tax-doc-classifier
Project / 项目 · In the catalogue / 在目录中查看
What Jev decides here · Jev 在这里做什么决定
Classification (分类), Document triage (文档分拣)
choice: text signal only: the cited file contains their request or answer shape 仅文本信号：引用的文件里出现了它们的请求或回答格式
a person read the call site 有人读过调用点 · · Cited file / 引用的文件: src/backend.ts
Summary · 摘要
Classifies tax document pages: one request per page asks Jev two choices, page kind (7 options) and IRS form (230 plus none), and a follow-up choice for five forms' schedules; criteria come from IRS PDFs and code gates at 0.95. Its author measured no strict error on 314 filled pages.written by a model
税务文档分页分类器：每页一次请求，问 Jev 两个 choice：页面类型（7 个选项）和 IRS 表单（230 个另加“不在列表中”），五种表单的附表再用一个后续 choice 细分；选项描述由 IRS 官方 PDF 生成，代码以 0.95 为门槛。作者在 314 页已填写表单上测得严格错误为零。模型撰写机翻
Launches · 发布记录
Not launched yet. 还没有发布过。 Launch it / 发布它 ↗ · How a product launches / 怎样发布一个产品
Makers · Maker
Made this? Confirm or correct its entry / 这是你做的？确认或更正条目 ↗
The same form takes the product's one line and a demo link, in its maker's own words. 同一个表单也可以补上产品的一句话和演示链接，用 Maker 自己的话。
Badge for its README · README 徽章
[](https://kydlikebtc.github.io/awesome-jev/products/tax-doc-classifier.html)One line for the product's README, linked to this page. The picture says that it is listed; while it is on the launch board, that it is launching; after a week in the top three, its place. It is rebuilt with the site, so the line never needs changing. 放进产品 README 的一行，链接到本页。图片显示已收录；在发布榜上时显示正在发布；进过某周前三后显示名次。它随网站一起重建，这一行不用再改。
Also under this pattern · 同一模式的其他产品
json-render
Vercel Labs' generative UI framework. In its Jev experiment the model does not write JSON token by token — it only picks components, props and layout.
Inbox Zero: seven email decisions
Seven distinct email decisions, each with its own separately chosen threshold, falling back to the normal LLM on any error.
pg-jev
A real PostgreSQL extension exposing the primitives as SQL functions, so a semantic decision can appear in a WHERE clause over any row type.
jev-mcp
A ready-made judgement toolbox for agents: fact verification, content screening, semantic ranking, classification and extraction as separate tools.
docjev
Classifies and splits PDF, DOCX and PPTX files: LiteParse extracts page text locally, then Jev picks a document's category with a choice over your rules, or for a packet answers per page a category choice and a noul on whether a new document starts there. Its report covers 40 real PDFs.