{"id":"W2911244996","doi":"10.1016/j.jcomdis.2019.01.002","title":"Data-driven item selection for the Shirts and Shoes Test","year":2019,"lang":"en","type":"article","venue":"Journal of Communication Disorders","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Ambrose University; University of Connecticut","keywords":"Item response theory; Psychology; Test (biology); Item analysis; Reliability (semiconductor); Item bank; Differential item functioning; Classical test theory; Population; Selection (genetic algorithm); Psychometrics; Statistics; Applied psychology; Social psychology; Developmental psychology; Artificial intelligence; Computer science; Mathematics; Demography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03912618,0.0008313377,0.001497483,0.002546885,0.0005300397,0.001557643,0.002113987,0.001122998,0.00525945],"category_scores_gemma":[0.1636744,0.0005988891,0.001550658,0.002327612,0.0004417975,0.0008267759,0.001914815,0.001838385,0.001754919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006499995,"about_ca_system_score_gemma":0.002075965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002020871,"about_ca_topic_score_gemma":0.003293292,"domain_scores_codex":[0.969584,0.0215905,0.002434893,0.001683273,0.004272413,0.0004349001],"domain_scores_gemma":[0.8663973,0.1127341,0.002198657,0.006278714,0.01183262,0.0005586513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005301118,0.001648119,0.2622424,0.0006610609,0.001444611,0.0004095088,0.001427563,0.016405,0.008031583,0.007338728,0.01688376,0.6782065],"study_design_scores_gemma":[0.002652971,0.003261369,0.3669569,0.0004425169,0.001016761,0.001155008,0.001565633,0.5534702,0.02365322,0.02901107,0.01652073,0.0002936125],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4164205,0.0003188674,0.5640728,0.0007922332,0.0001894375,0.005378254,0.007423282,0.001857579,0.003546979],"genre_scores_gemma":[0.5364407,0.00009807523,0.4457785,0.0004097726,0.00005230663,0.007161306,0.008160766,0.0002940143,0.001604459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03912618,"threshold_uncertainty_score":0.2069215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4113550839938006,"score_gpt":0.4831262255380291,"score_spread":0.07177114154422853,"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."}}