SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1607.00653 · Knowledge Discovery and Data Mining · 2016

node2vec: Scalable Feature Learning for Networks

Jure Leskovec, Aditya Grover

arXiv · PDF · Open in the Atlas

Code that ran

15 of 25 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 4 failures of our instrument; 10 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/1607.00653.json · badge: /api/ran/1607.00653.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
cvg/scrstudio community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
WiktorJ/msnode2vec community
Papers with Code archive
2 ran · 1 no recorded run
fahrbach/icml-2020-faster-graph-embeddings community
Papers with Code archive
2 ran · 1 no recorded run
thibaudmartinez/node2vec community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
TheJacksonLaboratory/N2V community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
icd-codex/icd-codex community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
Robotmurlock/Deepwalk-and-Node2vec community
Papers with Code archive
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 1 no recorded run
olety/TIMLinUCB community
Papers with Code archive
0 ran · 1 no recorded run
dmlc/dgl community
Papers with Code archive
0 ran · 1 no recorded run
urielsinger/ctdne community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
urielsinger/fairwalk community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Graph Ran
ran on a synthesized input · constructed an object; no result was computed
WiktorJ/msnode2vec/src3/node2vec.py
code served (permissive licence) · get_code("61d87751f700a525")
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 an instance of its own class, Graph: the run constructed the object and did not call it, so no result was computed. 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

# Create a small weighted graph for testing
G = nx.Graph()
G.add_edge(0, 1, weight=1.0)
G.add_edge(1, 2, weight=1.0)
G.add_edge(2, 3, weight=1.0)
G.add_edge(0, 3, weight=1.0)

ARGS = {
    "nx_G": G,
    "is_directed": False,
    "p": 1.0,
    "q": 1.0,
    "log_stats": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph — the run constructed an instance of its own class and did not call it; no shape 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
Node2Vec Ran
ran on a synthesized input · constructed an object; no result was computed
Robotmurlock/Deepwalk-and-Node2vec/shallow_encoders/graph/random_walk_generator.py
code served (permissive licence) · get_code("8eb7ee072d5f2738")
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 an instance of its own class, Node2Vec: the run constructed the object and did not call it, so no result was computed. 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 seed for reproducibility
random.seed(42)

# Create a simple graph for testing
graph = nx.Graph()
graph.add_edges_from([
    ('node1', 'node2'),
    ('node2', 'node3'),
    ('node3', 'node4'),
    ('node4', 'node1'),
    ('node2', 'node4')
])

# Define all parameters for Node2Vec
ARGS = {
    'graph': graph,
    'length': 5,
    'p': 1.0,
    'q': 1.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Node2Vec — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Node2Vec 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
alias_draw Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
WiktorJ/msnode2vec/src3/node2vec.py
code served (permissive licence) · get_code("9e04436adf3455c1")
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 int64, ndim 0, dtype family int, 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 numpy as np

np.random.seed(0)

# alias_draw expects:
# J: a sequence (list/array) of indices to return as fallback
# q: a sequence (list/array) of probabilities, same length as J

K = 5  # number of categories
J = np.array([1, 2, 3, 4, 0])  # alias table: indices to return on rejection
q = np.array([0.3, 0.7, 0.5, 0.9, 0.2])  # acceptance probabilities for each bin

ARGS = {
    "J": J,
    "q": q
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int64, ndim 0, dtype family int, 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
approximate_normalized_graph_laplacian Ran
ran; our contract draft was wrong, not the code
fahrbach/icml-2020-faster-graph-embeddings/src/classification/NetMF.py
code served (permissive licence) · get_code("0c0ee39ba8faec97")
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 scipy.sparse as sparse
from scipy.sparse import csgraph
import numpy as np
import logging

logging.basicConfig(level=logging.INFO)

# Create a small sparse adjacency matrix
# A symmetric sparse matrix is needed for the graph Laplacian
n = 5
row = np.array([0, 1, 2, 3, 4, 0, 1, 2, 3])
col = np.array([1, 2, 3, 4, 0, 0, 1, 2, 3])
data = np.array([1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0])
A = sparse.csr_matrix((data, (row, col)), shape=(n, n))

# Ensure it's symmetric by making it undirected
A = A + A.T
A.data = np.ones_like(A.data)

rank = 2
which = 'LA'

ARGS = {
    'A': A,
    'rank': rank,
    'which': which
}
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 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
build_icd9_hierarchy Ran
ran on a synthesized input
icd-codex/icd-codex/icdcodex/datacleaning.py
code served (permissive licence) · get_code("fa97591fdcd9e8c2")
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 pandas as pd
import networkx as nx
import json
import tempfile
import os

