SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1603.05027 · ECCV · 2016

Identity Mappings in Deep Residual Networks

Kaiming He, Xiangyu Zhang, Jian Sun, Shaoqing Ren

arXiv · PDF · Open in the Atlas

Code that ran

14 of 25 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; 1 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 4 failures of our instrument; 11 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/1603.05027.json · badge: /api/ran/1603.05027.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
JoegameZhou/ms-resnetv2 community (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
brain-bzh/MCNN community (classifier label)
classifier basis not recorded on the link
6 ran · 7 no recorded run
Jeongyun-Lee-0423/Classification reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
wenxinxu/resnet-in-tensorflow reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
sitegui/ceci-nest-pas-un-chat community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
cov Ran
ran on a synthesized input
brain-bzh/MCNN/graph_processing/generate_graph.py
code served (permissive licence) · get_code("b360fb65c97f182b")
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 ndarray, ndim 2, dtype family float, shape (2, 2) 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 small test matrix
# The function expects a 2D numpy array (matrix)
# It accesses matrix.shape[1] for the number of columns
# and performs operations like copy(), sum(), and dot()

matrix = np.random.randn(2, 4)  # 2 rows, 4 columns

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 ndarray, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) 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
cre_groundtruth_dict Ran
ran on a synthesized input
JoegameZhou/ms-resnetv2/infer/resnetv2_101/sdk/classification_task_metric.py
code served (permissive licence) · get_code("590865e4e0a3e889")
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
import shutil

# Create a temporary directory for test files
test_dir = tempfile.mkdtemp()

# Create a sample JSON file with the expected structure
sample_annotation = {
    "image": {
        "annotations": [
            {
                "category_id": 5
            }
        ]
    }
}

# Create test JSON files
test_file_1 = os.path.join(test_dir, "image_001.json")
with open(test_file_1, 'w') as f:
    json.dump(sample_annotation, f)

test_file_2 = os.path.join(test_dir, "image_002.json")
with open(test_file_2, 'w') as f:
    json.dump(sample_annotation, f)

# Create a HiAI_label.json file that should be skipped
label_file = os.path.join(test_dir, "HiAI_label.json")
with open(label_file, 'w') as f:
    json.dump({"dummy": "data"}, f)

ARGS = {
    "gtfile_path": test_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 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
cre_groundtruth_dict_fromtxt Ran
ran on a synthesized input
JoegameZhou/ms-resnetv2/infer/resnetv2_101/sdk/classification_task_metric.py
code served (permissive licence) · get_code("b4b1e720f12820d2")
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 tempfile
import os

# Create a temporary file with ground truth data
temp_dir = tempfile.mkdtemp()
gtfile_path = os.path.join(temp_dir, "ground_truth.txt")

# Write sample ground truth data to the temporary file
with open(gtfile_path, 'w') as f:
    f.write("image001.jpg\t0\n")
    f.write("image002.jpg\t1\n")
    f.write("image003.png\t2\n")

ARGS = {
    "gtfile_path": gtfile_path
}
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
create_adjacence_matrix_from_covariance Ran
ran on a synthesized input
brain-bzh/MCNN/graph_processing/generate_graph.py
code served (permissive licence) · get_code("0ed3a7372ac14d78")
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 3, 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

# Create a small covariance-like matrix (4x4)
# Using values between 0 and 1 to simulate correlation/similarity
np.random.seed(0)
matrix = np.random.rand(4, 4).astype(np.float32)

# Ensure values are in valid range for a similarity/correlation matrix
matrix = np.clip(matrix, 0, 1)

# Set k to be reasonable (less than matrix dimension)
k = 2

# symmetric flag
symmetric = True

ARGS = {
    "matrix": matrix,
    "k": k,
    "symmetric": symmetric
}
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 tuple, ndim 3, 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
format_time Ran
ran; our contract draft was wrong, not the code
brain-bzh/MCNN/defferard/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from JunlinHan/YOCO, is pointer only (licence: NONE) · get_code("8d7ec010c29e813b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from JunlinHan/YOCO, 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. A run is recorded.

gen_file_name Ran
ran; our contract draft was wrong, not the code
JoegameZhou/ms-resnetv2/infer/resnetv2_101/sdk/classification_task_metric.py
code served (permissive licence) · get_code("0015055ff7835705")
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

def gen_file_name(img_name):
    full_name = img_name.split('/')[-1]
    return os.path.splitext(full_name)

ARGS = {
    'img_name': 'path/to/image.jpg'
}
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 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
generate_grid_graph Ran
ran on a synthesized input
brain-bzh/MCNN/graph_processing/translation_search.py
code served (permissive licence) · get_code("0430562f92bd5967")
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 ndarray, ndim 2, dtype family float, shape (16, 16) 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

