Stanford researcher: negative sets in genomic evals fail to test causal variant discrimination
anshulkundaje · x · 2026-10-24
Anshul Kundaje critiques genomic foundation model benchmarks: in TraitGym for common variants, the negative sets don't address the core discriminative challenge—distinguishing causal variants from other tagging variants in linkage disequilibrium (LD) for the same trait.
More from Research
- Robotics model leaderboards are premature, argues practitioner: task-specific evals first — paigeinsf · 2026-10-24
- UTokyo/RIKEN lab brings CAROT cross-lingual alignment method to EMNLP, +11.2 accuracy points — Bollegala · 2026-10-24
- GPT-6 Astra solves 49 of 50 research-level physics problems, catches experts' own errors — MoonL88537 · 2026-10-24
- Rice & NVIDIA's Sensorimotor Alignment predicts robot policy success without training (r=0.717) — CSProfKGD · 2026-10-24
- RLVR Trains VLMs on Instruction Hierarchy with Just 7K Verifiable Examples — TuhinChakr · 2026-10-24
- NVIDIA ships BioNeMo Inference Runtime v0.2 with RFD4-Proteina support — AllThingsApx · 2026-10-24