Krypton
AI Research Assistant with Multi-Signal Paper Ranking
Krypton is an AI-powered research assistant that searches arXiv and OpenAlex, ranks papers by relevance, recency, and citations, and helps users understand literature faster with Gemini-generated summaries, structured insights, research-gap analysis, and personalized topic recommendations in a FastAPI + React app.
What Jayant Potdar Built & Owned
Led technical architecture and development: designed the dual-source ingestion engine for arXiv and OpenAlex, wrote the multi-factor scoring formula balancing TF-IDF lexical relevance, citation velocity, and publication recency, implemented an in-memory TTL caching tier to respect external API rate limits, and integrated the Google Gemini API with strict prompt contracts for verbatim-supported synthesis.
Key Technical Decisions:
- Deterministic composite ranking algorithm balancing term relevance, citation authority, and exponential decay on recency.
- Parallel asynchronous querying of arXiv and OpenAlex APIs reducing search latency by 62%.
- Source-first AI paper summaries displaying exact citation excerpts side-by-side with generated synthesis.
- In-memory TTL cache preventing redundant external API calls and rate-limiting blocks.
Core System Features & Capabilities:
- ✓Multi-source paper search across arXiv and OpenAlex in one query flow.
- ✓Intelligent ranking using relevance (TF-IDF), recency, and citation-based scoring.
- ✓AI-generated paper understanding with plain-English summaries and key contributions.
- ✓Structured insight extraction for each paper: problem, method, result, and limitation.
- ✓Research gap analysis that finds open questions and thematic opportunity clusters.
- ✓Personalized research experience with user profiles, topic recommendations, and goal-aware suggestions.
Academic literature discovery suffers from two extremes: traditional keyword searches that drown users in dated papers, and generative AI search engines that hallucinate findings without verifiable source anchors.
Our team built a transparent pipeline. The user's query searches arXiv and OpenAlex concurrently. We calculate a composite score: 50% TF-IDF relevance, 30% normalized citation volume, and 20% publication recency. Gemini synthesizes key research gaps only from the ranked papers, pairing every observation with a clickable DOI reference.
Detailed interface walkthrough, diagnostic panels, and feature screenshots for Krypton.
Krypton won 1st Place at the university Project Expo. The platform proved that transparent, signal-weighted ranking combined with grounded AI synthesis dramatically accelerates early-stage literature reviews.
Ranking Academic Papers Without Black-Box Search: Blending TF-IDF, Citations, and Recency
Designing a transparent literature ranking algorithm that balances lexical relevance, citation authority, and publication velocity.
Read the engineering note (6 min read)
AstroPixel
AstroPixel is a FastAPI + React platform for exploring NASA gigapixel imagery with buttery-smooth deep zoom, annotations, and secure user/admin workflows. It ingests GeoTIFF/PSB files, generates tile pyramids with GDAL, and serves them through an optimized viewer.
NeuralNet
NeuralNet is a full-stack visual deep learning studio where you design neural networks with drag-and-drop nodes, compile to Keras, train with real TensorFlow metrics, and deploy secure prediction APIs.
