Benchmark RadarAI BENCHMARK PROFILE
MASH-Bench
Evaluates ML models on cross-source mass-shooting risk classification using 6,968 incidents with leave-one-dataset-out evaluation.
- Released
- 2026-08-23
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Cross-source generalization is critical for risk classification, and this benchmark isolates the role of feature completeness and label prevalence.
Motivation
Public mass-shooting databases differ substantially in coverage, feature availability, and reporting practices, creating challenges for machine-learning models that must generalize across data sources.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.