# Create a minimal ICD9 hierarchy JSON file
hierarchy_data = [
    {
        "chapter": "Infectious And Parasitic Diseases",
        "subchapter": "Cholera",
        "major": "001",
        "icd9": "001.0",
        "descLong": "Cholera due to vibrio cholerae"
    },
    {
        "chapter": "Infectious And Parasitic Diseases",
        "subchapter": "Cholera",
        "major": "001",
        "icd9": "001.1",
        "descLong": "Cholera due to vibrio cholerae el tor"
    },
    {
        "chapter": "Infectious And Parasitic Diseases",
        "subchapter": None,
        "major": "002",
        "icd9": "002.0",
        "descLong": "Typhoid fever with heart involvement"
    },
    {
        "chapter": "Neoplasms",
        "subchapter": "Malignant Neoplasm of Lip",
        "major": "140",
        "icd9": "140.0",
        "descLong": "Malignant neoplasm of upper lip, inner aspect"
    },
    {
        "chapter": "Neoplasms",
        "subchapter": "Malignant Neoplasm of Lip",
        "major": "140",
        "icd9": "140.1",
        "descLong": "Malignant neoplasm of lower lip, inner aspect"
    }
]

# Create a temporary file with the hierarchy JSON
temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.json', delete=False)
json.dump(hierarchy_data, temp_file)
temp_file.close()

ARGS = {
    "fp": temp_file.name,
    "root_name": "root"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, pandas — 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
evd_deepwalk_matrix Ran
ran, honoured the contract we drafted
fahrbach/icml-2020-faster-graph-embeddings/src/classification/NetMF.py
code served (permissive licence) · get_code("abcc32e0f84c4724")
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 ndarray, ndim 2, dtype family float, shape (6, 3) 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 scipy.sparse as sparse
import numpy as np

# Create a small sparse matrix suitable for eigenvalue decomposition
# The matrix should be square and symmetric for eigsh to work properly
np.random.seed(0)
n = 6
# Create a random sparse matrix and symmetrize it
X_dense = np.random.randn(n, n)
X_symmetric = (X_dense + X_dense.T) / 2
X = sparse.csr_matrix(X_symmetric)

dim = 3

ARGS = {
    'X': X,
    'dim': dim
}
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 ndarray, ndim 2, dtype family float, shape (6, 3) — shape (6, 3) 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
is_symmetric Ran
ran on a synthesized input
thibaudmartinez/node2vec/node2vec/helpers.py
code served (permissive licence) · get_code("443f57bf3337dc32")
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 bool, 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 numpy as np

# Create a symmetric matrix for testing
symmetric_matrix = np.array([
    [1.0, 2.0, 3.0],
    [2.0, 4.0, 5.0],
    [3.0, 5.0, 6.0]
])

ARGS = {
    "matrix": symmetric_matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
load_adjacency_matrix Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from xptree/NetMF
pointer only · get_code("61d600be2b025f26")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

merge_methods Ran
ran; our contract draft was wrong, not the code
cvg/scrstudio/scrstudio/configs/method_configs.py
code served (permissive licence) · get_code("c64c9a3a66a1d0c8")
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, 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.

import torch
from collections import OrderedDict

torch.manual_seed(0)

# Create sample methods - these are callables/functions
def method_1():
    return "result_1"

def method_2():
    return "result_2"

def method_3():
    return "result_3"

# Create existing methods and descriptions
existing_methods = OrderedDict({
    'method_1': method_1,
    'method_2': method_2,
})

existing_descriptions = OrderedDict({
    'method_1': 'Description for method 1',
    'method_2': 'Description for method 2',
})

# Create new methods and descriptions to merge in
new_methods = {
    'method_3': method_3,
    'method_2': lambda: "updated_result_2",  # This will overwrite method_2 if overwrite=True
}

new_descriptions = {
    'method_3': 'Description for method 3',
    'method_2': 'Updated description for method 2',
}

ARGS = {
    'methods': existing_methods,
    'method_descriptions': existing_descriptions,
    'new_methods': new_methods,
    'new_descriptions': new_descriptions,
    'overwrite': True,
}
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 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
normalize_model_list_parameter Ran
ran on a synthesized input
TheJacksonLaboratory/N2V/embiggen/utils/normalize_model_structural_parameters.py
code served (permissive licence) · get_code("bab88306f9266ce9")
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 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Test case 1: Valid list of objects with matching length
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model1 = SimpleModel()
model2 = SimpleModel()
model3 = SimpleModel()

