Skip to content
JevDirectory.org
CommunityTools & Integrations5 starsVerified 2026-09-22

Paper Trellis Citation Verifier

A browser tool that checks whether a cited paper supports the sentence citing it: code matches references and verifies quotes, Claude proposes an evidence passage, and Jev scores supports, contradicts, or says nothing.

Open github.comMarissaFamularo/citation-verifier
Category
Tools & Integrations
Published by
Community
Author
MarissaFamularo
Added
2026-09-22
Tagscommunityjavascriptbrowserevaluationprivacy

Highlights

  • References are matched in PubMed first, then Crossref and OpenAlex, so preprints, conference papers, and non-biomedical journals are covered.
  • Claude proposes a verdict and verbatim passage, and the app discards any quote not found in the fetched text rather than showing it as support.
  • Jev reads the citing sentence next to the proven passage and returns a probability for supports, contradicts, or says nothing as the reliability mark.
  • Paywalled papers are checked against the abstract only, and a silent abstract is reported as needs full text, never as unsupported.
  • The manuscript is read in the browser with no database or application server, and Jev calls pass through a stateless relay that stores and logs nothing.

Quickstart

bash
npm install
cp .env.example .env.local   # set VITE_CONTACT_EMAIL for Unpaywall lookups
npm run dev

Watch out

MIT-licensed; needs an Anthropic or TypeSafe API key under BYOK, scanned PDFs are not read, citing sentences and paper text go to the selected providers, and thresholds have not been validated on a labelled biomedical set.

More like this

Jev Browser Use
354GitHub stars
A Codex skill (with a plugin option) that hands clicks, toggles, navigation, and scrolling to Jev over accessibility text while Codex types, interprets visuals, and verifies the outcome.
Tools & Integrations#community#javascript#skills
Communityjev-browser-use
voice-browser
143GitHub stars
Control a headed Chromium window by voice: one Jev request per partial transcript decides intent, target, and completeness in roughly 300 ms, while code applies thresholds and builds the action.
Tools & Integrations#community#javascript#browser
Communityjev-voice-browser
Jev × WebMCP Chrome Extension
95GitHub stars
A Chrome side panel that turns the current page's WebMCP tool schemas into typed Jev questions, predicting the tool call, its arguments, confidence, and latency as you type.
Tools & Integrations#community#javascript#chrome-extension
Communityjev-webmcp-extension
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Inferring Jev's internals from 1,000 calls

iwashi / Yoshimasa Iwase
iwashi / Yoshimasa Iwase
@iwashi86
·

Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more

Reply
Read 2 replies

The open System One roundup

小墨同学
小墨同学
@xiaomovps
·

Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格

Image
Reply
Read 6 replies

The launch post

Trading bot, one decision per block

Classifying 1,500 real emails

vogel
vogel
Anomaly
@ryanvogel
·

this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 69 replies

Fast browser use with Stagehand

Kyle Jeong
Kyle Jeong
Browserbase
@kylejeong
·

we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 30 replies