ARGS = {
    "W": 4,
    "H": 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 ndarray, ndim 2, dtype family float, shape (16, 16) — shape (16, 16) 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
get_center Ran
ran on a synthesized input
brain-bzh/MCNN/graph_processing/translation_search.py
code served (permissive licence) · get_code("43278cc51d5e4611")
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 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
import tqdm

# Create a small adjacency matrix A
# This represents a graph where A[i,j] > 0 means there's an edge from i to j
# Using a 4x4 matrix for a small graph
A = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [1, 1, 0, 1],
    [0, 1, 1, 0]
], dtype=float)

ARGS = {
    "A": A
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tqdm — 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 int — 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
lr_schedule Ran
ran, honoured the contract we drafted
Jeongyun-Lee-0423/Classification/cifar10_resnet.py
pointer only (licence: NONE) · get_code("67e18e3fdd805d03")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jeongyun-Lee-0423/Classification 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. A run is recorded.

merge Ran
ran; our contract draft was wrong, not the code
JoegameZhou/ms-resnetv2/model_utils/config.py
code served (permissive licence) · get_code("b9e24c3e3e0e88a7")
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 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 torch
import argparse

torch.manual_seed(0)

# Create a mock args object with some attributes
args = argparse.Namespace(
    learning_rate=0.001,
    batch_size=32,
    epochs=10,
    model_name="test_model",
    debug=True,
    seed=42
)

# Create a base configuration dictionary
cfg = {
    "default_lr": 0.0001,
    "default_batch": 16,
    "dataset": "cifar10"
}

ARGS = {
    "args": args,
    "cfg": cfg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
parse_cli_to_yaml Ran
ran; our contract draft was wrong, not the code
JoegameZhou/ms-resnetv2/model_utils/config.py
code served (permissive licence) · get_code("738456e1b7388e7e")
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 Namespace. 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 argparse
import ast

# Create minimal parent parser
parent_parser = argparse.ArgumentParser(add_help=False)

# Create base configuration dict with various types
cfg = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 10,
    'use_cuda': False,
    'model_name': 'resnet50',
    'dropout': 0.5,
    'debug': True,
    'nested_list': [1, 2, 3],  # This will be skipped since it's a list
    'nested_dict': {'a': 1},   # This will be skipped since it's a dict
}

# Create helper descriptions
helper = {
    'learning_rate': 'Learning rate for optimizer',
    'batch_size': 'Batch size for training',
    'epochs': 'Number of training epochs',
    'use_cuda': 'Whether to use CUDA',
    'model_name': 'Name of the model architecture',
    'dropout': 'Dropout rate',
    'debug': 'Enable debug mode',
}

# Create choices for specific parameters
choices = {
    'model_name': ['resnet50', 'vgg16', 'mobilenet'],
}

# Set config path
cfg_path = 'default_config.yaml'

ARGS = {
    'parser': parent_parser,
    'cfg': cfg,
    'helper': helper,
    'choices': choices,
    'cfg_path': cfg_path,
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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_yaml Ran
ran on a synthesized input
JoegameZhou/ms-resnetv2/model_utils/config.py
code served (permissive licence) · get_code("96a9939953d5992d")
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 tempfile
import os
import yaml

# Create a temporary YAML file with valid config structure
temp_dir = tempfile.mkdtemp()
yaml_path = os.path.join(temp_dir, "config.yaml")

# Write a valid YAML file with 3 documents: config, helper, and choices
yaml_content = """
model: resnet50
learning_rate: 0.001
batch_size: 32
---
model: "Model architecture to use"
learning_rate: "Learning rate for optimization"
batch_size: "Batch size for training"
---
model: [resnet50, resnet101, vgg16]
learning_rate: [0.0001, 0.001, 0.01]
batch_size: [16, 32, 64]
"""

with open(yaml_path, 'w') as f:
    f.write(yaml_content)

ARGS = {
    "yaml_path": yaml_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
prepare_covariance_matrix Ran
ran on a synthesized input
brain-bzh/MCNN/graph_processing/generate_graph.py
code served (permissive licence) · get_code("cfa5d19782f91d21")
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 ndarray, ndim 2, dtype family float, shape (3, 3) 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 small test matrix
# The function expects a 2D numpy array
# Using shape (3, 4) to have distinct dimensions
matrix = np.random.randn(3, 4)

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 ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 3) 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
read_file_list Ran
ran on a synthesized input
JoegameZhou/ms-resnetv2/infer/resnetv2_152/sdk/prec/eval_sdk.py
code served (permissive licence) · get_code("b5abc534653271c4")
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 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 tempfile
import os

# Create a temporary file with sample data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("image1.bin,0\n")
temp_file.write("image2.bin,1\n")
temp_file.write("image3.bin,2\n")
temp_file.close()

ARGS = {
    'input_f': temp_file.name
}
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 tuple, ndim 2, 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
ChebPreActResNet18 Not yet run
unverified (harvested, no recorded run)
brain-bzh/MCNN/defferard/models/chebnet_preact_resnet.py
code served (permissive licence) · get_code("cde0a8a6285fbdc7")
How it ran

no invocation recorded.

