TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Annotated Paper – Easily read, annotate, and understand research papers

3 点作者 sabakhoj大约 1 个月前
Heya HN! I&#x27;ve been working on this side project for a few weeks and I decided to do a soft launch to share. It&#x27;s open-source, so link to code below.<p>This is Annotated Paper. I mainly built this for myself as I was reading up on AI safety research to read research papers more effectively. I&#x27;m sharing it because it could be useful to anyone reading a decent amount of papers.<p>It allows you to: 1. Read your paper in a split-pane view, with some actions available in the right panel. 2. Ask questions with an AI copilot &amp; get grounded responses that link back to the source PDF. 3. Add highlights &amp; annotations to the PDF (hence, annotated paper). Highlighting any text also gives you a neat inline menu with quick actions. 4. Take notes in markdown format, quickly extracting snippets from the PDF 5. Tune the AI response - pick from concise, normal, and detailed response lengths. 6. Search over your knowledge base of uploaded PDFs.<p>Citations generation was somewhat complex. I setup a syntax I&#x27;ve called the citation protocol. It pushes the LLM to ground its response in footnote syntax, providing inline citations to any claims it&#x27;s making about the paper. The response is streamed with grounded references, which I then use for reverse lookup in the source PDF.<p>Reverse-lookup from the citation to location in the PDF has been tricky, because the LLM-extracted text isn&#x27;t always a match to the client-extracted text layers. So I do some fuzzy matching.<p>I created a split-pane view with the PDF, because I wanted to actually read the paper, not just upload it and treat it like a black box. For humans to gracefully _learn_ with AI, we should still read the source docs, rather than give up control.<p>It&#x27;s not been super stress-tested, but should work decently on PDFs &lt; 50 pages. No paywall at the moment, so give it a spin :). I&#x27;d love some feedback.<p>Note: I haven&#x27;t yet developed a mobile view, because I don&#x27;t think people meaningfully are reading papers on their phones. I may get to it eventually if there&#x27;s demand.<p>Model: `gemini-2.5-pro`, because it&#x27;s quite decent with reasoning &amp; technical work. I do think adding model switching would be useful for diversity, depending on subject matter.<p>-----<p>GitHub repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;sabaimran&#x2F;annotated-paper">https:&#x2F;&#x2F;github.com&#x2F;sabaimran&#x2F;annotated-paper</a><p>Overall vision: <a href="https:&#x2F;&#x2F;annotatedpaper.khoj.dev&#x2F;blog&#x2F;manifesto">https:&#x2F;&#x2F;annotatedpaper.khoj.dev&#x2F;blog&#x2F;manifesto</a><p>Citations protocol prompt: <a href="https:&#x2F;&#x2F;github.com&#x2F;sabaimran&#x2F;annotated-paper&#x2F;blob&#x2F;master&#x2F;server&#x2F;app&#x2F;llm&#x2F;prompts.py#L20">https:&#x2F;&#x2F;github.com&#x2F;sabaimran&#x2F;annotated-paper&#x2F;blob&#x2F;master&#x2F;ser...</a><p>Request: Try out the app and let me know any feedback you might have. It&#x27;s a pretty rough prototype at the moment!<p>If you&#x27;ve built anything similar for document processing, I&#x27;d love some advice on the reverse reference look-up or processing PDFs with images.<p>If you are reading a decent amount of papers, I&#x27;d love some insight into what your reading workflows look like currently, and which tools are already useful.<p>Thank you!

2 条评论

toomuchtodo大约 1 个月前
Hey! Very cool, thank you for sharing. I use Zotero today, is that where you&#x27;re headed from a product roadmap perspective?
评论 #43772865 未加载
eamag大约 1 个月前
How does it compare to other tools like <a href="https:&#x2F;&#x2F;www.semanticscholar.org&#x2F;product&#x2F;semantic-reader" rel="nofollow">https:&#x2F;&#x2F;www.semanticscholar.org&#x2F;product&#x2F;semantic-reader</a> or many others? What was missing there?
评论 #43773067 未加载
评论 #43772971 未加载