Pinned Loading

1. bio-overrefusal-v0.1 bio-overrefusal-v0.1 Public

   Domain-expert-authored benchmark for LLM over-refusal on legitimate biology research queries.

   Python

2. narrow-model-safety-eval narrow-model-safety-eval Public

   Empirical dual-use risk assessment of protein language models (ESM-2) and structure-based design tools (ProteinMPNN)

   Python

3. constitutional-bioguard constitutional-bioguard Public

   Biological dual-use content classifier using Constitutional Classifiers methodology — biosafety constitution, synthetic data pipeline, DeBERTa-v3-base classifier

   Python

4. GeneLab_benchmark GeneLab_benchmark Public

   GeneLab Spaceflight Transcriptomics Benchmark — NASA OSDR mouse bulk RNA-seq LOMO benchmark for AI/ML and Foundation Models

   Python

5. SpaceOmicsBench SpaceOmicsBench Public

   A multi-omics AI benchmark for spaceflight biomedical data — 21 ML tasks across 9 modalities + 100-question LLM evaluation (Inspiration4, NASA Twins, JAXA)

   Python