SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.08541 · IJCAI · 2021

DACBench: A Benchmark Library for Dynamic Algorithm Configuration

Frank Hutter, André Biedenkapp, Marius Lindauer, Steven Adriaensen, Theresa Eimer, Maximilian Reimer

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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, 1 violated it and 0 have no contract verdict; 5 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/2105.08541.json · badge: /api/ran/2105.08541.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
automl/DACBench canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
generate_global_step Ran
ran; our contract draft was wrong, not the code
automl/DACBench/dacbench/plotting.py
code served (permissive licence) · get_code("e35967ef27d45434")
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 pandas as pd

# Create a sample DataFrame with episode and step columns
# The function expects data with at least the x_label_columns present
data = pd.DataFrame({
    'episode': [1, 1, 1, 2, 2, 2, 3, 3],
    'step': [0, 1, 2, 0, 1, 2, 0, 1],
    'reward': [10.5, 11.2, 12.1, 9.8, 10.5, 11.0, 12.3, 13.1],
    'loss': [0.5, 0.45, 0.4, 0.55, 0.48, 0.42, 0.38, 0.35]
})

ARGS = {
    'data': data,
    'x_column': 'global_step',
    'x_label_columns': ['episode', 'step']
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
load_logs Ran
ran; our contract draft was wrong, not the code
automl/DACBench/dacbench/logger.py
code served (permissive licence) · get_code("20a71e68acc4ed60")
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 json
import tempfile
from pathlib import Path

# Create a temporary JSONL file with sample log data
temp_dir = tempfile.mkdtemp()
log_file_path = Path(temp_dir) / "test_logs.jsonl"

# Write sample log entries in JSONL format
log_entries = [
    {
        "instance": 0,
        "episode": 0,
        "step": 1,
        "example_log_val": {
            "values": [0.1, 0.2, 0.3],
            "episode": [0, 0, 0],
            "step": [1, 1, 1]
        }
    },
    {
        "instance": 1,
        "episode": 1,
        "step": 2,
        "example_log_val": {
            "values": [0.4, 0.5, 0.6],
            "episode": [1, 1, 1],
            "step": [2, 2, 2]
        }
    }
]

with open(log_file_path, 'w') as f:
    for entry in log_entries:
        f.write(json.dumps(entry) + '\n')

ARGS = {
    "log_file": log_file_path
}
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 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
plot Ran
ran; our contract draft was wrong, not the code
automl/DACBench/dacbench/plotting.py
code served (permissive licence) · get_code("5432f2deacd9aedd")
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 FacetGrid. 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 seaborn as sns
import numpy as np

# Create a small sample dataset for plotting
np.random.seed(0)
data = pd.DataFrame({
    'x_variable': np.random.choice(['A', 'B', 'C'], 20),
    'y_variable': np.random.randn(20),
    'group': np.random.choice(['Group1', 'Group2'], 20)
})

# Define a simple plot function that returns a FacetGrid
def simple_plot_function(data, x, y, **kwargs):
    """Wrapper around sns.catplot to return a FacetGrid"""
    return sns.catplot(data=data, x=x, y=y, **kwargs)

ARGS = {
    'plot_function': simple_plot_function,
    'settings': {
        'data': data,
        'x': 'x_variable',
        'y': 'y_variable',
    },
    'title': 'Test Plot Title',
    'x_label': 'X Axis Label',
    'y_label': 'Y Axis Label',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, seaborn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FacetGrid — a FacetGrid output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a FacetGrid 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
run_benchmark Ran
ran, violated the contract we drafted
automl/DACBench/dacbench/runner.py
code served (permissive licence) · get_code("34e849e141cb91d1")
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
import gymnasium as gym
from gymnasium import spaces

class DummyAgent:
    def __init__(self):
        self.train_calls = 0
    
    def act(self, state, reward):
        # Return a valid action based on state
        return 0
    
    def train(self, next_state, reward):
        self.train_calls += 1
    
    def end_episode(self, state, reward):
        pass

class DummyEnv(gym.Env):
    def __init__(self):
        self.observation_space = spaces.Box(low=-1, high=1, shape=(4,), dtype=np.float32)
        self.action_space = spaces.Discrete(2)
        self.step_count = 0
        self.max_steps = 3
    
    def reset(self):
        self.step_count = 0
        return np.zeros(4, dtype=np.float32), {}
    
    def step(self, action):
        self.step_count += 1
        next_state = np.random.randn(4).astype(np.float32)
        reward = float(np.random.randn())
        terminated = self.step_count >= self.max_steps
        truncated = False
        info = {}
        return next_state, reward, terminated, truncated, info
    
    def close(self):
        pass

env = DummyEnv()
agent = DummyAgent()
num_episodes = 2
logger = None

ARGS = {
    "env": env,
    "agent": agent,
    "num_episodes": num_episodes,
    "logger": logger
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gymnasium, 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
space_sep_upper Ran
ran; our contract draft was wrong, not the code
automl/DACBench/dacbench/plotting.py
code served (permissive licence) · get_code("d302cf4a9288b61c")
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 str. 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

torch.manual_seed(0)

ARGS = {
    "column_name": "test_column_name"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
split Ran
ran; our contract draft was wrong, not the code
automl/DACBench/dacbench/logger.py
code served (permissive licence) · get_code("6b027295a0e0d3c6")
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 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 torch
from collections.abc import Callable, Iterable

torch.manual_seed(0)

# Define a simple predicate function that returns True for even numbers
def is_even(x: int) -> bool:
    return x % 2 == 0

# Define an iterable - a list of integers
test_iterable = [1, 2, 3, 4, 5, 6, 7, 8]

ARGS = {
    "predicate": is_even,
    "iterable": test_iterable,
}
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 2, dtype family int — 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
flatten_log_entry Not yet run
unverified (harvested, no recorded run)
automl/DACBench/dacbench/logger.py
code served (permissive licence) · get_code("d3747252399e6d3b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 6 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
space_sep_upper 1 other paper
1 later
2202.03259 (2022-02)
Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration

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

Dynamic Algorithm Configuration (DAC) aims to dynamically control a target algorithm's hyperparameters in order to improve its performance. Several theoretical and empirical results have demonstrated the benefits of dynamically controlling hyperparameters in domains like evolutionary computation, AI Planning or deep learning. Replicating these results, as well as studying new methods for DAC, however, is difficult since existing benchmarks are often specialized and incompatible with the same interfaces. To facilitate benchmarking and thus research on DAC, we propose DACBench, a benchmark library that seeks to collect and standardize existing DAC benchmarks from different AI domains, as well as provide a template for new ones. For the design of DACBench, we focused on important desiderata, such as (i) flexibility, (ii) reproducibility, (iii) extensibility and (iv) automatic documentation and visualization. To show the potential, broad applicability and challenges of DAC, we explore how a set of six initial benchmarks compare in several dimensions of difficulty.

For agents

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

get_harvested_code_for_paper("2105.08541")
get_code_for_paper("2105.08541")
have("2105.08541")

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

curl https://syntology.ai/api/ran/2105.08541.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.08541.svg)](https://syntology.ai/paper/2105.08541)

Connect an agent — have() is free.