SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.01569 · 2019

Exploring Randomly Wired Neural Networks for Image Recognition

arXiv · PDF · Open in the Atlas

Code that ran

10 of 31 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 7 have no contract verdict; 3 failures of our instrument; 21 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/1904.01569.json · badge: /api/ran/1904.01569.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
swdsld/RandWire_tensorflow community (classifier label)
classifier basis not recorded on the link
6 ran · 7 no recorded run
hebo1221/RandWireNN community (classifier label)
classifier basis not recorded on the link
3 ran · 6 no recorded run
timctho/random-wired-nn-tensorflow community (classifier label)
classifier basis not recorded on the link
1 ran · 7 no recorded run
leaderj1001/RandWireNN community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
build_graph Ran
ran on a synthesized input
hebo1221/RandWireNN/utils/graph.py
code served (permissive licence) · get_code("7a664040a2491c18")
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 Graph. 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 networkx as nx


class Config:
    def __init__(self):
        self.GRAPH_MODEL = 'ER'
        self.ER_P = 0.3
        self.BA_M = 2
        self.WS_K = 4
        self.WS_P = 0.5
        self.RND_SEED = 42


ARGS = {
    'Nodes': 10,
    'cfg': Config()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph — a Graph output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Graph output the recorded ndim 1 and dtype family int 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
bytes_feature Ran
ran; our contract draft was wrong, not the code
swdsld/RandWire_tensorflow/dataset/dataset_generator.py
code served (permissive licence) · get_code("d682a9593710857e")
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 Feature. 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

# bytes_feature expects a single parameter 'value' which should be bytes
# The function wraps it in tf.train.BytesList and then tf.train.Feature

ARGS = {
    "value": b"example_bytes_data"
}
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 Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
flip Ran
ran on a synthesized input
swdsld/RandWire_tensorflow/dataset/iter_utils.py
code served (permissive licence) · get_code("110b12d7b7a7feff")
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 tensorflow as tf
import numpy as np

# Create a small image tensor
# TensorFlow expects images as uint8 or float32
# Shape: (height, width, channels)
image = tf.constant(np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8), dtype=tf.uint8)

# Create a label (can be any value, function just returns it)
label = 0

ARGS = {
    "image": image,
    "label": label,
}
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 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
get_filenames Ran
ran on a synthesized input
timctho/random-wired-nn-tensorflow/src/dataset/imagenet.py
code served (permissive licence) · get_code("0b9d9456df95e57d")
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 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 tempfile
import os

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
train_dir = os.path.join(temp_dir, 'train')
validation_dir = os.path.join(temp_dir, 'validation')
os.makedirs(train_dir, exist_ok=True)
os.makedirs(validation_dir, exist_ok=True)

# Create some dummy files
open(os.path.join(train_dir, 'file1.txt'), 'w').close()
open(os.path.join(train_dir, 'file2.txt'), 'w').close()
open(os.path.join(validation_dir, 'file3.txt'), 'w').close()
open(os.path.join(validation_dir, 'file4.txt'), 'w').close()

ARGS = {
    'is_training': True,
    'data_dir': temp_dir
}
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 list, ndim 1, 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
int64_feature Ran
ran; our contract draft was wrong, not the code
swdsld/RandWire_tensorflow/dataset/dataset_generator.py
code served (permissive licence) · get_code("328d17201d9a0e68")
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 Feature. 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

def int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))

ARGS = {
    "value": 42
}
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 Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
int64_list_feature Ran
ran on a synthesized input
swdsld/RandWire_tensorflow/dataset/dataset_generator.py
code served (permissive licence) · get_code("f6d735872f4495ed")
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 Feature. 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

# The function expects a 'value' parameter that will be passed to
# tf.train.Int64List(value=value). This should be an iterable of integers.

