{"id":"W2899263706","doi":"10.1128/jmbe.v19i3.1627","title":"Development of a Tool to Assess Interrelated Experimental Design in Introductory Biology","year":2018,"lang":"en","type":"article","venue":"Journal of Microbiology and Biology Education","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Checklist; Inter-rater reliability; Computer science; Mathematics education; Reliability (semiconductor); Adaptability; Medical education; Psychology; Rating scale; Medicine; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003916924,0.00008037465,0.0002341567,0.0003580579,0.0001175595,0.000004205182,0.0001759666,0.000213564,0.00006664659],"category_scores_gemma":[0.000693129,0.00006532689,0.00002019534,0.0002187712,0.0005704112,0.00006008441,0.00004338034,0.0002011275,0.000004030319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000160236,"about_ca_system_score_gemma":0.0009089304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000344445,"about_ca_topic_score_gemma":0.00005806856,"domain_scores_codex":[0.9977806,0.001390119,0.0005006786,0.0001397504,0.00001599995,0.0001728812],"domain_scores_gemma":[0.9990902,0.0001901819,0.0003430404,0.00005776395,0.0002869176,0.00003187539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001282086,0.0001321679,0.01442881,0.000001831074,0.00002813467,1.204699e-7,0.02465093,1.303099e-7,0.9422846,0.003697031,0.0003132816,0.01433474],"study_design_scores_gemma":[0.0008547532,0.00171638,0.03083266,0.0001267587,0.00001901123,0.00009068721,0.02088593,0.000001319834,0.8538166,0.002749221,0.08858218,0.0003245169],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886476,0.0002696379,0.008546866,0.0005461939,0.001670008,0.0001347565,8.664928e-7,0.000003914996,0.0001801269],"genre_scores_gemma":[0.8863499,0.00000886729,0.1130983,0.0002218167,0.0002781386,0.000003947563,0.0000038362,0.000003043578,0.00003215436],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1045514,"threshold_uncertainty_score":0.2663953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1145250300818905,"score_gpt":0.4525388255679716,"score_spread":0.3380137954860811,"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."}}