{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01480785,0.0006319998,0.0008315068,0.001348655,0.0005177821,0.002506624,0.002547101,0.001070283,0.003550506],"category_scores_gemma":[0.05797334,0.0005493956,0.001197602,0.001083702,0.00218356,0.002018278,0.001823943,0.002184513,0.0005307751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001461548,"about_ca_system_score_gemma":0.001136443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007877668,"about_ca_topic_score_gemma":0.006594165,"domain_scores_codex":[0.9928917,0.005051938,0.0002325321,0.000899583,0.0006376204,0.0002865901],"domain_scores_gemma":[0.957216,0.03248308,0.003346471,0.003935016,0.002414485,0.0006050644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002075667,0.00020263,0.05799901,0.0002232017,0.0002996269,0.0005124057,0.002379901,0.2657606,0.001376124,0.5894811,0.002940197,0.07861752],"study_design_scores_gemma":[0.00002085447,0.00011613,0.009257175,0.00008265002,0.00005688025,0.000197924,0.0002574286,0.8021434,0.0003109643,0.1856209,0.001885816,0.00004978212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1435361,0.000327575,0.8437998,0.001664844,0.00007495825,0.0001355654,0.0002363808,0.0003228962,0.009901877],"genre_scores_gemma":[0.903881,0.000164986,0.09267253,0.000269832,0.00004673441,0.0002263385,0.0001450383,0.00008855668,0.002504835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01480785,"threshold_uncertainty_score":0.07831234,"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."}}