Applied Scientific Intelligence

All

2 repositories

refusalbench
Public
Reproducible, evergreen benchmark for LLM refusal on biological research prompts — 19 models, 141 prompts, 13,389 adjudicated trials
benchmark leaderboard alignment
benchmark leaderboard alignment protein-design ai-safety biosecurity llm-evaluation refusal
Python
•
MIT License
•2•4•0•0•Updated Jun 3, 2026Jun 3, 2026
CardioSafe-benchmark
Public
Curated data deposit for the CardioSafe cardiac ion channel benchmark: labels, Tanimoto-controlled splits (tan70 / tan60), and supplementary artifacts for hERG,…
benchmark deep-learning cheminformatics
benchmark deep-learning cheminformatics drug-discovery qsar herg multi-task-learning chembl cipa ion-channels
Python
•
MIT License
•0•1•0•0•Updated May 15, 2026May 15, 2026

ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.