English

FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution

Machine Learning 2026-05-11 v1

Abstract

Large Language Models (LLMs) are increasingly used to brainstorm and evaluate research ideas, yet assessing such judgments is fundamentally difficult because the true impact of a new idea may take years to emerge. We address this challenge by using the impact forecasting of human-authored manuscripts as a verifiable proxy task. In a prospective forecasting study, we find that frontier LLMs fail to reliably distinguish high-impact papers from ordinary publications, suggesting that static text-based judging is insufficient for scientific evaluation. To address this limitation, we propose FAME\textbf{FAME} (F\underline{\text{F}}orecasting A\underline{\text{A}}cademic Impact via Continuous-Time M\underline{\text{M}}anifold E\underline{\text{E}}volution), a spatiotemporal framework for modeling the dynamic trajectories of scientific topics. FAME projects papers into a dynamic latent space informed by textual features and a verified knowledge-flow graph, learning geometric constraints that align impactful manuscripts with the forward momentum of their fields. Experiments on 3,200 arXiv papers across three fast-evolving subfields show that FAME consistently and substantially outperforms state-of-the-art LLM evaluators in prospective multidimensional impact forecasting. Furthermore, integrating FAME's dynamic geometric signals into LLMs significantly improves their forecasting performance. These results support manuscript impact forecasting as a useful, measurable proxy benchmark and position FAME as a strong, trajectory-aware foundation for automated scientific evaluation.

Keywords

Cite

@article{arxiv.2605.07208,
  title  = {FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution},
  author = {Jianrong Ding and Jianyuan Zhong and Zhengyan Shi and Qiang Xu},
  journal= {arXiv preprint arXiv:2605.07208},
  year   = {2026}
}
R2 v1 2026-07-01T12:56:50.818Z