ARGS = {
    "value": [1, 2, 3, 4, 5]
}
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 Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
merge_configs Ran
ran on a synthesized input
hebo1221/RandWireNN/utils/config_helpers.py
code served (permissive licence) · get_code("9c0c354019b5b11c")
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 EasyDict. 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
from easydict import EasyDict

# Test case 1: Simple merge of two dicts
config1 = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'model': {
        'layers': 3,
        'hidden_dim': 64
    }
}

config2 = {
    'batch_size': 64,
    'model': {
        'hidden_dim': 128
    },
    'epochs': 10
}

# Test case 2: Merge with numpy arrays
config3 = {
    'learning_rate': 0.0005,
    'weights': np.array([1.0, 2.0, 3.0], dtype=np.float32)
}

config4 = {
    'weights': np.array([4.0, 5.0, 6.0], dtype=np.float32),
    'optimizer': 'adam'
}

# Test case 3: Three-way merge
config5 = {
    'param_a': 1,
    'nested': {'x': 10}
}

config6 = {
    'param_a': 2,
    'param_b': 3,
    'nested': {'y': 20}
}

config7 = {
    'param_c': 4,
    'nested': {'z': 30}
}

# Create config lists to test different scenarios
config_list_1 = [config1, config2]
config_list_2 = [config3, config4]
config_list_3 = [config5, config6, config7]

ARGS = {
    'config_list': config_list_1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict 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
parse_devkit Ran
ran; our contract draft was wrong, not the code
hebo1221/RandWireNN/utils/dataloader.py
code served (permissive licence) · get_code("10d196b211843339")
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 os
import tempfile
import scipy.io as sio
import numpy as np

# Create a temporary directory structure with necessary files
tmpdir = tempfile.mkdtemp()
data_dir = os.path.join(tmpdir, 'data')
os.makedirs(data_dir, exist_ok=True)

# Create a minimal meta.mat file
# The meta structure needs synsets with fields indexed at position 4 being num_children
# Structure: (idx, wnid, classes, parent_idx, num_children, ...)
meta_data = np.array([
    (1, 'n0001', 'dog, puppy', 0, 0),
    (2, 'n0002', 'cat, feline', 0, 0),
    (3, 'n0003', 'animal', 0, 2),
], dtype=[('idx', 'i4'), ('wnid', 'U10'), ('classes', 'U50'), ('parent', 'i4'), ('num_children', 'i4')])

sio.savemat(
    os.path.join(data_dir, 'meta.mat'),
    {'synsets': meta_data},
    do_compression=False
)

# Create validation ground truth file
val_ground_truth_path = os.path.join(data_dir, 'ILSVRC2012_validation_ground_truth.txt')
with open(val_ground_truth_path, 'w') as f:
    f.write('1\n')
    f.write('2\n')
    f.write('1\n')

ARGS = {
    'root': tmpdir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
read_meta Ran
ran on a synthesized input
swdsld/RandWire_tensorflow/dataset/cifar10/cifar10.py
code served (permissive licence) · get_code("24c0c54d387a898f")
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 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 pickle
import tempfile
import os

# Create a temporary file with pickled metadata
temp_dir = tempfile.mkdtemp()
filename = os.path.join(temp_dir, 'batches.meta')

# Create the expected pickle structure
meta_dict = {
    b'label_names': [b'airplane', b'automobile', b'bird', b'cat', b'deer']
}

with open(filename, 'wb') as f:
    pickle.dump(meta_dict, f)

ARGS = {
    'filename': 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 list, ndim 1, 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
standardization Ran
ran on a synthesized input
swdsld/RandWire_tensorflow/dataset/iter_utils.py
code served (permissive licence) · get_code("63508099a4ccf94d")
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 tensorflow as tf
import numpy as np

# Create a small image tensor (height=4, width=3, channels=3)
image = tf.constant(np.random.randn(4, 3, 3).astype(np.float32))

# Create a label (can be any value)
label = tf.constant(0, dtype=tf.int32)

ARGS = {
    "image": image,
    "label": label
}
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 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
accuracy Not yet run
unverified (harvested, no recorded run)
hebo1221/RandWireNN/RandWireNN_train.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from boone891214/MEST, is pointer only (licence: NONE) · get_code("913d82af53065418")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from boone891214/MEST, and GitHub detected no licence in that repository 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.

build_stage Not yet run
unverified (harvested, no recorded run)
swdsld/RandWire_tensorflow/network/RandWire.py
code served (permissive licence) · get_code("efe4fed6b02397da")
How it ran

no invocation recorded.

conv_block Not yet run
unverified (harvested, no recorded run)
swdsld/RandWire_tensorflow/network/RandWire.py
code served (permissive licence) · get_code("925c72f289b0471c")
How it ran

no invocation recorded.

convert_to_tf_records Not yet run
unverified (harvested, no recorded run)
timctho/random-wired-nn-tensorflow/src/dataset/imagenet_to_tfrecord.py
code served (permissive licence) · get_code("eebc9108bb04b0a0")
How it ran

no invocation recorded.

dataset Not yet run
unverified (harvested, no recorded run)
timctho/random-wired-nn-tensorflow/src/dataset/mnist.py
code served (permissive licence) · get_code("11ec2c233298a0d4")
How it ran

no invocation recorded.

download Not yet run
unverified (harvested, no recorded run)
timctho/random-wired-nn-tensorflow/src/dataset/mnist.py
code served (permissive licence) · get_code("0d65e022d1e2371e")
How it ran

no invocation recorded.

download_dataset Not yet run
unverified (harvested, no recorded run)
timctho/random-wired-nn-tensorflow/src/dataset/imagenet_to_tfrecord.py
code served (permissive licence) · get_code("46b5f4c4a7bdc5c9")
How it ran

no invocation recorded.

get_graph_info Not yet run
unverified (harvested, no recorded run)
hebo1221/RandWireNN/utils/graph.py
code served (permissive licence) · get_code("ac311b2099cb6644")
How it ran

no invocation recorded.

get_total_loss Not yet run
unverified (harvested, no recorded run)
timctho/random-wired-nn-tensorflow/src/model/util.py
code served (permissive licence) · get_code("8eb610c6ecbc7249")
How it ran

no invocation recorded.

graph_generator Not yet run
unverified (harvested, no recorded run)
swdsld/RandWire_tensorflow/utils/graph_generator.py
code served (permissive licence) · get_code("03fdad149064c68e")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
leaderj1001/RandWireNN/DropPath_RandWireNN/preprocess.py
code served (permissive licence) · get_code("66d8b14bac327fa0")
How it ran

no invocation recorded.

load_graph Not yet run
unverified (harvested, no recorded run)
hebo1221/RandWireNN/utils/graph.py
code served (permissive licence) · get_code("174138ce951dc5a6")
How it ran

no invocation recorded.

pad_and_crop Not yet run
unverified (harvested, no recorded run)
swdsld/RandWire_tensorflow/dataset/iter_utils.py
code served (permissive licence) · get_code("98f8da7ba43d02d6")
How it ran

no invocation recorded.

preprocess_image Not yet run
unverified (harvested, no recorded run)
timctho/random-wired-nn-tensorflow/src/dataset/imagenet_preprocessing.py
code served (permissive licence) · get_code("b21e4335631beda5")
How it ran

no invocation recorded.

read32 Not yet run
unverified (harvested, no recorded run)
timctho/random-wired-nn-tensorflow/src/dataset/mnist.py
code served (permissive licence) · get_code("aec170f547afa0ca")
How it ran

no invocation recorded.

read_cifar10 Not yet run
unverified (harvested, no recorded run)
swdsld/RandWire_tensorflow/dataset/cifar10/cifar10.py
code served (permissive licence) · get_code("133311a54c75881c")
How it ran

no invocation recorded.

read_image Not yet run
unverified (harvested, no recorded run)
swdsld/RandWire_tensorflow/dataset/mnist/mnist.py
code served (permissive licence) · get_code("591b652aaf3077eb")
How it ran

no invocation recorded.

