Instructional Risk Evaluation Dataset for LLM-Generated Teaching Outputs

This dataset contains the expert evaluations and learner detectability assessments used to analyze instructional risk in LLM-generated outputs. It includes annotations of instructional failure modes, severity scores, propagation risk ratings, and learner judgments of correctness and reuse intention. These data form the empirical basis for computing the Instructional Risk Index (IRI) and for examining cross-domain risk patterns and learner susceptibility to pedagogically misleading outputs.