{"id":"W4409353748","doi":"10.1111/jedm.12433","title":"Theory‐Driven IRT Modeling of Vocabulary Development: Matthew Effects and the Case for Unipolar IRT","year":2025,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Reading and Literacy Development","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Item response theory; Vocabulary; Psychology; Econometrics; Psychometrics; Natural language processing; Mathematics education; Computer science; Linguistics; Mathematics; Developmental psychology; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.003500008,0.0001218142,0.0002594304,0.0002008538,0.0001632009,0.0000269859,0.0001682639,0.00004573296,0.00004963975],"category_scores_gemma":[0.0004779042,0.00008043722,0.00009153772,0.0001137051,0.00005935326,0.00005898158,0.00002377437,0.0001402715,0.000002884276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001579466,"about_ca_system_score_gemma":0.0006457237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001529572,"about_ca_topic_score_gemma":0.000003821161,"domain_scores_codex":[0.9985147,0.0002703744,0.0006421682,0.0001291696,0.0002937381,0.0001498134],"domain_scores_gemma":[0.9979714,0.0008409782,0.0003097685,0.0001473552,0.0006697879,0.00006073579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.005578117,0.002580104,0.01890376,0.00195445,0.007791587,0.00008976,0.07649899,0.002528487,0.001763991,0.7607893,0.02438014,0.0971413],"study_design_scores_gemma":[0.05957355,0.001468451,0.1935163,0.01501396,0.004176045,0.01045167,0.02833325,0.008305037,0.008683035,0.4617766,0.2061529,0.002549233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9132726,0.01911639,0.04654428,0.01088608,0.003889988,0.001150539,0.000005647509,0.00000745303,0.005127086],"genre_scores_gemma":[0.9923044,0.00002045473,0.006412505,0.0003625013,0.0001256542,0.00006468423,0.000001943899,0.000009759895,0.0006981378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2990127,"threshold_uncertainty_score":0.3280135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03195175338742903,"score_gpt":0.3215903201546934,"score_spread":0.2896385667672643,"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."}}