SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.03036 · 2019

HEAT: Hyperbolic Embedding of Attributed Networks

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 1 failure 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/1903.03036.json · badge: /api/ran/1903.03036.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
DavidMcDonald1993/heat canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
hyperboloid_to_poincare_ball Ran
ran, honoured the contract we drafted
DavidMcDonald1993/heat/heat/utils.py
code served (permissive licence) · get_code("6dc4b1a2f985be4f")
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 (2, 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 torch

torch.manual_seed(0)

# The function takes X and performs operations: X[:, :-1] and X[:, -1:]
# X needs to be a 2D tensor where:
# - X[:, :-1] selects all but the last column
# - X[:, -1:] selects the last column
# The result is X[:, :-1] / (1 + X[:, -1:])

# For a hyperboloid to Poincaré ball transformation,
# X should represent points on the hyperboloid model
# Batch size: 2, feature dimension: 5 (so :-1 gives 4 dims, -1: gives 1 dim)

X = torch.randn(2, 5)

ARGS = {
    "X": X
}
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 (2, 4) — shape (2, 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
load_data Ran
ran; our contract draft was wrong, not the code
DavidMcDonald1993/heat/heat/utils.py
code served (permissive licence) · get_code("d451df9a866da224")
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 numpy as np
import networkx as nx
import pandas as pd
import tempfile
import os

# Create temporary files for testing
temp_dir = tempfile.mkdtemp()

# Create a simple edgelist file
edgelist_path = os.path.join(temp_dir, "edgelist.txt")
with open(edgelist_path, "w") as f:
    f.write("0\t1\t0.5\n")
    f.write("1\t2\t0.8\n")
    f.write("2\t0\t0.3\n")

# Create a features CSV file
features_path = os.path.join(temp_dir, "features.csv")
features_df = pd.DataFrame({
    "feature_1": [1.0, 2.0, 3.0],
    "feature_2": [4.0, 5.0, 6.0],
    "feature_3": [7.0, 8.0, 9.0]
}, index=[0, 1, 2])
features_df.index.name = "node_id"
features_df.to_csv(features_path)

# Create a labels CSV file
labels_path = os.path.join(temp_dir, "labels.csv")
labels_df = pd.DataFrame({
    "label": [0, 1, 0]
}, index=[0, 1, 2])
labels_df.index.name = "node_id"
labels_df.to_csv(labels_path)

# Create args object
class Args:
    def __init__(self, edgelist, features, labels, directed):
        self.edgelist = edgelist
        self.features = features
        self.labels = labels
        self.directed = directed

ARGS = {
    "args": Args(
        edgelist=edgelist_path,
        features=features_path,
        labels=labels_path,
        directed=False
    )
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy, pandas, sklearn — 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_embedding Ran
ran, honoured the contract we drafted
DavidMcDonald1993/heat/heat/utils.py
code served (permissive licence) · get_code("6f273824d8b61a7f")
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, 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 pandas as pd
import gzip
import io
import tempfile
import os

# Create a temporary CSV file compressed with gzip
temp_dir = tempfile.mkdtemp()
csv_filename = os.path.join(temp_dir, 'embeddings.csv.gz')

# Create sample embedding data
embedding_data = pd.DataFrame(
    {
        'dim_0': [0.1, 0.2, 0.3],
        'dim_1': [0.4, 0.5, 0.6],
        'dim_2': [0.7, 0.8, 0.9],
    },
    index=['token_c', 'token_a', 'token_b']
)

# Write to gzip compressed CSV
with gzip.open(csv_filename, 'wt') as f:
    embedding_data.to_csv(f)

ARGS = {
    'embedding_filename': csv_filename
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — 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, 3) — shape (3, 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding these networks into hyperbolic space because it can naturally represent a network's hierarchical structure. However, existing hyperbolic embedding approaches cannot deal with attributed networks, in which nodes are annotated with additional attributes. These attributes might provide additional proximity information to constrain the representations of the nodes, which is important to learn high quality hyperbolic embeddings. To fill this gap, we introduce HEAT (Hyperbolic Embedding of ATributed networks), the first method for embedding attributed networks to a hyperbolic space. HEAT consists of 1) a modified random walk algorithm to obtain training samples that capture both topological and attribute similarity; and 2) a learning algorithm for learning hyperboloid embeddings from the obtained training samples. We show that by leveraging node attributes, HEAT can outperform a state-of-the-art Hyperbolic embedding algorithm on several downstream tasks. As a general embedding method, HEAT opens the door to hyperbolic manifold learning on a wide range of attributed and unattributed networks.

For agents

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

get_harvested_code_for_paper("1903.03036")
get_code_for_paper("1903.03036")
have("1903.03036")

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

curl https://syntology.ai/api/ran/1903.03036.json

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

[![Syntology run record](https://syntology.ai/api/ran/1903.03036.svg)](https://syntology.ai/paper/1903.03036)

Connect an agent — have() is free.