SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1509.01626 · 2015

Character-level Convolutional Networks for Text Classification *

Xiang Zhang, Yann Lecun, Junbo Zhao

arXiv · PDF · Open in the Atlas

Code that ran

17 of 20 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 13 have no contract verdict; 4 failures of our instrument; 3 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/1509.01626.json · badge: /api/ran/1509.01626.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
ahmedbesbes/character-based-cnn community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
paper-cat/Sentence-Classifications community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
Fadeich/HotFlip-CNN-pytorch extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
sjmiller8182/character-convolutions-classification community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
paddorch/CharCNN.paddle community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
ZeweiChu/NatCat community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 1 no recorded run
FunctionStatusWhere it lives
F_score Ran
ran on a synthesized input
paddorch/CharCNN.paddle/model/metric.py
code served (permissive licence) · get_code("da3b18d772dc8f1f")
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 torch
import numpy as np

torch.manual_seed(0)

# Construct precision and recall dictionaries
# The function expects dicts where keys are labels and values are numeric scores
p = {
    'label_A': 0.8,
    'label_B': 0.6,
    'label_C': 0.0,
    'label_D': 0.9
}

r = {
    'label_A': 0.75,
    'label_B': 0.0,
    'label_C': 0.0,
    'label_D': 0.85
}

ARGS = {
    'p': p,
    'r': r
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
char_base_vectorize Ran
ran on a synthesized input
paper-cat/Sentence-Classifications/preprocessing/text_preprocessing.py
code served (permissive licence) · get_code("47cacd8e59547060")
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 torch
import numpy as np

torch.manual_seed(0)

# Construct arguments for char_base_vectorize function
data = ["hello", "world", "test"]
labels = ["pos", "neg", "pos"]
char_dict = {'Pad': 0, 'Unk': 1}
label_dict = {}
train = True

ARGS = {
    'data': data,
    'labels': labels,
    'char_dict': char_dict,
    'label_dict': label_dict,
    'train': train
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
compute_metrics Ran
ran on a synthesized input
ZeweiChu/NatCat/code/utils.py
code served (permissive licence) · get_code("8eaa3c45016e8715")
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 torch
import numpy as np

torch.manual_seed(0)

# Looking at compute_metrics function:
# - task_name: string parameter that's checked against task names
# - preds: passed to simple_accuracy, compared with labels using ==, then .mean() is called
# - labels: passed to simple_accuracy, compared with preds using ==

# preds and labels need to support == comparison and .mean() method
# They should be numpy arrays or torch tensors with numeric values

# Create simple predictions and labels
preds = np.array([0, 1, 1, 0, 2, 1])
labels = np.array([0, 1, 0, 0, 2, 1])

ARGS = {
    'task_name': 'natcat',
    'preds': preds,
    'labels': labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
dpp Ran
ran; our contract draft was wrong, not the code
Fadeich/HotFlip-CNN-pytorch/data_loader_hotflip_greedy.py
pointer only (licence: NONE) · get_code("cb41f722c36c3b59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Fadeich/HotFlip-CNN-pytorch 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.

dpp_candidates Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Fadeich/HotFlip-CNN-pytorch/data_loader_hotflip_beam.py
pointer only (licence: NONE) · get_code("fce2825df6934a6e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Fadeich/HotFlip-CNN-pytorch 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.

dpp_next_element Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Fadeich/HotFlip-CNN-pytorch/data_loader_hotflip_beam.py
pointer only (licence: NONE) · get_code("5aecd25926c298ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Fadeich/HotFlip-CNN-pytorch 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.

get_convolutional_model Ran
ran on a synthesized input
sjmiller8182/character-convolutions-classification/src/model.py
code served (permissive licence) · get_code("eaa4cba327eb7e51")
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 Sequential. 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

ARGS = {
    "vocab_size": 128,
    "input_length": 160,
    "num_classes": 5,
    "embedding_size": 300,
    "model_size": "small"
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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
get_recurrent_model Ran
ran on a synthesized input
sjmiller8182/character-convolutions-classification/src/model.py
code served (permissive licence) · get_code("584c7d5b746edcaf")
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 Sequential. 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

ARGS = {
    'vocab_size': 100,
    'input_length': 160,
    'num_classes': 5,
    'embedding_size': 300
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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
get_sample_weights Ran
ran on a synthesized input
ahmedbesbes/character-based-cnn/src/data_loader.py
code served (permissive licence) · get_code("286cdf64bccfcc8e")
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 1, dtype family float, shape (10,) 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
from collections import Counter

def get_sample_weights(labels):
    counter = Counter(labels)
    counter = dict(counter)
    for k in counter:
        counter[k] = 1 / counter[k]
    sample_weights = np.array([counter[l] for l in labels])
    return sample_weights

# Create sample labels with multiple classes
labels = [0, 1, 2, 0, 1, 0, 2, 2, 1, 0]

ARGS = {
    "labels": labels
}
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 1, dtype family float, shape (10,) — shape (10,) 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_time_dif Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from gaussic/text-classification-cnn-rnn
pointer only · get_code("d9e00c99bc3b43d2")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

label_converter Ran
ran on a synthesized input
paper-cat/Sentence-Classifications/preprocessing/text_preprocessing.py
code served (permissive licence) · get_code("e4018986564263d5")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Construct arguments for label_converter function
labels = ["cat", "dog", "cat", "bird", "dog", "elephant"]
label_dict = {}

