• Computer Science > Artificial Intelligence [Submitted on 24 Feb 2026] Title:PreScience: A Benchmark for Forecasting Scientific Contributions View PDFAbstract:Can AI systems trained on the scientific record up to a fixed point in time forecast the scientific advances that follow? • Such a capability could help researchers identify collaborators and impactful research directions, and anticipate which problems and methods will become central next. • We introduce PreScience – a scientific forecasting benchmark that decomposes the research process into four interdependent generative tasks: collaborator prediction, prior work selection, contribution generation, and impact prediction. • PreScience is a carefully curated dataset of 98K recent AI-related research papers, featuring disambiguated author identities, temporally aligned scholarly metadata, and a structured graph of companion author publication histories and citations spanning 502K total papers. • We develop baselines and evaluations for each task, including LACERScore, a novel LLM-based measure of contribution similarity that outperforms previous metrics and approximates inter-annotator agreement. • We find substantial headroom remains in each task – e.g.

Article Summaries:

  • PreScience: A Benchmark for Forecasting Scientific Contributions

Researchers have released PreScience, a new benchmark that evaluates AI systems’ ability to predict future scientific progress. The dataset contains 98,000 recent AI papers with disambiguated author identities, temporally aligned metadata, and a citation graph of over 500,000 publications. PreScience breaks the research process into four tasks-collaborator prediction, prior work selection, contribution generation, and impact prediction-and introduces LACERScore, an LLM‑based metric that outperforms prior similarity measures. Experiments show that even state‑of‑the‑art language models only achieve moderate alignment with real contributions, and synthetic research generated by these models is less diverse and novel than actual human‑authored work.

Sources: