ML Reads

ML Reads is a minimal Next.js website that recommends five machine learning papers from arXiv each day.

Features

• Fetches live arXiv papers from broad ML categories: cs.LG, cs.AI, stat.ML, cs.CV, cs.CL, and cs.NE.
• Shows a deterministic daily set of five recommendations based on the UTC date.
• Includes title, authors, abstract summary, category, published date, abstract link, and PDF link.
• Handles empty and arXiv error states with a friendly fallback.

Getting Started

Install dependencies:

npm install

Run the development server:

npm run dev

Open http://localhost:3000 to view the site.

Daily Selection

The app fetches the latest arXiv papers from the configured ML categories and scores each paper with a deterministic hash of the UTC date and paper ID. That means the same day shows the same recommendations while still allowing the candidate set to refresh from arXiv.

Current Limitations

• No accounts or saved reading history.
• No personalization.
• No database persistence.
• arXiv availability affects whether live papers can be shown.