SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.07191 · 2018

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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 6 have no contract verdict; 0 failures of our instrument; 3 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/1802.07191.json · badge: /api/ran/1802.07191.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
kirthevasank/nasbot canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_average_prediction_error Ran
ran on a synthesized input
kirthevasank/nasbot/gp/unittest_gp_core.py
code served (permissive licence) · get_code("ef50c08f1ff46b68")
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 torch

# The function accesses dataset[4] and computes norm with preds
# dataset needs to be indexable and have at least 5 elements
# dataset[4] should be array-like with a shape that matches preds
# preds should be array-like

# Create a mock dataset as a list/tuple where index 4 contains ground truth values
dataset = [
    np.array([1.0, 2.0, 3.0, 4.0]),
    np.array([5.0, 6.0, 7.0, 8.0]),
    np.array([9.0, 10.0, 11.0, 12.0]),
    np.array([13.0, 14.0, 15.0, 16.0]),
    np.array([1.0, 2.0, 3.0, 4.0])  # This is dataset[4] - ground truth
]

# Create predictions with same shape as dataset[4]
preds = np.array([1.1, 2.1, 2.9, 4.2])

ARGS = {
    "dataset": dataset,
    "preds": preds
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
get_mean_func_from_options Ran
ran on a synthesized input
kirthevasank/nasbot/gp/gp_core.py
code served (permissive licence) · get_code("bd6937e07a692c60")
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 function. 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

class Options:
    def __init__(self, mean_func=None, mean_func_type='mean', mean_func_const=5.0):
        self.mean_func = mean_func
        self.mean_func_type = mean_func_type
        self.mean_func_const = mean_func_const

# Create sample observations
Y = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

# Test case 1: options with mean_func already defined
custom_mean_func = lambda x: np.array([10.0] * len(x))
options_with_func = Options(mean_func=custom_mean_func)

# Test case 2: options without mean_func, using 'mean' type
options_mean = Options(mean_func=None, mean_func_type='mean')

ARGS = {
    'options': options_mean,
    '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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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_model_fn Ran
ran on a synthesized input
kirthevasank/nasbot/cg/run_tensorflow.py
code served (permissive licence) · get_code("f76525418cf49d82")
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 function. 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 tensorflow as tf

class NNStructure:
    def __init__(self):
        self.num_internal_layers = 2
        self.conn_mat = {(0, 1), (1, 2), (0, 2), (2, 3)}
        self.num_units_in_each_layer = [4, 8, 6, None]
        self.layer_labels = ['linear', 'relu', 'elu', 'linear']
        self.class_or_reg = 'class'

nn = NNStructure()
learningRate = 0.01
num_classes = 3

ARGS = {
    'nn': nn,
    'learningRate': learningRate,
    'num_classes': num_classes
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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_noise_var_from_options_and_hyperparams Ran
ran on a synthesized input
kirthevasank/nasbot/gp/gp_core.py
code served (permissive licence) · get_code("94bf803b1d0a42f0")
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

class OptionsConfig:
    def __init__(self, noise_var_type, noise_var_label=None, noise_var_value=None):
        self.noise_var_type = noise_var_type
        self.noise_var_label = noise_var_label
        self.noise_var_value = noise_var_value

# Case 1: noise_var_type == 'tune'
options_tune = OptionsConfig(noise_var_type='tune')
gp_hyperparams_tune = np.array([0.5, 1.2, 2.1])
Y_tune = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

# Case 2: noise_var_type == 'label'
options_label = OptionsConfig(noise_var_type='label', noise_var_label=0.1)
gp_hyperparams_label = np.array([0.5, 1.2, 2.1])
Y_label = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

# Case 3: noise_var_type == 'value' (default case)
options_value = OptionsConfig(noise_var_type='value', noise_var_value=0.05)
gp_hyperparams_value = np.array([0.5, 1.2, 2.1])
Y_value = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

ARGS = {
    'options': options_tune,
    'gp_hyperparams': gp_hyperparams_tune,
    'Y': Y_tune,
    'noise_var_idx': 0
}
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
is_a_conv_layer_label Ran
ran on a synthesized input
kirthevasank/nasbot/nn/neural_network.py
code served (permissive licence) · get_code("f77a8e0b35483ac1")
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 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 torch

torch.manual_seed(0)

ARGS = {
    "layer_label": "conv1"
}
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 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
is_a_pooling_layer_label Ran
ran on a synthesized input
kirthevasank/nasbot/nn/neural_network.py
code served (permissive licence) · get_code("72ee2c78a10ad1ad")
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 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 torch

torch.manual_seed(0)

ARGS = {
    "layer_label": "max_pool"
}
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 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
compute_num_channels_at_each_layer Not yet run
unverified (harvested, no recorded run)
kirthevasank/nasbot/nn/neural_network.py
code served (permissive licence) · get_code("a6a4abcc2973fed9")
How it ran

no invocation recorded.

get_layer_parents Not yet run
unverified (harvested, no recorded run)
kirthevasank/nasbot/cg/cifar/cifar10_model.py
code served (permissive licence) · get_code("86331e4a8e28234f")
How it ran

no invocation recorded.

mlp_definition Not yet run
unverified (harvested, no recorded run)
kirthevasank/nasbot/cg/run_tensorflow.py
code served (permissive licence) · get_code("ddfb882c2b659e1a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Bayesian Optimisation (BO) refers to a class of methods for global optimisation of a function $f$ which is only accessible via point evaluations. It is typically used in settings where $f$ is expensive to evaluate. A common use case for BO in machine learning is model selection, where it is not possible to analytically model the generalisation performance of a statistical model, and we resort to noisy and expensive training and validation procedures to choose the best model. Conventional BO methods have focused on Euclidean and categorical domains, which, in the context of model selection, only permits tuning scalar hyper-parameters of machine learning algorithms. However, with the surge of interest in deep learning, there is an increasing demand to tune neural network \emph{architectures}. In this work, we develop NASBOT, a Gaussian process based BO framework for neural architecture search. To accomplish this, we develop a distance metric in the space of neural network architectures which can be computed efficiently via an optimal transport program. This distance might be of independent interest to the deep learning community as it may find applications outside of BO. We demonstrate that NASBOT outperforms other alternatives for architecture search in several cross validation based model selection tasks on multi-layer perceptrons and convolutional neural networks.

For agents

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

get_harvested_code_for_paper("1802.07191")
get_code_for_paper("1802.07191")
have("1802.07191")

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

curl https://syntology.ai/api/ran/1802.07191.json

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

[![Syntology run record](https://syntology.ai/api/ran/1802.07191.svg)](https://syntology.ai/paper/1802.07191)

Connect an agent — have() is free.