SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.00848 · 2019

Neural Predictor for Neural Architecture Search

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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; 3 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/1912.00848.json · badge: /api/ran/1912.00848.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
itouchz/Neural-Predictor-Tensorflow community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
ultmaster/neuralpredictor.pytorch community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
gen_is_edge_fn Ran
ran on a synthesized input
itouchz/Neural-Predictor-Tensorflow/nasbench/lib/graph_util.py
code served (permissive licence) · get_code("b558868dfd1955d6")
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 vectorize. 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

# The function gen_is_edge_fn takes a single parameter: bits
# bits should be an integer that will be interpreted as a bit mask
# Let's use a small integer that will create some edges in the adjacency pattern

ARGS = {
    "bits": 21  # Binary: 010101, which sets bits at positions 0, 2, 4
}
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 vectorize — a vectorize output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a vectorize 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
graph_pooling Ran
ran; our contract draft was wrong, not the code
ultmaster/neuralpredictor.pytorch/model.py
code served (permissive licence) · get_code("0750ccde070048ff")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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)

# Create inputs tensor: batch_size=2, num_vertices=3, features=4
inputs = torch.randn(2, 3, 4)

# Create num_vertices tensor: batch_size=2
num_vertices = torch.tensor([3, 3])

ARGS = {
    "inputs": inputs,
    "num_vertices": num_vertices,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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_full_dag Ran
ran on a synthesized input
itouchz/Neural-Predictor-Tensorflow/nasbench/lib/graph_util.py
code served (permissive licence) · get_code("283b1ed886dfa4c1")
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 numpy as np

# Create a valid full DAG matrix
# A full DAG means:
# 1) All rows except the last have at least one 1 (all vertices have outgoing edges)
# 2) All columns except the first have at least one 1 (all vertices have incoming edges)
# 3) Upper triangular (no cycles)

# 5x5 upper triangular matrix representing a full DAG
matrix = np.array([
    [0, 1, 1, 0, 0],  # vertex 0 has outgoing edges
    [0, 0, 1, 1, 0],  # vertex 1 has outgoing edges
    [0, 0, 0, 1, 1],  # vertex 2 has outgoing edges
    [0, 0, 0, 0, 1],  # vertex 3 has outgoing edges
    [0, 0, 0, 0, 0],  # vertex 4 (output) has no outgoing edges - OK
], dtype=int)

ARGS = {
    "matrix": matrix
}
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 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
normalize_adj Ran
ran; our contract draft was wrong, not the code
ultmaster/neuralpredictor.pytorch/model.py
code served (permissive licence) · get_code("8316e25dc7e10a44")
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 Tensor, ndim 3, dtype family float, shape (2, 4, 4) 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)

# The function normalize_adj expects:
# - adj: a tensor that supports .size(-1), .sum(), .repeat(), and torch.div()
# The function performs:
#   1. Gets last dimension size
#   2. Sums along dimension 2, keeps dimension, repeats along last dimension
#   3. Divides adj by the rowsum
# 
# This suggests adj is a 3D tensor (batch, rows, cols)
# Let's create a small valid adjacency matrix tensor

adj = torch.randn(2, 4, 4)  # batch_size=2, rows=4, cols=4

ARGS = {
    "adj": adj
}
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 Tensor, ndim 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 4) 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
num_edges Ran
ran on a synthesized input
itouchz/Neural-Predictor-Tensorflow/nasbench/lib/graph_util.py
code served (permissive licence) · get_code("2e655699a68fae2a")
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 int64, ndim 0, dtype family int, 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 numpy as np

# Create a simple adjacency matrix
# The function sums all elements, so we need a numeric matrix
# Using a small 3x3 adjacency matrix with some edges
adjacency_matrix = np.array([
    [0, 1, 1],
    [1, 0, 1],
    [1, 1, 0]
], dtype=np.int32)

ARGS = {
    "matrix": adjacency_matrix
}
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 int64, ndim 0, dtype family int, 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
proxylessnas_random Ran
ran on a synthesized input
itouchz/Neural-Predictor-Tensorflow/random_search.py
code served (permissive licence) · get_code("4feff3a3206d13be")
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 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 numpy as np

ARGS = {
    'num_reps': 5,
    'latency_limit': (-1, -1)
}
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 list, ndim 2, dtype family int — 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
s_sigmoid Ran
ran on a synthesized input
itouchz/Neural-Predictor-Tensorflow/neural_predictor.py
code served (permissive licence) · get_code("aff00961c29617af")
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 EagerTensor, ndim 2, dtype family float, shape (2, 4) 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 tensorflow as tf
import numpy as np

def s_sigmoid(x):
    x = tf.sigmoid(x) * 100
    x = tf.where(x >= 100.0, 100.0, x)
    return x

