A claim-centered validity framework, grounded in psychometrics, tells evaluators when benchmark scores support narrow versus broad claims about AI capabilities.
Beyond these core types, external validity refers to the extent to which a study’s findings can be generalized beyond its specific conditions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Measurement to Meaning: A Validity-Centered Framework for AI Evaluation
A claim-centered validity framework, grounded in psychometrics, tells evaluators when benchmark scores support narrow versus broad claims about AI capabilities.