SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.09693 · 2024

Neural Solver Selection for Combinatorial Optimization

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 4 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/2410.09693.json · badge: /api/ran/2410.09693.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
lamda-bbo/neural-solver-selection canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
augment_xy_by_8_fold Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lamda-bbo/neural-solver-selection/utils.py
code served (permissive licence) · get_code("3db541b736338de2")
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 3, dtype family float, shape (16, 4, 2) 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

torch.manual_seed(0)

# Create a small tensor with shape (batch, sequence, features)
# The function expects problems[:, :, [0]] and problems[:, :, [1]] to extract x and y
# So we need at least 2 features in the last dimension
# Shape: (batch_size=2, sequence_length=4, features=2)
problems = torch.rand(2, 4, 2)

ARGS = {
    "problems": problems
}
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 3, dtype family float, shape (16, 4, 2) — shape (16, 4, 2) 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
generate_tsp_data Ran
ran, honoured the contract we drafted
lamda-bbo/neural-solver-selection/datasets/data_utils.py
code served (permissive licence) · get_code("11df7363c2047f6b")
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 3, dtype family float, shape (2, 4, 2) 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 numpy as np
import torch
from sklearn.preprocessing import MinMaxScaler

torch.manual_seed(0)

# Create a minimal config dict with required parameters for Gaussian distribution
config = {
    'Gaussian_params': {
        'var_lower': 0.1,
        'var_upper': 0.5,
        'num_modes_lower': 2,
        'num_modes_upper': 2,
        'no_cov': True
    },
    'Explosion_params': {},
    'Rotation_params': {}
}

ARGS = {
    'dataset_size': 2,
    'problem_size': 4,
    'config': config,
    'distribution': 'Gaussian'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 2) — shape (2, 4, 2) 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
generate_tsp_data_gaussian Ran
ran, honoured the contract we drafted
lamda-bbo/neural-solver-selection/datasets/data_utils.py
code served (permissive licence) · get_code("56f4b6ddfcdc2968")
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 list, ndim 3, 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.

import numpy as np
import torch
from sklearn.preprocessing import MinMaxScaler

torch.manual_seed(0)

ARGS = {
    'dataset_size': 2,
    'problem_size': 5,
    'params': {
        'var_lower': 0.1,
        'var_upper': 0.5,
        'num_modes_lower': 2,
        'num_modes_upper': 3,
        'no_cov': False
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, dtype family float — a list 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
generate_vrp_data Ran
ran; our contract draft was wrong, not the code
lamda-bbo/neural-solver-selection/datasets/data_utils.py
code served (permissive licence) · get_code("6e293e11ca816f24")
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 dict. 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
import random
from sklearn.preprocessing import MinMaxScaler

torch.manual_seed(0)
random.seed(0)
np.random.seed(0)

ARGS = {
    'dataset_size': 2,
    'problem_size': 4,
    'config': {
        'Gaussian_params': {
            'var_lower': 0.1,
            'var_upper': 0.5,
            'num_modes_lower': 1,
            'num_modes_upper': 3,
            'no_cov': False
        },
        'Explosion_params': {
            'var_lower': 0.1,
            'var_upper': 0.5,
            'num_modes_lower': 1,
            'num_modes_upper': 2
        }
    },
    'distribution': 'Gaussian',
    'capacity_type': 'scale'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
multi_head_attention Ran
ran; our contract draft was wrong, not the code
lamda-bbo/neural-solver-selection/model.py
code served (permissive licence) · get_code("13f7aec0cb34d440")
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 3, dtype family float, shape (2, 4, 15) 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

torch.manual_seed(0)

# Set up dimensions
batch_s = 2
head_num = 3
n = 4  # query sequence length
key_dim = 5
input_s = 6  # key/value sequence length

