{"id":"W4416211129","doi":"10.1080/08957347.2025.2563889","title":"Establishing Cognitive Item Models for Fair and Theory-Grounded Automatic Item Generation: A Large-Scale Assessment Study with Image-Based Math Items","year":2025,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fonds National de la Recherche Luxembourg","keywords":"Item response theory; Cognition; Item analysis; Differential item functioning; Test (biology); Equating; Item bank; Standardized test","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01886035,0.0002276633,0.0003931785,0.0007776427,0.0003368564,0.000779983,0.0003158481,0.00006958295,0.00001297015],"category_scores_gemma":[0.009214113,0.0001720643,0.00004061659,0.001873682,0.00004696043,0.000436351,0.00005854543,0.0001633395,0.000001403128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003303513,"about_ca_system_score_gemma":0.0007973295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003823319,"about_ca_topic_score_gemma":0.0001851927,"domain_scores_codex":[0.9963232,0.0005662334,0.0007674625,0.0007831723,0.001241731,0.0003181808],"domain_scores_gemma":[0.9875879,0.01056697,0.0003995275,0.0004351857,0.0009371789,0.00007319247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000544945,0.006991009,0.1052943,0.0002907903,0.000233188,0.000001314129,0.01132314,0.002451187,0.003906493,0.06665377,0.002266254,0.8000436],"study_design_scores_gemma":[0.006734626,0.0005339031,0.1844523,0.0004455379,0.0002422017,0.000001999072,0.1769689,0.4873459,0.0007758313,0.1416061,0.0002737096,0.0006190226],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3994448,0.0001269324,0.5934358,0.0002438402,0.0003385436,0.002177852,0.000005382751,0.00004937891,0.004177491],"genre_scores_gemma":[0.9039317,0.000002710794,0.093821,0.0003348278,0.0000735252,0.001724798,0.00001946402,0.00001446291,0.00007752952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7994246,"threshold_uncertainty_score":0.9991317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2627134757698749,"score_gpt":0.4411525673993796,"score_spread":0.1784390916295048,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}