pith. sign in

How should ai safety benchmarks benchmark safety?

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CY 1

years

2026 2

representative citing papers

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents

cs.CY · 2026-04-11 · accept · novelty 8.0

This paper delivers the first systematic taxonomy and cross-benchmark consistency analysis of 40 agent safety benchmarks, finding broad but shallow risk coverage, no ranking concordance across evaluations, and that benchmark choice systematically alters reported safety.

citing papers explorer

Showing 2 of 2 citing papers.

  • Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents cs.CY · 2026-04-11 · accept · none · ref 60

    This paper delivers the first systematic taxonomy and cross-benchmark consistency analysis of 40 agent safety benchmarks, finding broad but shallow risk coverage, no ranking concordance across evaluations, and that benchmark choice systematically alters reported safety.

  • Making AI Evaluation Deployment Relevant Through Context Specification cs.AI · 2026-03-06 · unverdicted · none · ref 18

    Context specification is a process that turns diffuse stakeholder perspectives into explicit definitions of properties, behaviors, and outcomes to guide context-aware AI evaluations.