SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.07638 · 2019

Random Search and Reproducibility for Neural Architecture Search

arXiv · PDF · Open in the Atlas

Code that ran

2 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, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 5 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/1902.07638.json · badge: /api/ran/1902.07638.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
liamcli/randomNAS_release canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
microsoft/nn-meter community (classifier label)
classifier basis not recorded on the link
2 ran · 4 no recorded run
FunctionStatusWhere it lives
load_config_file Ran
ran on a synthesized input
microsoft/nn-meter/nn_meter/builder/config_manager.py
code served (permissive licence) · get_code("7a5022a04158a95d")
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 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 os
import tempfile
import yaml

# Create a temporary workspace directory structure with config files
workspace_path = tempfile.mkdtemp()
configs_dir = os.path.join(workspace_path, 'configs')
os.makedirs(configs_dir, exist_ok=True)

# Create minimal valid YAML config files
backend_config = {
    'backend': 'test_backend',
    'version': '1.0'
}

ruletest_config = {
    'ruletest': 'test_ruletest',
    'enabled': True
}

predictorbuild_config = {
    'predictorbuild': 'test_predictorbuild',
    'model': 'default'
}

# Write config files
backend_filepath = os.path.join(configs_dir, 'backend_config.yaml')
ruletest_filepath = os.path.join(configs_dir, 'ruletest_config.yaml')
predictorbuild_filepath = os.path.join(configs_dir, 'predictorbuild_config.yaml')

with open(backend_filepath, 'w') as f:
    yaml.dump(backend_config, f)

with open(ruletest_filepath, 'w') as f:
    yaml.dump(ruletest_config, f)

with open(predictorbuild_filepath, 'w') as f:
    yaml.dump(predictorbuild_config, f)

ARGS = {
    'workspace_path': workspace_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — 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
merge_info Ran
ran on a synthesized input
microsoft/nn-meter/nn_meter/builder/utils.py
code served (permissive licence) · get_code("b71a0773c6a09b13")
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

# Create temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Case 1: Using info_save_path with a new file (no previous info)
new_info_1 = {
    "module_a": {"param1": 10, "param2": "value1"},
    "module_b": {"param3": 20}
}
info_save_path_1 = os.path.join(temp_dir, "info_new.json")

# Case 2: Using prev_info directly (no file path)
new_info_2 = {
    "module_a": {"param1": 15},
    "module_c": {"param4": 30}
}
prev_info_2 = {
    "module_a": {"param1": 10, "param2": "value1"},
    "module_b": {"param3": 20}
}

# Case 3: Using info_save_path with existing file
existing_file_path = os.path.join(temp_dir, "info_existing.json")
with open(existing_file_path, 'w') as f:
    json.dump({
        "module_x": {"x1": 100, "x2": "existing"},
        "module_y": {"y1": 200}
    }, f)

new_info_3 = {
    "module_x": {"x1": 150},
    "module_z": {"z1": 300}
}

# Test case 1: new_info + info_save_path (new file)
ARGS = {
    "new_info": new_info_1,
    "info_save_path": info_save_path_1,
    "prev_info": None
}
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
convert_models Not yet run
unverified (harvested, no recorded run)
microsoft/nn-meter/nn_meter/builder/nn_meter_builder.py
code served (permissive licence) · get_code("d3f2511e0002a6af")
How it ran

no invocation recorded.

load_predictor_config Not yet run
unverified (harvested, no recorded run)
microsoft/nn-meter/nn_meter/predictor/nn_meter_predictor.py
code served (permissive licence) · get_code("c2ec14f99d80dc2b")
How it ran

no invocation recorded.

main Not yet run
unverified (harvested, no recorded run)
liamcli/randomNAS_release/searchers/random_weight_share.py
pointer only (licence: NONE) · get_code("4be4b8fdd0aa0d3a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liamcli/randomNAS_release when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

onnx_model_to_graph Not yet run
unverified (harvested, no recorded run)
microsoft/nn-meter/nn_meter/ir_converter/utils.py
code served (permissive licence) · get_code("c58336805ae6a6ab")
How it ran

no invocation recorded.

profile_models Not yet run
unverified (harvested, no recorded run)
microsoft/nn-meter/nn_meter/builder/nn_meter_builder.py
code served (permissive licence) · get_code("9370e87a7f7cbebd")
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, 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 7 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 research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In this work, in order to help ground the empirical results in this field, we propose new NAS baselines that build off the following observations: (i) NAS is a specialized hyperparameter optimization problem; and (ii) random search is a competitive baseline for hyperparameter optimization. Leveraging these observations, we evaluate both random search with early-stopping and a novel random search with weight-sharing algorithm on two standard NAS benchmarks---PTB and CIFAR-10. Our results show that random search with early-stopping is a competitive NAS baseline, e.g., it performs at least as well as ENAS, a leading NAS method, on both benchmarks. Additionally, random search with weight-sharing outperforms random search with early-stopping, achieving a state-of-the-art NAS result on PTB and a highly competitive result on CIFAR-10. Finally, we explore the existing reproducibility issues of published NAS results. We note the lack of source material needed to exactly reproduce these results, and further discuss the robustness of published results given the various sources of variability in NAS experimental setups. Relatedly, we provide all information (code, random seeds, documentation) needed to exactly reproduce our results, and report our random search with weight-sharing results for each benchmark on multiple runs.

For agents

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

get_harvested_code_for_paper("1902.07638")
get_code_for_paper("1902.07638")
have("1902.07638")

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

curl https://syntology.ai/api/ran/1902.07638.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.07638.svg)](https://syntology.ai/paper/1902.07638)

Connect an agent — have() is free.