Raphael
Product · Landing site
Research intelligence that forecasts research trajectories and designs the teams and resources behind breakthroughs.
Visit ↗
About
Raphael is a research intelligence platform. It uses forward simulation to forecast how research fields and their impact may develop, and inverse design to propose the teams, resources and collaboration structures that could lead to a breakthrough.
It continuously ingests new literature from ArXiv, Semantic Scholar and PubMed, and renders citation and concept networks as interactive 3D knowledge graphs that update as new research arrives.
Graph, map and experiment studios launch runs and show results live, with pluggable deterministic and stochastic engines. The live demo classifies a research paper into one of seven fields and is labeled an approximate classifier.
Butts Studios designed the landing site.
Details
- What we made
- Landing site
- Captured
- October 2026
Gallery
3 images. Tap any one to see it full size.
Articles & notes
Published pages from Raphael: write-ups, docs and data. Each opens on its own site.
- raphaelresearch.com ↗The Science of ScienceTechnical overview of novelty, disruption and citation-dynamics measures
- raphaelresearch.com ↗A single number that asks whether a paper opened a new directionExplainer on the disruption index for scientific papers
- raphaelresearch.com ↗Large teams and small teams do different jobs in scienceHow team size relates to developing versus disrupting ideas
- raphaelresearch.com ↗Modeling how a paper accumulates its citations over timeNotes on citation-growth models for individual papers
- raphaelresearch.com ↗Discovery is speeding up, and direction becomes the scarce resourceCommentary on research direction as discovery accelerates
- raphaelresearch.com ↗Benchmarking a graph surrogate turns on the splitsWhy train and test splits decide graph model benchmark results