SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.01015 · 2021

Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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, 2 violated it and 0 have no contract verdict; 2 failures 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/2105.01015.json · badge: /api/ran/2105.01015.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/multi-obj-baselines canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
get_budgets Ran
ran, honoured the contract we drafted
automl/multi-obj-baselines/baselines/methods/shemoa/shemoa.py
code served (permissive licence) · get_code("45f2cf458c73a0ec")
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 math
import numpy as np

ARGS = {
    "bmin": 4,
    "bmax": 128,
    "eta": 2,
    "max_evals": 1000,
    "pop_size": 50
}
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 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
load_experiment Ran
ran; our contract draft was wrong, not the code
automl/multi-obj-baselines/baselines/core/multiobjective_experiment.py
code served (permissive licence) · get_code("45e296fc334698d8")
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 = {
    "model_state": [1, 2, 3],
    "config": {"learning_rate": 0.001, "epochs": 10},
    "results": [0.95, 0.97, 0.99]
}

# Create a temporary file and save the test data
temp_dir = tempfile.gettempdir()
temp_filename = os.path.join(temp_dir, "test_experiment.pkl")

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

ARGS = {
    "filename": temp_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
nDS_index Ran
ran, honoured the contract we drafted
automl/multi-obj-baselines/baselines/core/pareto.py
code served (permissive licence) · get_code("7ee0e5b484a7fac2")
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

# Create sample data for testing nDS_index
# costs: (n_points, m_cost_values) array - we'll use 5 points with 2 cost values each
costs = np.array([
    [1.0, 5.0],
    [2.0, 4.0],
    [3.0, 3.0],
    [4.0, 2.0],
    [5.0, 1.0]
], dtype=np.float32)

# index_list: array of indices corresponding to each point in costs
index_list = np.array([0, 1, 2, 3, 4], dtype=np.int32)

ARGS = {
    "costs": costs,
    "index_list": index_list
}
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
pareto Ran
ran, violated the contract we drafted
automl/multi-obj-baselines/baselines/core/pareto.py
code served (permissive licence) · get_code("f46a5480051b974f")
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 1, dtype family float, shape (5,) 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 small 2D cost array with 5 points and 3 cost dimensions
# This represents 5 points, each with 3 different cost values to minimize
costs = np.array([
    [1.0, 2.0, 3.0],      # point 0
    [2.0, 1.0, 4.0],      # point 1
    [3.0, 3.0, 1.0],      # point 2
    [1.5, 1.5, 1.5],      # point 3 - likely on pareto front
    [5.0, 5.0, 5.0],      # point 4 - dominated
], dtype=np.float32)

ARGS = {
    "costs": costs
}
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 1, dtype family float, shape (5,) — shape (5,) 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
pareto_index Ran
ran; our contract draft was wrong, not the code
automl/multi-obj-baselines/baselines/core/pareto.py
code served (permissive licence) · get_code("7f70268ea14d24e2")
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

# Create costs array with shape (n_points, m_cost_values)
# Using 5 points and 3 cost dimensions
costs = np.array([
    [1.0, 2.0, 3.0],
    [2.0, 1.0, 2.0],
    [3.0, 3.0, 1.0],
    [0.5, 0.5, 0.5],
    [4.0, 4.0, 4.0]
], dtype=float)

# Create index_list as a numpy array that maps points to their indices
# This will be used to return the indices of pareto-optimal points
index_list = np.array([10, 20, 30, 40, 50])

ARGS = {
    "costs": costs,
    "index_list": index_list
}
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
str2bool Ran
ran, violated the contract we drafted
automl/multi-obj-baselines/baselines/methods/mobohb/run_mobohb.py
code served (permissive licence) · get_code("7c508037b40522af")
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) 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 argparse

def str2bool(v):
    if isinstance(v, bool):
        return v
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# Test cases for str2bool
ARGS = {
    'v': 'true'  # string input that should convert to boolean
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 5 later) and 1 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
str2bool 175 other papers
28 dated earlier, 3 the same month, 144 later · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
load_experiment 1 other paper
1 later
2210.06015 (2022-10)
EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search
nDS_index 1 other paper
1 later
2210.06015 (2022-10)
EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search
pareto 1 other paper
1 later
2210.06015 (2022-10)
EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search
pareto_index 1 other paper
1 later
2210.06015 (2022-10)
EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search

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

Neural architecture search (NAS) and hyperparameter optimization (HPO) make deep learning accessible to non-experts by automatically finding the architecture of the deep neural network to use and tuning the hyperparameters of the used training pipeline. While both NAS and HPO have been studied extensively in recent years, NAS methods typically assume fixed hyperparameters and vice versa - there exists little work on joint NAS + HPO. Furthermore, NAS has recently often been framed as a multi-objective optimization problem, in order to take, e.g., resource requirements into account. In this paper, we propose a set of methods that extend current approaches to jointly optimize neural architectures and hyperparameters with respect to multiple objectives. We hope that these methods will serve as simple baselines for future research on multi-objective joint NAS + HPO. To facilitate this, all our code is available at https://github.com/automl/multi-obj-baselines.

For agents

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

get_harvested_code_for_paper("2105.01015")
get_code_for_paper("2105.01015")
have("2105.01015")

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

curl https://syntology.ai/api/ran/2105.01015.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.01015.svg)](https://syntology.ai/paper/2105.01015)

Connect an agent — have() is free.