Japan Open Data Lab
Author ProfileClaim This Author Profile
Prove ownership by publishing #HashtagPLUS and this profile link on your author page or an article under your byline. A moderator or admin will review the request before it merges into your real HashtagPLUS username.
π dev.toSource
TL;DR β We released ja-doc-classify-v1, a router that sits at the entrance of a Japanese...
π dev.toSource
TL;DR β We released ja-error-detect-v1, a small token-classification model that finds the spans in a...
π dev.toSource
TL;DR β We released ja-address-ner-v1, a two-stage component that extracts Japanese addresses from...
π dev.toSource
TL;DR β We released ja-punct-restore-v1, a small model that restores γγοΌοΌ into punctuation-free...
π dev.toSource
TL;DR β We released ja-phish-guard-v1, a Japanese text classifier that scores phishing, fraud, and...
π dev.toSource
TL;DR β We released ja-injection-guard-v1, a small text classifier that flags likely...
π dev.toSource
Our best custom Gemma 4 agent scored 15/114 vs the zero-think baseline's 16/114. Aggregate results and six findings from 1,800+ trials β no task data, no code.