ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
arXiv cs.AI · 2 Oct 2026, 03:59 AEST
What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-growing archive of research, a new problem needs.
Key facts
- What makes great scientists great?
- Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-growing archive of research, a new problem needs.
- To study this skill, we draw on researchers who know firsthand which earlier work advanced their completed projects, with papers serving as pointers to the ideas within.
- Using our automated pipeline that makes author annotation scalable, we build ScholarCatalyst by having 184 lead authors of 207 recent computer science papers label which candidates did or could have advanced their.
- We introduce a retrieval task with author-provided judgments: given an initial research question, retrieve these papers from only the literature available when the project began.
Read aloud
What makes great scientists great? Even as A I systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-growing archive of research, a new problem needs. What makes great scientists great? Even as A I systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-growing archive of research, a new problem needs. To study this skill, we draw on researchers who know firsthand which earlier work advanced their completed projects, with papers serving as pointers to the ideas within. Using our automated pipeline that makes author annotation scalable, we build ScholarCatalyst by having one hundred eighty four lead authors of two hundred seven recent computer science papers label which candidates did or could have advanced their. We introduce a retrieval task with author-provided judgments: given an initial research question, retrieve these papers from only the literature available when the project began.
Sources in this cluster
- ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
arXiv cs.AI · 2 Oct 2026, 03:59 AEST