# Create a small test tensor
x_input = tf.constant([[0.5, 1.0, -0.5, 2.0], [0.0, -1.0, 0.3, 1.5]], dtype=tf.float32)

ARGS = {
    "x": x_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
ss_sigmoid Ran
ran on a synthesized input
itouchz/Neural-Predictor-Tensorflow/neural_predictor.py
code served (permissive licence) · get_code("7c9f99c94a16f920")
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 EagerTensor, ndim 2, dtype family float, shape (2, 4) 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 tensorflow as tf
import numpy as np

# Create a small TensorFlow tensor as input
x = tf.constant([[-2.0, 0.0, 2.0, 5.0], [1.5, -1.5, 3.0, 4.5]], dtype=tf.float32)

# Define the arguments dictionary
ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
to_cuda Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ultmaster/neuralpredictor.pytorch/utils.py
code served (permissive licence) · get_code("55e3ec7719400172")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Test case 1: tensor input
tensor_obj = torch.randn(2, 4)

# Test case 2: tuple of tensors
tuple_obj = (torch.randn(2, 4), torch.randn(3, 5))

# Test case 3: list of tensors
list_obj = [torch.randn(2, 4), torch.randn(3, 5)]

# Test case 4: dict with tensor values
dict_obj = {
    "tensor1": torch.randn(2, 4),
    "tensor2": torch.randn(3, 5),
    "nested_list": [torch.randn(2, 4)],
    "nested_dict": {"inner_tensor": torch.randn(2, 4)}
}

# Test case 5: primitive types
int_obj = 42
float_obj = 3.14
str_obj = "hello"

# Test case 6: nested structures
nested_obj = {
    "tensors": [torch.randn(2, 4), torch.randn(3, 5)],
    "tuple": (torch.randn(2, 4), 5, "test"),
    "scalar": 10
}

ARGS = {
    "obj": tensor_obj
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
conv_bn_relu Not yet run
unverified (harvested, no recorded run)
itouchz/Neural-Predictor-Tensorflow/nasbench/lib/base_ops.py
code served (permissive licence) · get_code("1500e49c46a26813")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 3 later) and 3 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
normalize_adj 3 other papers
1 dated earlier, 2 later
1810.05749 (2018-10)
Graph HyperNetworks for Neural Architecture Search
2207.10049 (2022-07)
Pretraining a Neural Network before Knowing Its Architecture
2210.14016 (2022-10)
Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
graph_pooling 2 other papers
1 dated earlier, 1 later
1810.05749 (2018-10)
Graph HyperNetworks for Neural Architecture Search
2207.10049 (2022-07)
Pretraining a Neural Network before Knowing Its Architecture
to_cuda 2 other papers
1 dated earlier, 1 later
1810.05749 (2018-10)
Graph HyperNetworks for Neural Architecture Search
2207.10049 (2022-07)
Pretraining a Neural Network before Knowing Its Architecture
conv_bn_relu 1 other paper
1 dated earlier
1902.09635 (2019-02)
NAS-Bench-101: Towards Reproducible Neural Architecture Search
gen_is_edge_fn 1 other paper
1 dated earlier
1902.09635 (2019-02)
NAS-Bench-101: Towards Reproducible Neural Architecture Search
is_full_dag 1 other paper
1 dated earlier
1902.09635 (2019-02)
NAS-Bench-101: Towards Reproducible Neural Architecture Search
num_edges 1 other paper
1 dated earlier
1902.09635 (2019-02)
NAS-Bench-101: Towards Reproducible 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 methods are effective but often use complex algorithms to come up with the best architecture. We propose an approach with three basic steps that is conceptually much simpler. First we train N random architectures to generate N (architecture, validation accuracy) pairs and use them to train a regression model that predicts accuracy based on the architecture. Next, we use this regression model to predict the validation accuracies of a large number of random architectures. Finally, we train the top-K predicted architectures and deploy the model with the best validation result. While this approach seems simple, it is more than 20 times as sample efficient as Regularized Evolution on the NASBench-101 benchmark and can compete on ImageNet with more complex approaches based on weight sharing, such as ProxylessNAS.

For agents

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

get_harvested_code_for_paper("1912.00848")
get_code_for_paper("1912.00848")
have("1912.00848")

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

curl https://syntology.ai/api/ran/1912.00848.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.00848.svg)](https://syntology.ai/paper/1912.00848)

Connect an agent — have() is free.