| Metric | Value |
|---|---|
| Queries | 15 |
| Any relevant in top-3 (headline) | 4 / 15 (26.7%) |
| Any relevant in top-5 | 6 / 15 (40.0%) |
| Mean P@3 | 0.1111 |
| Mean P@5 | 0.0933 |
This is the second-worst class baseline after acronym (4/22, 18%). For prose, this number represents an upper-bound on the methodology problem and a lower-bound on the ranker problem; the truth is somewhere in between.