{"id":"W4293408802","doi":"10.1177/01466216221124089","title":"Item Selection With Collaborative Filtering in On-The-Fly Multistage Adaptive Testing","year":2022,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computerized adaptive testing; Item bank; Selection (genetic algorithm); Computer science; Item response theory; Collaborative filtering; On the fly; Feature selection; Test (biology); Machine learning; Data mining; Artificial intelligence; Statistics; Recommender system; Mathematics; Psychometrics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01328367,0.0002454872,0.0003665104,0.0003628064,0.0006780036,0.0001349583,0.0008201291,0.0000561263,0.0005516226],"category_scores_gemma":[0.01649879,0.0001398079,0.00004664822,0.006474267,0.0001060941,0.00005057476,0.0001896474,0.0007225862,0.00003679296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003351191,"about_ca_system_score_gemma":0.00004279819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001962153,"about_ca_topic_score_gemma":0.00002044687,"domain_scores_codex":[0.9939356,0.001206018,0.0006642339,0.0009872083,0.002734805,0.0004721298],"domain_scores_gemma":[0.9827898,0.01583891,0.0004424195,0.000490337,0.0003467075,0.00009179107],"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":[0.005642999,0.002815352,0.08965644,0.00001013796,0.0001635294,0.000180964,0.002791474,0.04678565,0.07099558,0.03223433,0.014104,0.7346196],"study_design_scores_gemma":[0.005518064,0.008989912,0.8880799,0.0001008901,0.00003009521,0.00009479337,0.02435626,0.007005433,0.003474442,0.0420245,0.01883215,0.001493537],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8535135,0.0000939414,0.03386654,0.0009608243,0.0004750665,0.001736657,0.00001818305,0.0001797893,0.1091555],"genre_scores_gemma":[0.9688712,0.000001061622,0.02941031,0.0008741032,0.00005560796,0.0007100754,6.415321e-7,0.00001401481,0.00006302418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7984235,"threshold_uncertainty_score":0.9917856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6812333426754545,"score_gpt":0.4329920465484254,"score_spread":0.2482412961270291,"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."}}