SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.02760 · 2022

TREE-G: Decision Trees Contesting Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

9 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; 0 honoured the contract we drafted, 0 violated it and 9 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/2207.02760.json · badge: /api/ran/2207.02760.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
mayabechlerspeicher/tree-g canonical (classifier label)
classifier basis not recorded on the link
9 ran · 1 no recorded run
FunctionStatusWhere it lives
auc_pytorch Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/eval_utils/metrics.py
code served (permissive licence) · get_code("f6edee7478a3f851")
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 torch
import numpy as np

torch.manual_seed(0)

# Create tiny tensors for y and out parameters
# y: binary labels, shape (2,) - 2 samples
y = torch.tensor([0, 1], dtype=torch.float32)

# out: model outputs with shape (2, 2) for binary classification
# Second dimension is 2, so the function will extract column 1
out = torch.tensor([[0.1, 0.3], [0.8, 0.9]], dtype=torch.float32)

ARGS = {
    "y": y,
    "out": out
}
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 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
balance_data Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/utils.py
code served (permissive licence) · get_code("c5fb1e62e9b6b32b")
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 2, 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 random

random.seed(0)
np.random.seed(0)

# Create sample data with mixed positive and negative labels
# X should be array-like with samples
# y should be array-like with binary labels (0 for negative, >0 for positive)

X = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [2.0, 3.0, 4.0, 5.0],
    [3.0, 4.0, 5.0, 6.0],
    [4.0, 5.0, 6.0, 7.0],
    [5.0, 6.0, 7.0, 8.0],
    [6.0, 7.0, 8.0, 9.0],
])

# More negative samples than positive (to test the balancing logic)
y = np.array([0, 0, 0, 1, 1, 0])

ARGS = {
    'X': X,
    'y': y,
}
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 tuple, ndim 2, 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
create_logger Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/eval_utils/general.py
code served (permissive licence) · get_code("cfdf94fad1b8a3fe")
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 RootLogger. 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 os
import logging
import time
import tempfile
import shutil

# Create a temporary directory for logging
temp_log_dir = tempfile.mkdtemp()

ARGS = {
    'log_dir': temp_log_dir,
    'log_name': 'test_log',
    'dump': True
}
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 RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger 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
get_balanced_data_for_class Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/utils.py
code served (permissive licence) · get_code("b35b5897fe219832")
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 random

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

# Create sample data
# X: feature matrix with 10 samples and 4 features
X = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [2.0, 3.0, 4.0, 5.0],
    [3.0, 4.0, 5.0, 6.0],
    [4.0, 5.0, 6.0, 7.0],
    [5.0, 6.0, 7.0, 8.0],
    [6.0, 7.0, 8.0, 9.0],
    [7.0, 8.0, 9.0, 10.0],
    [8.0, 9.0, 10.0, 11.0],
    [9.0, 10.0, 11.0, 12.0],
    [10.0, 11.0, 12.0, 13.0],
], dtype=np.float32)

# y: binary labels (0 or 1)
y = np.array([0, 0, 0, 0, 0, 1, 1, 1, 1, 1], dtype=int)

# class_i: the class to balance for
class_i = 1

ARGS = {
    "class_i": class_i,
    "X": X,
    "y": y,
}
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 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
intersect Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/treeg/node_treeg/tree_node_learner_node_level.py
code served (permissive licence) · get_code("d9b7c68d3b67de6f")
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 int; 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
from typing import List

# Test case 1: regular lists with some common elements
lst1_test1 = [1, 2, 3, 4, 5]
lst2_test1 = [3, 4, 5, 6, 7]

# Test case 2: numpy arrays with common elements
lst1_test2 = np.array([10, 20, 30, 40])
lst2_test2 = np.array([30, 40, 50, 60])

# Using the first test case
ARGS = {
    "lst1": lst1_test1,
    "lst2": lst2_test1
}
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 list, ndim 1, dtype family int — 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
load_json Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/eval_utils/general.py
code served (permissive licence) · get_code("f753e3699554e87a")
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 json
import tempfile
import os

# Create a temporary JSON file with valid test data
temp_dir = tempfile.mkdtemp()
json_file = os.path.join(temp_dir, "test.json")

test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "dict"}
}

with open(json_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "json_filename": json_file
}
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 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
load_pickle Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/eval_utils/general.py
code served (permissive licence) · get_code("17a866b6340f7ad0")
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 pickle
import tempfile
import os

# Create a temporary pickle file with some test data
test_data = {
    'key1': 'value1',
    'key2': [1, 2, 3],
    'key3': {'nested': 'dict'}
}

# Create a temporary directory and file
temp_dir = tempfile.gettempdir()
pkl_filename = os.path.join(temp_dir, 'test_load_pickle.pkl')

# Write the test data to a pickle file
with open(pkl_filename, 'wb') as f:
    pickle.dump(test_data, f)

ARGS = {
    'pkl_filename': pkl_filename
}
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 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
load_pickle_from_path Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/utils.py
code served (permissive licence) · get_code("dfeb71444a0b6511")
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 pickle
import tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_pickle.pkl")

# Create and save some test data to pickle
test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "dict"}
}

with open(temp_file, 'wb') as f:
    pickle.dump(test_data, f)

# Define the arguments
ARGS = {
    "file_path_from_root": temp_file
}
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 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
round_acc Ran
ran on a synthesized input
mayabechlerspeicher/tree-g/eval_utils/metrics.py
code served (permissive licence) · get_code("69b43268d8037d42")
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 float64, ndim 0, 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

# Construct tiny arguments for round_acc
# The function takes y (ground truth labels) and y_pred (predicted probabilities)

# Create small numpy arrays for ground truth and predictions
y = np.array([0, 1, 1, 0, 1])
y_pred = np.array([0.2, 0.8, 0.6, 0.3, 0.9])

ARGS = {
    "y": y,
    "y_pred": y_pred,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
acc Not yet run
unverified (harvested, no recorded run)
mayabechlerspeicher/tree-g/eval_utils/metrics.py
code served (permissive licence) · get_code("21640f228c42e71d")
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, 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 10 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

When dealing with tabular data, models based on decision trees are a popular choice due to their high accuracy on these data types, their ease of application, and explainability properties. However, when it comes to graph-structured data, it is not clear how to apply them effectively, in a way that incorporates the topological information with the tabular data available on the vertices of the graph. To address this challenge, we introduce TREE-G. TREE-G modifies standard decision trees, by introducing a novel split function that is specialized for graph data. Not only does this split function incorporate the node features and the topological information, but it also uses a novel pointer mechanism that allows split nodes to use information computed in previous splits. Therefore, the split function adapts to the predictive task and the graph at hand. We analyze the theoretical properties of TREE-G and demonstrate its benefits empirically on multiple graph and vertex prediction benchmarks. In these experiments, TREE-G consistently outperforms other tree-based models and often outperforms other graph-learning algorithms such as Graph Neural Networks (GNNs) and Graph Kernels, sometimes by large margins. Moreover, TREE-Gs models and their predictions can be explained and visualized

For agents

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

get_harvested_code_for_paper("2207.02760")
get_code_for_paper("2207.02760")
have("2207.02760")

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

curl https://syntology.ai/api/ran/2207.02760.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.02760.svg)](https://syntology.ai/paper/2207.02760)

Connect an agent — have() is free.