{"id":"W2924341464","doi":"10.2505/4/jcst19_048_04_64","title":"Two-Stage (Collaborative) Testing in Science Teaching: Does It Improve Grades on Short-Answer Questions and Retention of Material?","year":2019,"lang":"en","type":"article","venue":"Journal of College Science Teaching","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Guelph","funders":"","keywords":"Mathematics education; Science education; Teaching method; Psychology; Pedagogy","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":[0.007984334,0.0006337485,0.0008250762,0.0005839449,0.0003765474,0.0008373883,0.001601515,0.001544356,0.001467886],"category_scores_gemma":[0.02713449,0.0003355647,0.0008607017,0.0005098556,0.0004250612,0.001406927,0.001004122,0.0009626582,0.0005223553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005839376,"about_ca_system_score_gemma":0.0008802762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001946891,"about_ca_topic_score_gemma":0.002865462,"domain_scores_codex":[0.9941618,0.002645566,0.0004035613,0.0007200643,0.001827829,0.0002411597],"domain_scores_gemma":[0.9819195,0.009884963,0.003073958,0.001627341,0.0014618,0.002032498],"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":[0.01979306,0.04820016,0.1197894,0.000986679,0.0005500974,0.0002388825,0.003224228,0.001631781,0.03926697,0.0003169919,0.001700546,0.7643012],"study_design_scores_gemma":[0.003770997,0.221417,0.6973665,0.0004271379,0.0005977849,0.001060332,0.0008212499,0.0123442,0.05709598,0.001026144,0.003779052,0.0002936737],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9963847,0.0003925968,0.002208686,0.0001392445,0.00004483619,0.000205183,0.00003011848,0.00006396216,0.0005305695],"genre_scores_gemma":[0.9894852,0.0003082547,0.008299597,0.000158878,0.00004083284,0.0003507141,0.0001419991,0.00001599211,0.001198551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007984334,"threshold_uncertainty_score":0.04222572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04291436430538549,"score_gpt":0.3999190650102065,"score_spread":0.357004700704821,"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."}}