read_label Not yet run
unverified (harvested, no recorded run)
swdsld/RandWire_tensorflow/dataset/mnist/mnist.py
code served (permissive licence) · get_code("38bfe991e2a72c25")
How it ran

no invocation recorded.

train_data_loader Not yet run
unverified (harvested, no recorded run)
hebo1221/RandWireNN/utils/dataloader.py
code served (permissive licence) · get_code("518c0532c14f0053")
How it ran

no invocation recorded.

val_data_loader Not yet run
unverified (harvested, no recorded run)
hebo1221/RandWireNN/utils/dataloader.py
code served (permissive licence) · get_code("bdbd7768b2fdb8c1")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
hebo1221/RandWireNN/RandWireNN_train.py
code served (permissive licence) · get_code("2ff692a2018660a1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 31 samples lifted from this paper's linked repositories, 31 carry a function identity and 0 do not. Of the 31 distinct functions with an identity, 9 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 7 later) and 22 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
accuracy 80 other papers
17 dated earlier, 63 later
1307.0414 (2013-07)
Challenges in Representation Learning: A report on three machine learning contests
1412.6553 (2014-12)
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
1503.02531 (2015-03)
Distilling the Knowledge in a Neural Network
and 77 more not named here
bytes_feature 8 other papers
6 dated earlier, 2 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1607.08022 (2016-07)
Instance Normalization: The Missing Ingredient for Fast Stylization
1609.05158 (2016-09)
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
and 5 more not named here
int64_feature 7 other papers
5 dated earlier, 2 later
1607.08022 (2016-07)
Instance Normalization: The Missing Ingredient for Fast Stylization
1611.07810 (2016-11)
A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering
1802.05591 (2018-02)
Towards End-to-End Lane Detection: an Instance Segmentation Approach
and 4 more not named here
int64_list_feature 5 other papers
3 dated earlier, 2 later
1607.08022 (2016-07)
Instance Normalization: The Missing Ingredient for Fast Stylization
1803.10562 (2018-03)
ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
1812.00442 (2018-12)
Deep Cosine Metric Learning for Person Re-Identification
and 2 more not named here
parse_devkit 4 other papers
4 later
1905.00397 (2019-05)
Fast AutoAugment
2003.03780 (2020-03)
DADA: Differentiable Automatic Data Augmentation
2006.05553 (2020-06)
Neural Methods for Point-wise Dependency Estimation
and 1 more not named here
download 2 other papers
2 dated earlier
1406.2572 (2014-06)
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
1807.10875 (2018-07)
TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
preprocess_image 2 other papers
2 later
1908.07919 (2019-08)
Deep High-Resolution Representation Learning for Visual Recognition
aaai_16474 (2021 (year only))
Optimizing Information Theory Based Bitwise Bottlenecks for Efficient Mixed-Precision Activation Quantization
convert_to_tf_records 1 other paper
1 later
1906.10337 (2019-06)
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
read32 1 other paper
1 dated earlier
1406.2572 (2014-06)
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

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 networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets and DenseNets is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the joint optimization of wiring and operation types, however, the space of possible wirings is constrained and still driven by manual design despite being searched. In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks. To do this, we first define the concept of a stochastic network generator that encapsulates the entire network generation process. Encapsulation provides a unified view of NAS and randomly wired networks. Then, we use three classical random graph models to generate randomly wired graphs for networks. The results are surprising: several variants of these random generators yield network instances that have competitive accuracy on the ImageNet benchmark. These results suggest that new efforts focusing on designing better network generators may lead to new breakthroughs by exploring less constrained search spaces with more room for novel design.

For agents

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

get_harvested_code_for_paper("1904.01569")
get_code_for_paper("1904.01569")
have("1904.01569")

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

curl https://syntology.ai/api/ran/1904.01569.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.01569.svg)](https://syntology.ai/paper/1904.01569)

Connect an agent — have() is free.