{"id":"W4321004017","doi":"10.1037/met0000540","title":"Let the algorithm speak: How to use neural networks for automatic item generation in psychological scale development.","year":2023,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Economic and Social Research Council; Cambridge Trust","keywords":"Computer science; Scale (ratio); Generator (circuit theory); Process (computing); Code (set theory); Artificial neural network; Generative grammar; Artificial intelligence; Machine learning; Algorithm; Natural language processing; Programming language","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":[0.004531591,0.0002802606,0.0003646312,0.0001953647,0.0003028338,0.0004419352,0.001537306,0.0002098925,0.00003389018],"category_scores_gemma":[0.001731765,0.0001855729,0.0001247639,0.002374148,0.00009809187,0.0004393603,0.0003412019,0.0003707081,0.00008744636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006952805,"about_ca_system_score_gemma":0.00001070759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006442287,"about_ca_topic_score_gemma":0.00002030858,"domain_scores_codex":[0.9959932,0.001219469,0.0005803063,0.001026632,0.0003215861,0.0008588136],"domain_scores_gemma":[0.996644,0.002068378,0.0001233855,0.0008489978,0.0001177763,0.000197495],"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":[0.000009278595,0.0001412423,0.0001863592,0.000008106033,0.000006891726,0.00002309204,0.0004156988,0.002078078,0.0009093597,0.001048101,0.00908913,0.9860846],"study_design_scores_gemma":[0.0001511891,0.0002765025,0.02408723,0.00002719495,0.000004484897,0.0000242919,0.00006333544,0.9632928,0.001079805,0.002524929,0.008160195,0.0003080499],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07411549,0.00008549393,0.9110647,0.01191028,0.001180312,0.001110662,0.000001824816,0.0004350642,0.00009612246],"genre_scores_gemma":[0.05301762,0.00004809217,0.9378195,0.007820833,0.0002375477,0.0007199142,0.00001362309,0.0000191978,0.0003036088],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9857766,"threshold_uncertainty_score":0.7567444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2390750010588527,"score_gpt":0.4633744701333101,"score_spread":0.2242994690744574,"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."}}