SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.12857 · 2020

NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search

arXiv · PDF · Open in the Atlas

Code that ran

2 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 0 have no contract verdict; 2 failures of our instrument; 2 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/2003.12857.json · badge: /api/ran/2003.12857.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
auroua/NPENASv1 canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
FunctionStatusWhere it lives
evolution_search_case1 Ran
ran; our contract draft was wrong, not the code
auroua/NPENASv1/nas_lib/algos/evolution.py
code served (permissive licence) · get_code("353f720011876855")
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 list, 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 random
import numpy as np

class MockSearchSpace:
    """Mock search space that simulates architecture search."""
    
    def __init__(self):
        self.arch_counter = 0
        self.random_state = np.random.RandomState(42)
    
    def generate_random_dataset(self, num=10, allow_isomorphisms=False, deterministic_loss=True):
        """Generate random dataset of (arch, metadata, loss) tuples."""
        data = []
        for i in range(num):
            arch = f"arch_{self.arch_counter}"
            self.arch_counter += 1
            metadata = {"id": i}
            loss = self.random_state.uniform(0.1, 0.9)
            data.append((arch, metadata, loss))
        return data
    
    def mutate_arch(self, arch, mutation_rate):
        """Mutate an architecture."""
        mutated = f"{arch}_mutated_{self.arch_counter}"
        self.arch_counter += 1
        return mutated
    
    def query_arch(self, arch, deterministic=True):
        """Query an architecture and return (arch, metadata, loss) tuple."""
        metadata = {"queried": True}
        if deterministic:
            loss = 0.5
        else:
            loss = self.random_state.uniform(0.1, 0.9)
        return (arch, metadata, loss)


search_space = MockSearchSpace()

ARGS = {
    "search_space": search_space,
    "num_init": 10,
    "k": 10,
    "population_size": 30,
    "total_queries": 100,
    "tournament_size": 10,
    "mutation_rate": 1.0,
    "allow_isomorphisms": False,
    "deterministic": True,
    "verbose": 1,
    "logger": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, 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
evolution_search_case2 Ran
ran; our contract draft was wrong, not the code
auroua/NPENASv1/nas_lib/algos/evolution.py
code served (permissive licence) · get_code("e840d840463ce034")
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 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 random
import numpy as np
from unittest.mock import Mock

# Create a minimal search_space mock that implements the required methods
class MockSearchSpace:
    def __init__(self):
        self.call_count = 0
    
    def generate_random_dataset(self, num, allow_isomorphisms=False, deterministic_loss=False):
        """
        Returns a list of tuples: (id, matrix, ops, other_data, val_loss)
        Each element represents an architecture candidate
        """
        dataset = []
        for i in range(num):
            # matrix: 4x3 adjacency matrix
            matrix = np.random.rand(4, 3)
            # ops: list of operation strings
            ops = ['conv3x3', 'conv1x1', 'maxpool3x3']
            # other_data: placeholder
            other_data = {'info': f'arch_{i}'}
            # val_loss: validation loss (float)
            val_loss = float(np.random.rand())
            dataset.append((i, matrix, ops, other_data, val_loss))
        return dataset
    
    def mutate_arch(self, arch_dict, mutation_rate):
        """
        Takes a dict with 'matrix' and 'ops' keys, returns mutated architecture
        """
        matrix = arch_dict['matrix'].copy()
        ops = arch_dict['ops'].copy()
        
        # Simulate mutation
        if np.random.rand() < mutation_rate:
            matrix = matrix + np.random.randn(*matrix.shape) * 0.1
        
        # Return in same format as generate_random_dataset
        val_loss = float(np.random.rand())
        return (len(matrix), matrix, ops, {'mutated': True}, val_loss)

# Create a mock logger
class MockLogger:
    def info(self, msg):
        print(msg)

# Set random seed for reproducibility
random.seed(42)
np.random.seed(42)

# Build ARGS dictionary
ARGS = {
    'search_space': MockSearchSpace(),
    'num_init': 10,
    'k': 10,
    'population_size': 30,
    'total_queries': 100,
    'tournament_size': 10,
    'mutation_rate': 1.0,
    'allow_isomorphisms': False,
    'deterministic': True,
    'verbose': 1,
    'logger': MockLogger(),
    'record_kt': 'F',
    'record_mutation': 'F',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
gin_predictor_case1 Not yet run
unverified (harvested, no recorded run)
auroua/NPENASv1/nas_lib/algos/predictor.py
code served (permissive licence) · get_code("7bb483d43904f827")
How it ran

no invocation recorded.

gin_uncertainty_case1 Not yet run
unverified (harvested, no recorded run)
auroua/NPENASv1/nas_lib/algos/predictor.py
code served (permissive licence) · get_code("239ad7be53fae717")
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

Neural architecture search (NAS) is a promising method for automatically design neural architectures. NAS adopts a search strategy to explore the predefined search space to find outstanding performance architecture with the minimum searching costs. Bayesian optimization and evolutionary algorithms are two commonly used search strategies, but they suffer from computationally expensive, challenge to implement or inefficient exploration ability. In this paper, we propose a neural predictor guided evolutionary algorithm to enhance the exploration ability of EA for NAS (NPENAS) and design two kinds of neural predictors. The first predictor is defined from Bayesian optimization and we propose a graph-based uncertainty estimation network as a surrogate model that is easy to implement and computationally efficient. The second predictor is a graph-based neural network that directly outputs the performance prediction of the input neural architecture. The NPENAS using the two neural predictors are denoted as NPENAS-BO and NPENAS-NP respectively. In addition, we introduce a new random architecture sampling method to overcome the drawbacks of the existing sampling method. Extensive experiments demonstrate the superiority of NPENAS. Quantitative results on three NAS search spaces indicate that both NPENAS-BO and NPENAS-NP outperform most existing NAS algorithms, with NPENAS-BO achieving state-of-the-art performance on NASBench-201 and NPENAS-NP on NASBench-101 and DARTS, respectively.

For agents

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

get_harvested_code_for_paper("2003.12857")
get_code_for_paper("2003.12857")
have("2003.12857")

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

curl https://syntology.ai/api/ran/2003.12857.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.12857.svg)](https://syntology.ai/paper/2003.12857)

Connect an agent — have() is free.