{"id":"W3004171085","doi":"10.1039/c9rp00274j","title":"Evaluating students’ learning gains, strategies, and errors using OrgChem101's module: organic mechanisms—mastering the arrows","year":2020,"lang":"en","type":"article","venue":"Chemistry Education Research and Practice","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Metacognition; Formalism (music); Mathematics education; Computer science; Test (biology); Psychology; Cognition","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002785883,0.0009793768,0.0007924334,0.0008251478,0.0003296926,0.0008055458,0.0008106282,0.0007710411,0.003114375],"category_scores_gemma":[0.007373394,0.0002896434,0.000581475,0.0004123533,0.0003842855,0.0007831003,0.0009764169,0.0008648612,0.001118433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004751995,"about_ca_system_score_gemma":0.0007395885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005441114,"about_ca_topic_score_gemma":0.001004729,"domain_scores_codex":[0.9986713,0.000302276,0.0001558829,0.0002094839,0.0003935593,0.0002675373],"domain_scores_gemma":[0.993206,0.002839513,0.001020946,0.0003328389,0.001183923,0.001416749],"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":[0.005624316,0.1033472,0.2709647,0.001368516,0.0002746149,0.0006141146,0.01350228,0.006952522,0.0755367,0.000456153,0.006079326,0.5152795],"study_design_scores_gemma":[0.0008439928,0.07131327,0.8004482,0.0001830546,0.0003648602,0.0004837103,0.004543607,0.01178016,0.1021107,0.0006245684,0.007087635,0.0002162705],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984877,0.00001602796,0.0005983137,0.00003282078,0.00000668125,0.0001663609,0.00006300843,0.00005338813,0.0005756803],"genre_scores_gemma":[0.9885603,0.0001285986,0.006406248,0.00008171928,0.00001796321,0.0005874624,0.0004083253,0.00002441348,0.003785123],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003114375,"threshold_uncertainty_score":0.01473331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3986438866750975,"score_gpt":0.5921792560203151,"score_spread":0.1935353693452176,"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."}}