{"id":"W4318486478","doi":"10.32920/21977009.v1","title":"Evaluating the Effectiveness of Modified Peer Instruction in Large Introductory Physics Classes","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Peer instruction; Class (philosophy); Mathematics education; Session (web analytics); Multiple choice; Computer science; Psychology; Peer feedback; Mathematics; Artificial intelligence; World Wide Web; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01125168,0.0009906357,0.0009229959,0.001175419,0.0006371348,0.001434903,0.003230806,0.001299301,0.003635515],"category_scores_gemma":[0.05978346,0.0004104422,0.0006253205,0.000596083,0.0006949556,0.001880805,0.001871662,0.001031,0.001063552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001352249,"about_ca_system_score_gemma":0.001702714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002145006,"about_ca_topic_score_gemma":0.002303897,"domain_scores_codex":[0.9872516,0.006766063,0.0008048353,0.001746957,0.003000287,0.000430265],"domain_scores_gemma":[0.9427425,0.03894421,0.004251802,0.003258942,0.005563467,0.005239171],"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":[0.03269672,0.09155511,0.02380945,0.002493555,0.0007368532,0.000381679,0.005811645,0.00732123,0.02534597,0.0004319628,0.003182503,0.8062333],"study_design_scores_gemma":[0.01176628,0.666738,0.2229903,0.0005013293,0.0014605,0.0004181256,0.003297587,0.02079072,0.05831667,0.0008761986,0.012474,0.0003701838],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940873,0.0002024629,0.002057759,0.0001277695,0.00006436115,0.001201549,0.00007376108,0.000261646,0.001923385],"genre_scores_gemma":[0.9748858,0.0003203528,0.01929671,0.0001454567,0.0001408236,0.001596981,0.0003427975,0.00008748975,0.003183467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01125168,"threshold_uncertainty_score":0.05950534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2233371603745883,"score_gpt":0.5008575750919582,"score_spread":0.2775204147173699,"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."}}