{"id":"W4248200253","doi":"","title":"RESEARCH AND TEACHING Collaborative Testing: Evidence of Learning in a Controlled In-Class Study of Undergraduate Students","year":2014,"lang":"en","type":"article","venue":"","topic":"Reflective Practices in Education","field":"Social Sciences","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics education; Class (philosophy); Teaching method; Psychology; Science education; Pedagogy; Computer science","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":[0.01856122,0.0009327356,0.001183144,0.0008360665,0.00132218,0.001990644,0.002329298,0.001769445,0.002789152],"category_scores_gemma":[0.04878908,0.0007528669,0.0009755521,0.0006039698,0.003468102,0.001512833,0.001058306,0.001760765,0.0004258509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003291,"about_ca_system_score_gemma":0.002102407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002397376,"about_ca_topic_score_gemma":0.002703253,"domain_scores_codex":[0.975151,0.01734061,0.001032994,0.002570819,0.002921293,0.0009833246],"domain_scores_gemma":[0.9330874,0.03873901,0.01064507,0.00938346,0.002582404,0.005562666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"nonrandomized_trial","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.16633,0.5723506,0.06823761,0.002024608,0.001988385,0.0007331087,0.02239466,0.0005542855,0.01866099,0.001162251,0.001443611,0.1441198],"study_design_scores_gemma":[0.04880679,0.757442,0.1711787,0.0003405314,0.0009607209,0.0004188853,0.003823239,0.00157645,0.009745843,0.001094223,0.004436939,0.0001757374],"study_design_candidate":"nonrandomized_trial","study_design_consensus":"nonrandomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975984,0.0002688887,0.0004372019,0.00007376636,0.00005694484,0.0006907989,0.00003302958,0.00001192902,0.0008291259],"genre_scores_gemma":[0.9956588,0.000297276,0.001455108,0.0002186147,0.00009875184,0.001206946,0.0001103149,0.00001311419,0.0009411305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01856122,"threshold_uncertainty_score":0.09816235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1504244910715768,"score_gpt":0.5438010138242099,"score_spread":0.393376522752633,"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."}}