{"id":"W2094237702","doi":"10.1119/1.4820241","title":"Integrated testlets and the immediate feedback assessment technique","year":2013,"lang":"en","type":"article","venue":"American Journal of Physics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"","keywords":"Context (archaeology); Multiple choice; Set (abstract data type); Test (biology); Reliability (semiconductor); Standard deviation; Computer science; Mathematics education; Statistics; Physics; Psychology; Mathematics; Programming language; Significant difference","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":[0.0008092449,0.0001028169,0.0002799651,0.00003386408,0.0002113487,0.0001505919,0.0003158412,0.00002162359,0.00007936086],"category_scores_gemma":[0.00006388561,0.00006124085,0.00009318788,0.0003911037,0.001336761,0.0003029527,0.00004561514,0.0002932086,0.0000138038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006954724,"about_ca_system_score_gemma":0.0002021417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001207429,"about_ca_topic_score_gemma":0.00001534244,"domain_scores_codex":[0.9987262,0.0003001026,0.0002560219,0.00008356306,0.0004260115,0.0002080272],"domain_scores_gemma":[0.9986572,0.0003650885,0.0004791864,0.00009646557,0.0002950625,0.0001069583],"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":[0.0001581648,0.0004539207,0.09990366,0.0000118376,0.0005164511,0.0000152721,0.0313728,0.00001356734,0.0103702,0.09438385,0.01550198,0.7472983],"study_design_scores_gemma":[0.009601241,0.00271418,0.4882534,0.0004086049,0.0006177009,0.00005907371,0.2876128,0.0005174114,0.001879638,0.1460695,0.0606811,0.001585375],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9450119,0.0001604601,0.009137763,0.01680175,0.0005085437,0.0009350246,0.000002887964,0.00004165825,0.02739999],"genre_scores_gemma":[0.9936556,0.0003198148,0.005031847,0.0003609815,0.0004325228,0.00001900647,5.264812e-7,0.000009536945,0.0001701796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7457129,"threshold_uncertainty_score":0.4925351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01254507973410524,"score_gpt":0.314171238454659,"score_spread":0.3016261587205538,"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."}}