{"id":"W4244056413","doi":"10.1002/9781118445112.stat06402","title":"Test Construction","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Function (biology); Construct (python library); Computer science; Item bank; Computerized adaptive testing; Key (lock); Item response theory; Process (computing); Data mining; Information retrieval; Artificial intelligence; Statistics; Mathematics; Psychometrics; 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":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002324232,0.000622817,0.001244108,0.001515363,0.0001570083,0.0003265036,0.001528774,0.0005443287,0.01397609],"category_scores_gemma":[0.1153138,0.0004716339,0.00009833866,0.001702297,0.0005349481,0.0000707972,0.0003042359,0.0008041757,0.001542234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007413329,"about_ca_system_score_gemma":0.0002636973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002793377,"about_ca_topic_score_gemma":0.0004969206,"domain_scores_codex":[0.9937505,0.0005971043,0.001465487,0.001351817,0.002144568,0.0006904881],"domain_scores_gemma":[0.9651667,0.03003197,0.002071575,0.001717518,0.0006535727,0.0003585898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007372275,0.00007793758,0.002306574,0.00002914989,0.00002560512,0.00001497865,0.00001109631,0.000004199381,0.000009200448,0.008635619,0.6639771,0.3249011],"study_design_scores_gemma":[0.0004260228,0.0002325637,0.001580489,0.0002470362,0.00004866474,0.00002928449,0.0001683661,0.001107222,0.000002362992,0.07577861,0.9198022,0.0005771102],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002676018,0.0008346245,0.622557,0.0001273357,0.002482702,0.0003584094,0.02639909,0.0004254234,0.3467886],"genre_scores_gemma":[0.0001491624,0.001332687,0.6708017,0.000188191,0.0007184439,0.00001224433,0.001196614,0.0002948787,0.3253061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.324324,"threshold_uncertainty_score":0.9997736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.353458140929248,"score_gpt":0.4677002338967999,"score_spread":0.1142420929675519,"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."}}