Position: Benchmarking is Broken - Don't Let AI be Its Own Judge
2025PublicationOpen access
10.52202/085713-2433Full text1 citations
2025PublicationOpen access
10.52202/085713-2433Full text1 citations
16 authors across 12 institutions in 3 countries.
Assignment is probabilistic — a work belongs to several fields in proportions.
Several sources describing one work is the point — it means the record rests on more than one authority.
2025 · 1 citations
https://openalex.org/W4414111563