# Create q, k, v tensors
# q: (batch_s, head_num, n, key_dim)
q = torch.randn(batch_s, head_num, n, key_dim)

# k: (batch_s, head_num, input_s, key_dim)
k = torch.randn(batch_s, head_num, input_s, key_dim)

# v: (batch_s, head_num, input_s, key_dim)
v = torch.randn(batch_s, head_num, input_s, key_dim)

# rank2_ninf_mask: (batch_s, input_s) - optional mask for keys
rank2_ninf_mask = torch.zeros(batch_s, input_s)
rank2_ninf_mask[0, -1] = float('-inf')  # mask out last position for first batch

# rank3_ninf_mask: (batch_s, n, input_s) - optional mask for query-key pairs
rank3_ninf_mask = torch.zeros(batch_s, n, input_s)
rank3_ninf_mask[0, 0, -1] = float('-inf')  # mask out last key for first query in first batch

ARGS = {
    'q': q,
    'k': k,
    'v': v,
    'rank2_ninf_mask': rank2_ninf_mask,
    'rank3_ninf_mask': rank3_ninf_mask
}
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 3, dtype family float, shape (2, 4, 15) — shape (2, 4, 15) 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
reshape_by_heads Ran
ran; our contract draft was wrong, not the code
lamda-bbo/neural-solver-selection/model.py
pointer only (licence: MIT); the stored copy get_code serves, from yihang0410/RADAR, is pointer only (licence: NONE) · get_code("459fe521069329c6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from yihang0410/RADAR, and GitHub detected no licence in that repository 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.

collate_fn Not yet run
unverified (harvested, no recorded run)
lamda-bbo/neural-solver-selection/dataset.py
code served (permissive licence) · get_code("11b4c8925238565e")
How it ran

no invocation recorded.

manual_features Not yet run
unverified (harvested, no recorded run)
lamda-bbo/neural-solver-selection/dataset.py
code served (permissive licence) · get_code("fb3893f25da812de")
How it ran

no invocation recorded.

prepare_dataset Not yet run
unverified (harvested, no recorded run)
lamda-bbo/neural-solver-selection/utils.py
code served (permissive licence) · get_code("2eeabea8e2f0857a")
How it ran

no invocation recorded.

process_instance_CVRP Not yet run
unverified (harvested, no recorded run)
lamda-bbo/neural-solver-selection/utils.py
code served (permissive licence) · get_code("8ed2844221376cf5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 9 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.

FunctionAlso present inEarliest-datedOthers named
reshape_by_heads 28 other papers
14 dated earlier, 2 the same month, 10 later, 1 same year, order not determinable, 1 undated · 15 only as an assembly brick
2010.16011 (2020-10)
POMO: Policy Optimization with Multiple Optima for Reinforcement Learning
2106.11113 (2021-06)
Matrix Encoding Networks for Neural Combinatorial Optimization
2203.15386 (2022-03)
Pareto Set Learning for Neural Multi-objective Combinatorial Optimization
and 25 more not named here

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

Machine learning has increasingly been employed to solve NP-hard combinatorial optimization problems, resulting in the emergence of neural solvers that demonstrate remarkable performance, even with minimal domain-specific knowledge. To date, the community has created numerous open-source neural solvers with distinct motivations and inductive biases. While considerable efforts are devoted to designing powerful single solvers, our findings reveal that existing solvers typically demonstrate complementary performance across different problem instances. This suggests that significant improvements could be achieved through effective coordination of neural solvers at the instance level. In this work, we propose the first general framework to coordinate the neural solvers, which involves feature extraction, selection model, and selection strategy, aiming to allocate each instance to the most suitable solvers. To instantiate, we collect several typical neural solvers with state-of-the-art performance as alternatives, and explore various methods for each component of the framework. We evaluated our framework on two extensively studied combinatorial optimization problems, Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP). Experimental results show that the proposed framework can effectively distribute instances and the resulting composite solver can achieve significantly better performance (e.g., reduce the optimality gap by 0.88\% on TSPLIB and 0.71\% on CVRPLIB) than the best individual neural solver with little extra time cost.

For agents

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

get_harvested_code_for_paper("2410.09693")
get_code_for_paper("2410.09693")
have("2410.09693")

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

curl https://syntology.ai/api/ran/2410.09693.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.09693.svg)](https://syntology.ai/paper/2410.09693)

Connect an agent — have() is free.