{"id":"W2906848100","doi":"10.1080/10691316.2018.1518209","title":"Put your instruction to the test: Half a dozen question types for evaluating students","year":2018,"lang":"en","type":"article","venue":"College & Undergraduate Libraries","topic":"Online and Blended Learning","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Session (web analytics); Test (biology); Dozen; Mathematics education; Information literacy; Computer science; Questions and answers; Multiple choice; Matching (statistics); Psychology; Reading (process); Information retrieval; World Wide Web; Linguistics; Mathematics; Arithmetic","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009919795,0.0001352761,0.0001511268,0.00009432077,0.002079785,0.0005002516,0.0004342263,0.00008960222,0.0000404355],"category_scores_gemma":[0.002723258,0.0001052618,0.00006118047,0.0006291108,0.0002596986,0.0006981339,0.0001269933,0.0001296336,0.00007036347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007128648,"about_ca_system_score_gemma":0.0005692019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002255724,"about_ca_topic_score_gemma":0.00213059,"domain_scores_codex":[0.9983155,0.0002838534,0.0002293851,0.0002847585,0.0005244134,0.0003621361],"domain_scores_gemma":[0.998748,0.0006019311,0.0001239116,0.0001909023,0.0002328107,0.000102441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002726262,0.0001883489,0.02425977,0.00004197563,0.0001186426,0.000003240058,0.01697635,0.0002095101,0.0003968464,0.8281578,0.0250393,0.1043355],"study_design_scores_gemma":[0.0009569263,0.0008980045,0.006796099,0.0001018267,0.00009371484,0.000002644443,0.01430183,0.001585483,0.0006874278,0.119124,0.8550936,0.0003584189],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.698134,0.0001901516,0.003792329,0.2805415,0.00249846,0.002261929,0.00005876318,0.0005060164,0.01201684],"genre_scores_gemma":[0.973812,0.00001864891,0.01570918,0.0004278164,0.001775088,0.00008592768,0.00001132487,0.00002423373,0.008135707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8300543,"threshold_uncertainty_score":0.9992194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04722641568258455,"score_gpt":0.381072684290945,"score_spread":0.3338462686083604,"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."}}