Benchmark RadarAI BENCHMARK PROFILE
RATIO
Evaluates retrieval models on three ideation moves—Address, Broaden, Specify—using relevance judgments derived from full-text scientific papers across computer science literature.
- Released
- 2026-08-27
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Defines relevance by operations that support literature-grounded ideation, enabling training and evaluation of retrieval systems tailored to scientific inspiration.
Motivation
Retrieved scientific literature can serve as inspiration for both human and AI scientists.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.