ARGS = {
    "labels": labels,
    "label_dict": label_dict,
}
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 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
load_dicts Ran
ran on a synthesized input
paper-cat/Sentence-Classifications/pipeline.py
code served (permissive licence) · get_code("e144f38dd5693140")
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 pickle
import tempfile
import os

# Create a temporary directory to hold the pickle files
temp_dir = tempfile.mkdtemp()

# Create sample dictionaries
text_dict = {
    'hello': 0,
    'world': 1,
    'test': 2
}

label_dict = {
    'positive': 0,
    'negative': 1,
    'neutral': 2
}

# Write the dictionaries to pickle files in the temp directory
with open(os.path.join(temp_dir, 'text_dict'), 'wb') as handle:
    pickle.dump(text_dict, handle)

with open(os.path.join(temp_dir, 'label_dict'), 'wb') as handle:
    pickle.dump(label_dict, handle)

# Define ARGS with the route parameter
ARGS = {
    'route': 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 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
lower Ran
ran on a synthesized input
ahmedbesbes/character-based-cnn/src/utils.py
code served (permissive licence) · get_code("d8919140d7bb81f7")
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 str. 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

torch.manual_seed(0)

ARGS = {
    "text": "Hello World"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
precision_recall Ran
ran on a synthesized input
paddorch/CharCNN.paddle/model/metric.py
code served (permissive licence) · get_code("c01024271e313d54")
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 torch
import numpy as np

torch.manual_seed(0)

# The function precision_recall takes two parameters:
# - output: a sequence of predicted labels
# - target: a sequence of true labels
# The function iterates through them with len() and compares elements
# It treats them as sequences that can be indexed and len() can be called on them

# Create simple list-based label sequences
output = [0, 1, 0, 1, 2, 2]
target = [0, 1, 1, 1, 2, 1]

ARGS = {
    "output": output,
    "target": target
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
remove_hashtags Ran
ran on a synthesized input
ahmedbesbes/character-based-cnn/src/utils.py
code served (permissive licence) · get_code("7031f3d110ff2bb6")
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 str. 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 re

def remove_hashtags(text):
    clean_text = re.sub('#[A-Za-z0-9_]+', '', text)
    return clean_text

# Setup code
ARGS = {
    'text': 'Hello #world this is #awesome and #Python123 code'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
remove_user_mentions Ran
ran on a synthesized input
ahmedbesbes/character-based-cnn/src/utils.py
code served (permissive licence) · get_code("fac1f52a515f3408")
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 str. 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 re

def remove_user_mentions(text):
    clean_text = re.sub('@[A-Za-z0-9_]+', '', text)
    return clean_text

ARGS = {
    'text': 'Hello @john_doe and @jane123! Check out @user_name for more info.'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
similarity Ran
ran on a synthesized input
sjmiller8182/character-convolutions-classification/src/util.py
code served (permissive licence) · get_code("fc127f1284f11efc")
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 float32, 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 two small random vectors for similarity calculation
np.random.seed(0)
vector1 = np.random.randn(4).astype(np.float32)
vector2 = np.random.randn(4).astype(np.float32)

ARGS = {
    "vector1": vector1,
    "vector2": vector2,
}
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 float32, 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
feed_data Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from gaussic/text-classification-cnn-rnn
pointer only · get_code("4515828165469544")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

load_data Not yet run
unverified (harvested, no recorded run)
ahmedbesbes/character-based-cnn/src/data_loader.py
code served (permissive licence) · get_code("74b2ee2bcf9a5318")
How it ran

no invocation recorded.

simple_accuracy Not yet run
unverified (harvested, no recorded run)
ZeweiChu/NatCat/code/utils.py
code served (permissive licence) · get_code("3c241ecfe3749a6d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 5 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 later) and 15 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
simple_accuracy 59 other papers
1 dated earlier, 58 later
1506.05865 (2015-06)
LCSTS: A Large Scale Chinese Short Text Summarization Dataset
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1905.12866 (2019-05)
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
and 56 more not named here
get_time_dif 3 other papers
1 dated earlier, 2 later
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2205.15485 (2022-05)
FinBERT-MRC: financial named entity recognition using BERT under the machine reading comprehension paradigm
F_score 1 other paper
1 later
1703.03130 (2017-03)
A Structured Self-attentive Sentence Embedding
feed_data 1 other paper
1 dated earlier
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
precision_recall 1 other paper
1 later
1703.03130 (2017-03)
A Structured Self-attentive Sentence Embedding

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

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several largescale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks. * An early version of this work entitled "Text Understanding from Scratch" was posted in Feb 2015 as arXiv:1502.01710. The present paper has considerably more experimental results and a rewritten introduction.

For agents

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

get_harvested_code_for_paper("1509.01626")
get_code_for_paper("1509.01626")
have("1509.01626")

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

curl https://syntology.ai/api/ran/1509.01626.json

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

[![Syntology run record](https://syntology.ai/api/ran/1509.01626.svg)](https://syntology.ai/paper/1509.01626)

Connect an agent — have() is free.