{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1094113,0.001942465,0.001308778,0.008344573,0.00101895,0.003571143,0.003529246,0.001749004,0.003893171],"category_scores_gemma":[0.3443469,0.001299085,0.002401317,0.003363542,0.001393869,0.004186977,0.004990628,0.002937227,0.00231593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002296816,"about_ca_system_score_gemma":0.006537763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005684396,"about_ca_topic_score_gemma":0.001244286,"domain_scores_codex":[0.8895369,0.06922431,0.01790753,0.004198425,0.01751552,0.001617346],"domain_scores_gemma":[0.5008172,0.3526669,0.02530219,0.03054958,0.08658116,0.004082866],"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":[0.0007037489,0.002038598,0.03433466,0.003047124,0.0002433342,0.0003495525,0.008704742,0.004742773,0.01550834,0.005088377,0.01864167,0.9065971],"study_design_scores_gemma":[0.003049002,0.02011159,0.2311733,0.01049013,0.001323844,0.003988408,0.02065327,0.14912,0.1173496,0.06299327,0.3773349,0.002412556],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06842802,0.0002725575,0.8841192,0.0008966538,0.0006689174,0.02946527,0.001274708,0.009100022,0.005774515],"genre_scores_gemma":[0.0396037,0.0001437253,0.9358926,0.0002292584,0.00005311369,0.02210447,0.0006604186,0.0003429172,0.0009697929],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1094113,"threshold_uncertainty_score":0.5786293,"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."}}