{"id":"W4403899111","doi":"10.5539/jel.v14n2p74","title":"Scoring Difficulty in Summary Writing Assessment: Toward the Reconstruction of Analytic Rubric","year":2024,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Rubric; Psychology; Mathematics education; Evaluation methods","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1133846,0.001593447,0.001299703,0.008802667,0.001801402,0.006253823,0.002991778,0.0008257087,0.0009229388],"category_scores_gemma":[0.3496146,0.001027905,0.001141171,0.00438181,0.003441991,0.005978318,0.005503104,0.002583764,0.000628541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002293074,"about_ca_system_score_gemma":0.004705263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002496039,"about_ca_topic_score_gemma":0.003591433,"domain_scores_codex":[0.8711856,0.08198194,0.01634669,0.004578954,0.02468594,0.001220756],"domain_scores_gemma":[0.7079954,0.1411939,0.03707338,0.01947606,0.09196807,0.002293139],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006132458,0.000489711,0.09018537,0.001845073,0.0002390824,0.0003607158,0.06056068,0.003723181,0.02329304,0.01984905,0.00567398,0.7931668],"study_design_scores_gemma":[0.0004486868,0.005196593,0.3103324,0.006981479,0.001008004,0.005490926,0.1393648,0.254074,0.07083536,0.09168607,0.1128551,0.001726541],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2111519,0.001578599,0.7719566,0.001650525,0.0003346275,0.002248049,0.0001744359,0.001102848,0.009802395],"genre_scores_gemma":[0.4212481,0.0008936102,0.5738384,0.0002218444,0.0001406328,0.001790171,0.0002857543,0.0003204626,0.001261077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8866154,"threshold_uncertainty_score":0.5996423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0306549708698953,"score_gpt":0.3844111303993394,"score_spread":0.3537561595294441,"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."}}