SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.00285 · 2023

Assembled-OpenML: Creating Efficient Benchmarks for Ensembles in AutoML with OpenML

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/2307.00285.json · badge: /api/ran/2307.00285.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
isg-siegen/assembled canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
check_fold_data_for_ensemble Ran
ran on a synthesized input
isg-siegen/assembled/assembled/utils/preprocessing.py
code served (permissive licence) · get_code("e913d0385d70c60e")
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 numpy as np

# Create sample data with numeric and categorical columns
np.random.seed(0)
n_samples = 2
n_numeric = 3
n_categorical = 2

# Create numeric columns
numeric_data = np.random.randn(n_samples, n_numeric)

# Create categorical columns
categorical_data = np.array([['A', 'X'], ['B', 'Y']])

# Combine into a DataFrame
X_train_df = pd.DataFrame(
    np.hstack([numeric_data, categorical_data]),
    columns=[f'num_{i}' for i in range(n_numeric)] + [f'cat_{i}' for i in range(n_categorical)]
)

# Set dtypes appropriately
for i in range(n_numeric):
    X_train_df[f'num_{i}'] = pd.to_numeric(X_train_df[f'num_{i}'])
for i in range(n_categorical):
    X_train_df[f'cat_{i}'] = X_train_df[f'cat_{i}'].astype('category')

# Create test data with same structure
numeric_data_test = np.random.randn(n_samples, n_numeric)
categorical_data_test = np.array([['C', 'Z'], ['A', 'X']])
X_test_df = pd.DataFrame(
    np.hstack([numeric_data_test, categorical_data_test]),
    columns=[f'num_{i}' for i in range(n_numeric)] + [f'cat_{i}' for i in range(n_categorical)]
)

for i in range(n_numeric):
    X_test_df[f'num_{i}'] = pd.to_numeric(X_test_df[f'num_{i}'])
for i in range(n_categorical):
    X_test_df[f'cat_{i}'] = X_test_df[f'cat_{i}'].astype('category')

# Create y data as pandas Series
y_train = pd.Series(np.array([0, 1]))
y_test = pd.Series(np.array([1, 0]))

# Create preprocessor as None to test default behavior
preprocessor = None

ARGS = {
    'X_train': X_train_df,
    'X_test': X_test_df,
    'y_train': y_train,
    'y_test': y_test,
    'preprocessor': preprocessor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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
get_logger Ran
ran on a synthesized input
isg-siegen/assembled/assembled/utils/logger.py
code served (permissive licence) · get_code("154a460210aaad8f")
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 Logger. 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 logging
import sys

ARGS = {
    "name": "test_logger"
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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_benchmark_details Ran
ran on a synthesized input
isg-siegen/assembled/assembled/benchmaker.py
code served (permissive licence) · get_code("db5bcd35c8bb8ff0")
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 os
import json
import tempfile
import shutil

# Create a temporary directory with benchmark details
temp_dir = tempfile.mkdtemp()

# Create sample benchmark details JSON
benchmark_data = {
    "model": "test_model",
    "dataset": "test_dataset",
    "metrics": ["accuracy", "f1_score"],
    "version": "1.0"
}

# Write the JSON file
json_path = os.path.join(temp_dir, 'benchmark_details.json')
with open(json_path, 'w') as f:
    json.dump(benchmark_data, f)

ARGS = {
    "path_to_benchmark_details": temp_dir
}
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
isolate_function Not yet run
unverified (harvested, no recorded run)
isg-siegen/assembled/assembled/utils/isolation.py
code served (permissive licence) · get_code("ac0438370fa2f27e")
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

Automated Machine Learning (AutoML) frameworks regularly use ensembles. Developers need to compare different ensemble techniques to select appropriate techniques for an AutoML framework from the many potential techniques. So far, the comparison of ensemble techniques is often computationally expensive, because many base models must be trained and evaluated one or multiple times. Therefore, we present Assembled-OpenML. Assembled-OpenML is a Python tool, which builds meta-datasets for ensembles using OpenML. A meta-dataset, called Metatask, consists of the data of an OpenML task, the task's dataset, and prediction data from model evaluations for the task. We can make the comparison of ensemble techniques computationally cheaper by using the predictions stored in a metatask instead of training and evaluating base models. To introduce Assembled-OpenML, we describe the first version of our tool. Moreover, we present an example of using Assembled-OpenML to compare a set of ensemble techniques. For this example comparison, we built a benchmark using Assembled-OpenML and implemented ensemble techniques expecting predictions instead of base models as input. In our example comparison, we gathered the prediction data of $1523$ base models for $31$ datasets. Obtaining the prediction data for all base models using Assembled-OpenML took ${\sim} 1$ hour in total. In comparison, obtaining the prediction data by training and evaluating just one base model on the most computationally expensive dataset took ${\sim} 37$ minutes.

For agents

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

get_harvested_code_for_paper("2307.00285")
get_code_for_paper("2307.00285")
have("2307.00285")

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

curl https://syntology.ai/api/ran/2307.00285.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.00285.svg)](https://syntology.ai/paper/2307.00285)

Connect an agent — have() is free.