SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.01718 · 2018

Deep Learning for Classical Japanese Literature

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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, 1 violated it and 6 have no contract verdict; 0 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/1812.01718.json · badge: /api/ran/1812.01718.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
rois-codh/kmnist canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
huckiyang/MOT-Kuzushiji-Fashion-Video community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
christianversloot/keras-cnn community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
array_to_color Ran
ran on a synthesized input
christianversloot/keras-cnn/3d_cnn.py
code served (permissive licence) · get_code("9fcefc8108e7dcc7")
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 3, dtype family float, shape (3, 2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
import matplotlib.pyplot as plt

# Create a small numpy array to pass as the 'array' parameter
array = np.array([[0.1, 0.2, 0.3],
                   [0.4, 0.5, 0.6],
                   [0.7, 0.8, 0.9]])

# Define the arguments dictionary
ARGS = {
    'array': array,
    'cmap': 'Oranges'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (3, 2, 4) — shape (3, 2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
func Ran
ran on a synthesized input
huckiyang/MOT-Kuzushiji-Fashion-Video/modules/submodules.py
code served (permissive licence) · get_code("79c9ed66ab16aba7")
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 ReLU. 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)

# The function takes a single parameter: func_name
# It returns None or an nn.Module based on the func_name string
# Valid values are: None, 'tanh', 'relu', 'sigmoid', 'softmax'

ARGS = {
    'func_name': 'relu'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
heatmap Ran
ran on a synthesized input
huckiyang/MOT-Kuzushiji-Fashion-Video/modules/utils.py
code served (permissive licence) · get_code("8686f5f8869b96ee")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (4, 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 torch
import matplotlib.pyplot as plt

torch.manual_seed(0)

# The function expects:
# - img: a 2D tensor that will be converted to numpy and passed through a colormap
# The colormap expects values in [0, 1] range typically
# img is indexed as img[:, :, :3] so it needs at least 3 dimensions after colormap
# Actually, looking at the code: cm(img.cpu().numpy()) treats img as 2D grayscale
# Then cimg becomes HxWx4 (RGBA), and we slice [:, :, :3] to get RGB

img = torch.rand(4, 3)  # Small 2D tensor with values in [0, 1]

ARGS = {
    'img': img,
    'cmap': 'hot'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (4, 3, 3) — shape (4, 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
imresize Ran
ran on a synthesized input
huckiyang/MOT-Kuzushiji-Fashion-Video/modules/utils.py
code served (permissive licence) · get_code("4f41ef64fff1779d")
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 3, dtype family int, shape (8, 6, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a small test image as a numpy array (height=4, width=3, channels=3)
img_numpy = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

ARGS = {
    "img": img_numpy,
    "height": 8,
    "width": 6
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (8, 6, 3) — shape (8, 6, 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
load Ran
ran, honoured the contract we drafted
rois-codh/kmnist/benchmarks/kuzushiji_mnist_cnn.py
pointer only (licence: CC-BY-SA-4.0) · get_code("a7ddd539340a0491")
How it ran

The body of this sample is withheld: CC-BY-SA-4.0, as GitHub detects it on this paper's repository, rois-codh/kmnist, is not in the permissive set Syntology serves inline. 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.

load_json Ran
ran on a synthesized input
huckiyang/MOT-Kuzushiji-Fashion-Video/modules/utils.py
code served (permissive licence) · get_code("0b4f56034d066154")
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 json
import tempfile
import os

# Create a temporary JSON file with sample data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_data.json")

sample_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(temp_file, 'w') as f:
    json.dump(sample_data, f)

ARGS = {
    "filename": temp_file
}
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
rgb_data_transform Ran
ran on a synthesized input
christianversloot/keras-cnn/3d_cnn.py
code served (permissive licence) · get_code("423d9f1135f3cf44")
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 5, dtype family float, shape (2, 16, 16, 16, 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

def rgb_data_transform(data):
    data_t = []
    for i in range(data.shape[0]):
        # Simulating array_to_color which returns shape (16, 16, 16, 4) then [:, :-1] -> (16, 16, 16, 3)
        # array_to_color expects a 1D array of shape (16, 16, 16) = 4096 elements
        pass
    return np.asarray(data_t, dtype=np.float32)

# Create a small dataset
# The function iterates over data.shape[0] and for each i calls array_to_color(data[i])
# array_to_color expects a 1D array that will be mapped to colors
# It then reshapes to (16, 16, 16, 3)
# So data[i] should be something that array_to_color can handle
# array_to_color uses plt.cm.ScalarMappable which expects a flat array or array-like
# Let's create data with shape (batch_size, 4096) where 4096 = 16*16*16

batch_size = 2
num_elements = 16 * 16 * 16  # 4096

# Create random data in range [0, 1] for color mapping
data = np.random.rand(batch_size, num_elements).astype(np.float32)

ARGS = {
    'data': data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 5, dtype family float, shape (2, 16, 16, 16, 3) — shape (2, 16, 16, 16, 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
sigmoid Ran
ran, violated the contract we drafted
christianversloot/keras-cnn/model_ftswish_comp_relu_swish.py
pointer only (licence: CC0-1.0); the stored copy get_code serves, from mtanveer1/KRPRVFL, is pointer only (licence: NONE) · get_code("1a3c174f69eae69e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (CC0-1.0), but get_code serves the stored copy, first harvested from mtanveer1/KRPRVFL, 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.

ftswish Not yet run
unverified (harvested, no recorded run)
christianversloot/keras-cnn/model_ftswish.py
code served (permissive licence) · get_code("16f75e261df71b2b")
How it ran

no invocation recorded.

norm_grad Not yet run
unverified (harvested, no recorded run)
huckiyang/MOT-Kuzushiji-Fashion-Video/modules/submodules.py
code served (permissive licence) · get_code("a198f270bbdcdaa2")
How it ran

no invocation recorded.

swish Not yet run
unverified (harvested, no recorded run)
christianversloot/keras-cnn/model_ftswish_comp_relu_swish.py
code served (permissive licence) · get_code("ac98794695de15e5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 10 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
sigmoid 1 other paper
1 later
2608.13628 (2026-08)
Robust Dual-Model Collaborative Random Vector Functional Link Network

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

Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance. In this work, we introduce Kuzushiji-MNIST, a dataset which focuses on Kuzushiji (cursive Japanese), as well as two larger, more challenging datasets, Kuzushiji-49 and Kuzushiji-Kanji. Through these datasets, we wish to engage the machine learning community into the world of classical Japanese literature. Dataset available at https://github.com/rois-codh/kmnist

For agents

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

get_harvested_code_for_paper("1812.01718")
get_code_for_paper("1812.01718")
have("1812.01718")

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

curl https://syntology.ai/api/ran/1812.01718.json

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

[![Syntology run record](https://syntology.ai/api/ran/1812.01718.svg)](https://syntology.ai/paper/1812.01718)

Connect an agent — have() is free.