children_map = {
            0: [1, 2],
            1: [3],
            2: [],
            3: []
        }
    
    def get_children(self, node):
        """Return list of children for a given node"""
        return self._children_map.get(node, [])

# Create a simple graph instance
graph = SimpleGraph()

# Define source set S
S = [0]

# Number of Monte Carlo trials
R = 10

# Package into tuple format expected by workerMC
x = (graph, S, R)

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 float, ndim 0, dtype family float, shape () — shape () 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

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, 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 4 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

Aiming at selecting a small subset of nodes with maximum influence on networks, the Influence Maximization (IM) problem has been extensively studied. Since it is #P-hard to compute the influence spread given a seed set, the state-of-the-art methods, including heuristic and approximation algorithms, faced with great difficulties such as theoretical guarantee, time efficiency, generalization, etc. This makes it unable to adapt to large-scale networks and more complex applications. On the other side, with the latest achievements of Deep Reinforcement Learning (DRL) in artificial intelligence and other fields, lots of works have been focused on exploiting DRL to solve combinatorial optimization problems. Inspired by this, we propose a novel end-to-end DRL framework, ToupleGDD, to address the IM problem in this paper, which incorporates three coupled graph neural networks for network embedding and double deep Q-networks for parameters learning. Previous efforts to solve IM problem with DRL trained their models on subgraphs of the whole network, and then tested on the whole graph, which makes the performance of their models unstable among different networks. However, our model is trained on several small randomly generated graphs with a small budget, and tested on completely different networks under various large budgets, which can obtain results very close to IMM and better results than OPIM-C on several datasets, and shows strong generalization ability. Finally, we conduct a large number of experiments on synthetic and realistic datasets, and experimental results prove the effectiveness and superiority of our model.

For agents

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

get_harvested_code_for_paper("2210.07500")
get_code_for_paper("2210.07500")
have("2210.07500")

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

curl https://syntology.ai/api/ran/2210.07500.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.07500.svg)](https://syntology.ai/paper/2210.07500)

Connect an agent — have() is free.