SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.03151 · NeurIPS · 2020

Curriculum learning for multilevel budgeted combinatorial problems

Adel Nabli, Margarida Carvalho

arXiv · PDF · Open in the Atlas

Code that ran

3 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 3 have no contract verdict; 0 failures of our instrument; 1 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/2007.03151.json · badge: /api/ran/2007.03151.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
AdelNabli/MCN canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
generate_random_graph Ran
ran on a synthesized input
AdelNabli/MCN/MCN/utils.py
code served (permissive licence) · get_code("c9dd0efb7d2cfaf9")
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 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 numpy as np
import networkx as nx

ARGS = {
    'n_nodes': 10,
    'density': 0.3,
    'directed': True,
    'is_tree': False,
    'seed': 42,
    'draw': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, networkx, numpy — 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
generate_random_instance Ran
ran on a synthesized input
AdelNabli/MCN/MCN/utils.py
code served (permissive licence) · get_code("d52232431b459f76")
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 Instance. 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 numpy as np
import networkx as nx
import random

# Set random seed for reproducibility
np.random.seed(0)
random.seed(0)

# Define ARGS dictionary with all parameters for generate_random_instance
ARGS = {
    'n_free_min': 2,
    'n_free_max': 5,
    'd_edge_min': 0.2,
    'd_edge_max': 0.6,
    'Omega_max': 3,
    'Phi_max': 2,
    'Lambda_max': 2,
    'Budget_target': np.nan,
    'weighted': False,
    'w_max': 1,
    'directed': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, networkx, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Instance — a Instance output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Instance 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
original_names_actions_episode Ran
ran on a synthesized input
AdelNabli/MCN/MCN/MCN_heur/mcn_heuristic.py
code served (permissive licence) · get_code("b6099a235cb6bad9")
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 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - actions_episode: list of actions taken during episode
# - J: list of already infected nodes
# - Phi, Lambda: int budgets
# - exact_protection: bool flag
# The function processes actions, filters based on infected nodes and budgets
# Returns three lists: D, I, P (vaccinate, attack, protect nodes)

# Construct minimal valid arguments
actions_episode = [0, 1, 2, 3, 4, 5, 6, 7]  # 8 actions total
J = [10, 15]  # Already infected nodes (distinct from action indices)
Phi = 2  # Budget for protection phase
Lambda = 2  # Budget for attack phase
exact_protection = True  # Use exact algorithm

ARGS = {
    "actions_episode": actions_episode,
    "J": J,
    "Phi": Phi,
    "Lambda": Lambda,
    "exact_protection": exact_protection,
}
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 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
generate_random_batch_instance Not yet run
unverified (harvested, no recorded run)
AdelNabli/MCN/MCN/utils.py
code served (permissive licence) · get_code("b977f6276422561b")
How it ran

no invocation recorded.

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

Learning heuristics for combinatorial optimization problems through graph neural networks have recently shown promising results on some classic NP-hard problems. These are single-level optimization problems with only one player. Multilevel combinatorial optimization problems are their generalization, encompassing situations with multiple players taking decisions sequentially. By framing them in a multi-agent reinforcement learning setting, we devise a value-based method to learn to solve multilevel budgeted combinatorial problems involving two players in a zero-sum game over a graph. Our framework is based on a simple curriculum: if an agent knows how to estimate the value of instances with budgets up to B, then solving instances with budget B + 1 can be done in polynomial time regardless of the direction of the optimization by checking the value of every possible afterstate. Thus, in a bottom-up approach, we generate datasets of heuristically solved instances with increasingly larger budgets to train our agent. We report results close to optimality on graphs up to 100 nodes and a 185× speedup on average compared to the quickest exact solver known for the Multilevel Critical Node problem, a max-min-max trilevel problem that has been shown to be at least Σ p 2 -hard.

For agents

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

get_harvested_code_for_paper("2007.03151")
get_code_for_paper("2007.03151")
have("2007.03151")

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

curl https://syntology.ai/api/ran/2007.03151.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.03151.svg)](https://syntology.ai/paper/2007.03151)

Connect an agent — have() is free.