{"id":"W4389089956","doi":"10.3389/feduc.2023.1279921","title":"Models of classroom assessment for course-based research experiences","year":2023,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fogarty International Center; Strong; Howard Hughes Medical Institute","keywords":"Grading (engineering); Mathematics education; Authentic assessment; Metacognition; Pedagogy; Psychology; Computer science; Engineering; Cognition; Curriculum","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":[0.01324527,0.00100522,0.0005924541,0.003953503,0.001430595,0.008012225,0.003703528,0.002080969,0.009634989],"category_scores_gemma":[0.07827648,0.0008249811,0.001016829,0.001798633,0.002590064,0.006658941,0.003736797,0.001695008,0.00286962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005626847,"about_ca_system_score_gemma":0.003955499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005162728,"about_ca_topic_score_gemma":0.007195348,"domain_scores_codex":[0.9815679,0.01099638,0.00101199,0.001792722,0.003923116,0.0007078454],"domain_scores_gemma":[0.9386829,0.03705119,0.003724664,0.006576464,0.01187975,0.002085079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004296179,0.001987016,0.04603936,0.0009915143,0.0001535373,0.0006592047,0.0539289,0.06120084,0.003555785,0.3857268,0.00860739,0.4367201],"study_design_scores_gemma":[0.000276785,0.001285548,0.02746985,0.001249635,0.0001462985,0.0008529885,0.02017905,0.5905415,0.005239102,0.2753781,0.07706833,0.0003127932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08246923,0.0002986988,0.8247125,0.00163805,0.0001190476,0.002404673,0.0003062592,0.001722012,0.0863296],"genre_scores_gemma":[0.5976407,0.0002427064,0.3854369,0.0001229647,0.00002107288,0.003479644,0.0003994431,0.0002071491,0.01244943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01324527,"threshold_uncertainty_score":0.07004851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.227151196797807,"score_gpt":0.5462137505449556,"score_spread":0.3190625537471485,"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."}}