{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006921158,0.00006015043,0.0001732024,0.0001947842,0.0002090702,0.0001867979,0.001826205,0.00003510043,0.00006097751],"category_scores_gemma":[0.05734255,0.00003314149,0.00005484985,0.0006202444,0.00006714692,0.0004562301,0.0002511313,0.0001798484,0.000004565802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001155064,"about_ca_system_score_gemma":0.00003878525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001125162,"about_ca_topic_score_gemma":0.00007421448,"domain_scores_codex":[0.9985699,0.0002941829,0.0005277216,0.0001197041,0.0003956265,0.00009283567],"domain_scores_gemma":[0.9113795,0.0864073,0.0008464751,0.0009750472,0.0003552974,0.00003633186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004636789,0.00006244665,0.5720531,0.000004628049,0.00003934648,2.631419e-8,0.0003178997,0.001160839,0.0001473954,0.0006211394,0.0179993,0.4075475],"study_design_scores_gemma":[0.0008424198,0.0002832951,0.5399162,0.00003590767,0.00003995701,0.0000282946,0.004291138,0.1177205,0.00001314963,0.03454764,0.3021664,0.0001150779],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8097317,0.01361102,0.1314773,0.03756192,0.001054417,0.0009003115,0.00003668136,0.00003607843,0.005590568],"genre_scores_gemma":[0.9734615,0.00177982,0.02438091,0.0001435767,0.00003443679,0.000002382772,0.000001976534,0.000005288138,0.0001900882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4074324,"threshold_uncertainty_score":0.9505979,"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."}}