# Test case: Single object that gets expanded to a list
single_model = SimpleModel()

# Test case: List of strings (simple object type)
string_list = ["layer1", "layer2", "layer3"]
single_string = "layer"

# Test case: List of integers
int_list = [1, 2, 3]
single_int = 5

ARGS = {
    "candidate_list": [model1, model2, model3],
    "elements_number": 3,
    "object_type": SimpleModel,
    "default_value": None,
    "can_be_empty": False
}
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 list, ndim 1, 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
normalize_model_ragged_list_parameter Ran
ran on a synthesized input
TheJacksonLaboratory/N2V/embiggen/utils/normalize_model_structural_parameters.py
code served (permissive licence) · get_code("473e754191aea19d")
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. 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 torch.nn as nn
from typing import List, Any, Union, Type, Optional

torch.manual_seed(0)

# Define a simple object type to use for the ragged list
class SimpleModule(nn.Module):
    def __init__(self, input_size: int = 4):
        super().__init__()
        self.linear = nn.Linear(input_size, 2)
    
    def forward(self, x):
        return self.linear(x)

# Create instances for the ragged list
module1 = SimpleModule(4)
module2 = SimpleModule(4)
module3 = SimpleModule(4)
module4 = SimpleModule(4)
module5 = SimpleModule(4)

# Define parameters for normalize_model_ragged_list_parameter
candidate_ragged_list = [
    [module1, module2],
    [module3, module4, module5]
]

submodules_number = 2

layers_per_submodule = [2, 3]

object_type = SimpleModule

default_value = SimpleModule(4)

ARGS = {
    "candidate_ragged_list": candidate_ragged_list,
    "submodules_number": submodules_number,
    "layers_per_submodule": layers_per_submodule,
    "object_type": object_type,
    "default_value": default_value
}
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 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
sort_methods Ran
ran; our contract draft was wrong, not the code
cvg/scrstudio/scrstudio/configs/method_configs.py
code served (permissive licence) · get_code("06036a2535dc9b18")
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, 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 OrderedDict

torch_manual_seed = 0

methods = OrderedDict([
    ("method_alpha", lambda x: x * 2),
    ("method_beta", lambda x: x + 1),
    ("method_gamma", lambda x: x - 1),
])

method_descriptions = OrderedDict([
    ("method_beta", "Description for beta"),
    ("method_alpha", "Description for alpha"),
    ("method_gamma", "Description for gamma"),
])

ARGS = {
    "methods": methods,
    "method_descriptions": method_descriptions,
}
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 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
to_immutable_dict Ran
ran on a synthesized input
cvg/scrstudio/scrstudio/configs/config_utils.py
code served (permissive licence) · get_code("86b0fba57294202e")
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 Field. 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.

from dataclasses import field
from typing import Any, Dict

torch_manual_seed_0 = None
try:
    import torch
    torch.manual_seed(0)
except:
    pass

# Create a sample dictionary with various types of values
sample_dict = {
    "key1": "value1",
    "key2": 42,
    "key3": [1, 2, 3],
    "key4": {"nested": "dict"},
    "key5": 3.14,
}

ARGS = {
    "d": sample_dict,
}
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 Field — a Field output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Field 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
weighted_gm Ran
ran on a synthesized input
cvg/scrstudio/scrstudio/model_components/losses.py
code served (permissive licence) · get_code("bfbbb40daca9a6f9")
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 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 torch

torch.manual_seed(0)

# Create small tensors for the function parameters
# rep_errs: representation errors, needs to be a tensor that supports division and exponentiation
rep_errs = torch.tensor([[1.0, 2.0, 3.0, 4.0],
                         [0.5, 1.5, 2.5, 3.5]])

# weight: needs to be broadcastable with rep_errs for division and multiplication
weight = torch.tensor([[0.1, 0.2, 0.3, 0.4],
                       [0.15, 0.25, 0.35, 0.45]])

# reduction: string parameter
reduction = 'mean'

ARGS = {
    'rep_errs': rep_errs,
    'weight': weight,
    'reduction': reduction
}
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 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
wv_to_numpy_array Ran
ran on a synthesized input
thibaudmartinez/node2vec/node2vec/helpers.py
code served (permissive licence) · get_code("8eaf4c1833454e08")
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 ndarray, ndim 2, dtype family float, shape (3, 4) 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

class MockWordVectors:
    def __init__(self):
        self.vocab = {
            '0': None,
            '1': None,
            '2': None,
        }
        self._vectors = {
            '0': np.array([0.1, 0.2, 0.3, 0.4], dtype=np.float32),
            '1': np.array([0.5, 0.6, 0.7, 0.8], dtype=np.float32),
            '2': np.array([0.9, 1.0, 1.1, 1.2], dtype=np.float32),
        }
    
    def __getitem__(self, key):
        return self._vectors[key]

wv = MockWordVectors()

