#benchmark validation

try —

2 papers match

cs.SE2026

PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks

Manyi Wang, Junjielong Xu, Pinjia He

The paper introduces PAIChecker, a multi‑agent system that automatically detects misalignments between pull requests and their linked issues in SWE‑bench‑style benchmarks, improvin…

#software engineering#large language models#benchmark validation#pr‑issue alignment

cs.AI2026

Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans

Jasmin Thelen, Oliver Wilhelm

The paper evaluates the ARC-AGI benchmark, originally designed for AI, as a measure of human fluid intelligence, finding good psychometric properties and a strong correlation with…

#fluid intelligence#rule induction#psychometrics#benchmark validation