{"id":"W4382600309","doi":"10.5539/jel.v12n5p67","title":"The Development of Scientific Modeling Skill Assessment for Grade 6 Students","year":2023,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mahasarakham University","keywords":"Generalizability theory; Context (archaeology); Test (biology); Psychology; Sample (material); Mathematics education; Medical education","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00414784,0.00003525131,0.00006799126,0.000126204,0.001436823,0.0001701044,0.0001466074,0.00001992392,0.00001346716],"category_scores_gemma":[0.000260877,0.00002623337,0.00003304573,0.0002134159,0.00005378504,0.0001195317,0.00001573255,0.0001199175,0.000001247716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006448079,"about_ca_system_score_gemma":0.002121651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001476712,"about_ca_topic_score_gemma":0.00008250978,"domain_scores_codex":[0.9990366,0.0001232517,0.0002790733,0.00005850008,0.0003927677,0.0001098777],"domain_scores_gemma":[0.9988772,0.0003875981,0.0002544398,0.00003087625,0.0003932696,0.00005662335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002837719,0.0006807068,0.2881577,0.00007432694,0.0001468883,1.632475e-7,0.3941148,0.003145148,0.0008733335,0.03352604,0.005097603,0.274155],"study_design_scores_gemma":[0.0003102642,0.00006595439,0.1233187,0.0001104107,0.00002919965,0.000001187784,0.468079,0.002145971,0.00003233425,0.005241612,0.400555,0.0001103156],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941654,0.000132059,0.001058456,0.002393775,0.001417177,0.00008791646,1.394243e-7,0.000004548871,0.0007405243],"genre_scores_gemma":[0.9888752,0.00008054171,0.004305596,0.00001500984,0.0002517726,0.000008409805,0.000003855099,0.000003423201,0.006456168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3954574,"threshold_uncertainty_score":0.9998631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1073839425888496,"score_gpt":0.5101870063385316,"score_spread":0.4028030637496821,"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."}}