Cite Smart AI

Landing Page
AI chatbot
add new projects
projects created
no projects created
auth (login)
project detail

Inspiration

The idea for Cite Smart AI stems from the challenges researchers face when managing academic citations and exploring interconnected papers. Finding relevant research, understanding how papers cite each other, and organizing citation data can be time-consuming and overwhelming. This tool aims to simplify that process, providing a personal AI companion to make research smarter, faster, and more insightful. By blending advanced AI with intuitive user interfaces, Cite Smart AI empowers users to focus on discovery and learning.

What it does

Cite Smart AI helps users manage and explore academic citations with ease. Its key functionalities include:

Searching citations: Find relevant papers based on titles, keywords, or research topics.
Connecting papers: Visualize how papers cite or are cited by others using a dynamic graph structure.
Answering questions: Use AI to provide context-aware answers about academic papers and citations.
Storing citation graphs: Save, and expand your citation networks for ongoing research projects.

In essence, it’s a personal AI companion focused on simplifying research and citation management.

How we built it

Frontend

Next.js: Framework for building a fast, dynamic, and user-friendly interface.
ShadCN + TailwindCSS: For modern, consistent, and responsive UI components.
Supabase: Handles user authentication, ensuring secure access to the app.

Backend

Modus + Hypermode: Enables server-side functionality with AssemblyScript and integrates a scalable backend for handling data.
DeepSeek AI: Powers intelligent citation search and retrieval from Semantic Scholar.
Text Transformer Model: Provides natural language understanding for answering user queries.

These tools work together to offer a seamless experience for exploring and managing academic citations.

Challenges we ran into

Unfamiliarity with AssemblyScript: Learning and implementing a new programming language was a steep learning curve.
GraphQL integration: Adapting to GraphQL queries within Modus for efficient data handling was tricky.
Neo4j database: Understanding how to structure citation relationships and optimize graph queries was challenging but essential for building a robust backend.
Combining tools: Integrating multiple technologies (Modus, Semantic Scholar, Neo4j) while maintaining performance and usability was a complex task.

Accomplishments that we’re proud of

Successfully integrating multiple technologies to create a functional and efficient citation management system.
Developing a knowledge graph that visualizes connections between papers, making academic research more intuitive.
Overcoming the challenges of working with new tools and frameworks like AssemblyScript and Neo4j.
Delivering a polished frontend experience that feels user-friendly and modern.

What we learned

AssemblyScript basics: Understanding its syntax, nuances, and capabilities.
Neo4j and GraphQL: Structuring data relationships and querying efficiently in a graph database.
Integration skills: Coordinating multiple advanced tools into a seamless system.
Teamwork and adaptability: Tackling unfamiliar technologies while maintaining focus on project goals.
A deep appreciation for the complexities of building scalable, AI-powered applications.

What’s next for Cite Smart AI

Add more features: Include advanced search filters, citation formatting tools, and collaborative features for research teams.
Expand AI capabilities: Train models to provide deeper insights, such as summarizing papers or highlighting trends in a research field.
Enhance the graph structure: Improve visualization, scalability, and usability of the citation graph for large datasets.
Integrate more data sources: Include additional academic databases to increase the range and depth of citation data.
User feedback: Continuously refine the app based on user needs and suggestions.