ARGS = {
    'wv': wv
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 4) — shape (3, 4) 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
RandomWalk Not yet run
unverified (harvested, no recorded run)
Robotmurlock/Deepwalk-and-Node2vec/shallow_encoders/graph/random_walk_generator.py
code served (permissive licence) · get_code("fdf62a385c9c3c79")
How it ran

no invocation recorded.

alias_setup Not yet run
unverified (harvested, no recorded run)
WiktorJ/msnode2vec/src3/node2vec.py
code served (permissive licence) · get_code("0f462717a557f615")
How it ran

no invocation recorded.

build_icd9_hierarchy_from_url Not yet run
unverified (harvested, no recorded run)
icd-codex/icd-codex/icdcodex/datacleaning.py
code served (permissive licence) · get_code("18bd96cd5e6b659a")
How it ran

no invocation recorded.

generate_node2vec_fetures Not yet run
unverified (harvested, no recorded run)
olety/TIMLinUCB/timlinucb.py
pointer only (licence: NONE) · get_code("7706b10825b13220")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, olety/TIMLinUCB 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. No invocation recorded.

get_features_nodes Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from olety/TIMLinUCB
pointer only; the stored copy get_code serves, from olety/TIMLinUCB, is pointer only (licence: NONE) · get_code("595ace8a8dae3b1d")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. No invocation recorded.

icd10cm Not yet run
unverified (harvested, no recorded run)
icd-codex/icd-codex/icdcodex/hierarchy.py
code served (permissive licence) · get_code("db538a57b89ffc55")
How it ran

no invocation recorded.

netmf_large Not yet run
unverified (harvested, no recorded run)
fahrbach/icml-2020-faster-graph-embeddings/src/classification/NetMF.py
code served (permissive licence) · get_code("2565edc5f1658e6e")
How it ran

no invocation recorded.

node2vec_random_walk Not yet run
unverified (harvested, no recorded run)
dmlc/dgl/python/dgl/sampling/node2vec_randomwalk.py
code served (permissive licence) · get_code("99d796c0f6439641")
How it ran

no invocation recorded.

parallel_generate_walks Not yet run
unverified (harvested, no recorded run)
urielsinger/ctdne/CTDNE/parallel.py
code served (permissive licence) · get_code("0834e8f66ab35dac")
How it ran

no invocation recorded.

parallel_generate_walks Not yet run
unverified (harvested, no recorded run)
urielsinger/fairwalk/fairwalk/parallel.py
code served (permissive licence) · get_code("9d36caa2def1ee2f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 7 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 5 later) and 18 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
alias_setup
brick of this paper's assembly: helper
5 other papers
5 later
1911.02613 (2019-11)
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
1911.08415 (2019-11)
GMAN: A Graph Multi-Attention Network for Traffic Prediction
2002.04784 (2020-02)
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
and 2 more not named here
merge_methods 5 other papers
5 later
2103.12352 (2021-03)
iMAP: Implicit Mapping and Positioning in Real-Time
2402.03307 (2024-02)
4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes
2403.09637 (2024-03)
GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping
and 2 more not named here
sort_methods 5 other papers
5 later
2103.12352 (2021-03)
iMAP: Implicit Mapping and Positioning in Real-Time
2402.03307 (2024-02)
4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes
2403.09637 (2024-03)
GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping
and 2 more not named here
alias_draw
brick of this paper's assembly: helper
4 other papers
4 later
1911.08415 (2019-11)
GMAN: A Graph Multi-Attention Network for Traffic Prediction
2002.04784 (2020-02)
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
2002.05257 (2020-02)
Shortest path distance approximation using deep learning techniques
and 1 more not named here
generate_node2vec_fetures
brick of this paper's assembly: entry
1 other paper
1 dated earlier
1404.0900 (2014-04)
Influence Maximization: Near-Optimal Time Complexity Meets Practical Efficiency
get_features_nodes
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1404.0900 (2014-04)
Influence Maximization: Near-Optimal Time Complexity Meets Practical Efficiency
load_adjacency_matrix 1 other paper
1 later
1710.02971 (2017-10)
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec

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

Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning approaches are not expressive enough to capture the diversity of connectivity patterns observed in networks. Here we propose node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node's network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations. We demonstrate the efficacy of node2vec over existing state-ofthe-art techniques on multi-label classification and link prediction in several real-world networks from diverse domains. Taken together, our work represents a new way for efficiently learning stateof-the-art task-independent representations in complex networks.

For agents

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

get_harvested_code_for_paper("1607.00653")
get_code_for_paper("1607.00653")
have("1607.00653")

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

curl https://syntology.ai/api/ran/1607.00653.json

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

[![Syntology run record](https://syntology.ai/api/ran/1607.00653.svg)](https://syntology.ai/paper/1607.00653)

Connect an agent — have() is free.