Papers › Deep Learning for Classical Japanese Literature

Deep Learning for Classical Japanese Literature

3 Dec 2018arXiv:1812.01718archive 2025-07-28

Tarin Clanuwat, Mikel Bober-Irizar, Asanobu Kitamoto, Alex Lamb, Kazuaki Yamamoto, David Ha

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

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1812.01718")

Code

Syntology Ran 2 of 11 code samples harvested from 3 repositories linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 10 samples from 2 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

rois-codh/kmnist officialmentioned in papermentioned on GitHub report
christianversloot/extra_keras_datasets mentioned on GitHubtfNOASSERTION report
christianversloot/keras-cnn mentioned on GitHubCC0-1.0 report
elisiojsj/Kuzushiji-49 mentioned on GitHubpytorch report
hardmaru/kanji2kanji mentioned on GitHubtf report
huckiyang/MOT-Kuzushiji-Fashion-Video mentioned on GitHubpytorchMIT report
mv-lab/kuzushiji-recognition mentioned on GitHubpytorch report
xyntechx/Manga-Layout-Analysis mentioned on GitHubApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 2 ran; 1 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
9unverified

Licence: 1 of the 11 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

load rois-codh/kmnist/benchmarks/kuzushiji_mnist_cnn.py official repository ran · honoured contract CC-BY-SA-4.0 (copyleft) · pointer only · a7ddd539340a0491 · report
sigmoid christianversloot/keras-cnn/model_ftswish_comp_relu_swish.py community (archive-listed) ran · violated contract fingerprinted CC0-1.0 (permissive) · 1a3c174f69eae69e · report
array_to_color christianversloot/keras-cnn/3d_cnn.py community (archive-listed) unverified CC0-1.0 (permissive) · 9fcefc8108e7dcc7 · report
ftswish christianversloot/keras-cnn/model_ftswish.py community (archive-listed) unverified CC0-1.0 (permissive) · 16f75e261df71b2b · report
func huckiyang/MOT-Kuzushiji-Fashion-Video/modules/submodules.py community (archive-listed) unverified MIT (permissive) · 79c9ed66ab16aba7 · report
heatmap huckiyang/MOT-Kuzushiji-Fashion-Video/modules/utils.py community (archive-listed) unverified MIT (permissive) · 8686f5f8869b96ee · report
imresize huckiyang/MOT-Kuzushiji-Fashion-Video/modules/utils.py community (archive-listed) unverified MIT (permissive) · 4f41ef64fff1779d · report
load_json huckiyang/MOT-Kuzushiji-Fashion-Video/modules/utils.py community (archive-listed) unverified MIT (permissive) · 0b4f56034d066154 · report
norm_grad huckiyang/MOT-Kuzushiji-Fashion-Video/modules/submodules.py community (archive-listed) unverified MIT (permissive) · a198f270bbdcdaa2 · report
rgb_data_transform christianversloot/keras-cnn/3d_cnn.py community (archive-listed) unverified CC0-1.0 (permissive) · 423d9f1135f3cf44 · report
swish christianversloot/keras-cnn/model_ftswish_comp_relu_swish.py community (archive-listed) unverified CC0-1.0 (permissive) · ac98794695de15e5 · report

Tasks

BIG-bench Machine LearningDeep LearningImage Classification

Datasets

Introduced by this paper, per the archive.

Kuzushiji-49Kuzushiji-KanjiKuzushiji-MNIST

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Kuzushiji-MNIST ResNet18 + VGG Ensemble Error 1.10 #26 of 26 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections