MIRAI: Prediction and Generation of High-Impact Academic Research
For researchers and funding agencies, MIRAI offers a practical tool to forecast paper impact and generate impactful research directions, though the impact gain is modest.
MIRAI predicts 5-year PageRank and citation counts from title, abstract, and date, achieving Spearman's ρ of 0.4686 and 0.6192 respectively on 2021 arXiv papers, and generates high-impact research ideas judged 4:3 more impactful than a baseline by an LLM.
The rapid pace of scientific publishing has made the identification and synthesis of high-impact work an increasingly urgent challenge. We introduce MIRAI (Multi-year Inference of Research trends and Academic Impact), a deep learning framework that predicts paper impact using only it's title, abstract, and publication date. We train MIRAI on the arXiv academic graph to predict 5-year PageRank and citation counts, achieving Spearman's $ρ$ of 0.4686 on PageRank prediction and 0.6192 on citation prediction for papers published in 2021. We propose a research ideation pipeline built on top of MIRAI that produces research ideas oriented towards high impact. These ideas were judged as more impactful than a baseline without MIRAI by an unbiased LLM judge at a 4:3 ratio. We make the 5-year citation prediction model publicly available at https://predict-paper-impact.vercel.app.