{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002998471,0.0009507698,0.00117221,0.001791199,0.0008938331,0.001040804,0.0008400377,0.001498385,0.01520102],"category_scores_gemma":[0.01711483,0.0003201548,0.0009345872,0.0008621012,0.000465968,0.001822607,0.001440271,0.0009500431,0.006368571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005692355,"about_ca_system_score_gemma":0.0006354504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004987557,"about_ca_topic_score_gemma":0.001272149,"domain_scores_codex":[0.9977666,0.0006284392,0.0005389143,0.0002555079,0.0006590895,0.0001513944],"domain_scores_gemma":[0.9883896,0.005458936,0.001172346,0.0009858048,0.003188002,0.0008052668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002451686,0.00538248,0.1484156,0.001214409,0.0001940144,0.0003031773,0.004193191,0.002201249,0.02512125,0.00211514,0.04106927,0.7673386],"study_design_scores_gemma":[0.0008449482,0.01305205,0.7362331,0.001074834,0.0004459089,0.001529891,0.009184706,0.01543745,0.07365505,0.0124722,0.1355938,0.0004761551],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9083339,0.0008643802,0.04211048,0.001457022,0.0005389347,0.007416051,0.006027014,0.002482957,0.03076941],"genre_scores_gemma":[0.7671273,0.001192991,0.1639807,0.001518164,0.0002167502,0.02360452,0.00841133,0.000643202,0.03330509],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01520102,"threshold_uncertainty_score":0.05085242,"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."}}