ChebPreActResNet34 Not yet run
unverified (harvested, no recorded run)
brain-bzh/MCNN/defferard/models/chebnet_preact_resnet.py
code served (permissive licence) · get_code("7e7353108b3eed6f")
How it ran

no invocation recorded.

GraphPreActResNet16 Not yet run
unverified (harvested, no recorded run)
brain-bzh/MCNN/defferard/graph.py
code served (permissive licence) · get_code("e653c1088e9d075a")
How it ran

no invocation recorded.

GraphPreActResNet18 Not yet run
unverified (harvested, no recorded run)
brain-bzh/MCNN/defferard/graph.py
code served (permissive licence) · get_code("1d4797c32ffbd2c7")
How it ran

no invocation recorded.

MiniChebNet Not yet run
unverified (harvested, no recorded run)
brain-bzh/MCNN/defferard/models/chebnet_preact_resnet.py
code served (permissive licence) · get_code("9ade73802f8550c8")
How it ran

no invocation recorded.

batch_normalization_layer Not yet run
unverified (harvested, no recorded run)
wenxinxu/resnet-in-tensorflow/resnet.py
code served (permissive licence) · get_code("6b5c23ab3faf0b82")
How it ran

no invocation recorded.

collect_images_from_directory Not yet run
unverified (harvested, no recorded run)
sitegui/ceci-nest-pas-un-chat/myutils.py
code served (permissive licence) · get_code("eff1e476cb4ffcbb")
How it ran

no invocation recorded.

extract_data Not yet run
unverified (harvested, no recorded run)
JoegameZhou/ms-resnetv2/infer/resnetv2_152/dataprocess/preprocess.py
code served (permissive licence) · get_code("569e04900031b215")
How it ran

no invocation recorded.

extract_test_data Not yet run
unverified (harvested, no recorded run)
JoegameZhou/ms-resnetv2/infer/resnetv2_152/dataprocess/preprocess.py
code served (permissive licence) · get_code("847447d82fbd6630")
How it ran

no invocation recorded.

get_mean_and_std Not yet run
unverified (harvested, no recorded run)
brain-bzh/MCNN/defferard/utils.py
code served (permissive licence) · get_code("7bd3a77007a65eec")
How it ran

no invocation recorded.

read_graph Not yet run
unverified (harvested, no recorded run)
brain-bzh/MCNN/graph_processing/translation_search.py
code served (permissive licence) · get_code("043a08fc8f5dbadb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 8 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 8 later) and 17 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
format_time 37 other papers
37 later
1605.07146 (2016-05)
Wide Residual Networks
1805.11327 (2018-05)
Lightweight Probabilistic Deep Networks
1809.00287 (2018-09)
Learning to Navigate for Fine-grained Classification
and 34 more not named here
merge 28 other papers
4 dated earlier, 1 the same month, 23 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
and 25 more not named here
parse_cli_to_yaml 20 other papers
4 dated earlier, 1 the same month, 15 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
and 17 more not named here
get_mean_and_std 18 other papers
18 later
1605.07146 (2016-05)
Wide Residual Networks
1805.11327 (2018-05)
Lightweight Probabilistic Deep Networks
1906.02629 (2019-06)
When Does Label Smoothing Help?
and 15 more not named here
parse_yaml 15 other papers
4 dated earlier, 1 the same month, 10 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
and 12 more not named here
lr_schedule 7 other papers
1 dated earlier, 6 later
1511.06807 (2015-11)
Adding Gradient Noise Improves Learning for Very Deep Networks
1807.06521 (2018-07)
CBAM: Convolutional Block Attention Module
1905.05040 (2019-05)
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
and 4 more not named here
batch_normalization_layer 1 other paper
1 later
2109.03082 (2021-09)
Perceptual Learned Video Compression with Recurrent Conditional GAN
gen_file_name 1 other paper
1 later
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks

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

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep residual networks [1] have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. A series of ablation experiments support the importance of these identity mappings. This motivates us to propose a new residual unit, which makes training easier and improves generalization. We report improved results using a 1001-layer ResNet on CIFAR-10 (4.62% error) and CIFAR-100, and a 200-layer ResNet on ImageNet. Code is available at: https://github.com/KaimingHe/ resnet-1k-layers.

For agents

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

get_harvested_code_for_paper("1603.05027")
get_code_for_paper("1603.05027")
have("1603.05027")

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

curl https://syntology.ai/api/ran/1603.05027.json

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

[![Syntology run record](https://syntology.ai/api/ran/1603.05027.svg)](https://syntology.ai/paper/1603.05027)

Connect an agent — have() is free.