{"id":"W4200196734","doi":"10.5539/elt.v15n1p16","title":"Establishing an Operational Model of Rating Scale Construction for English Writing Assessment","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Education of the People's Republic of China","keywords":"Writing assessment; Judgement; Rating scale; Psychology; Scale (ratio); Grading (engineering); Mathematics education; Weighting; Construct (python library); Likert scale; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.001275759,0.0001260748,0.0001776119,0.00009806095,0.0003903983,0.0002987832,0.0004277015,0.00009402994,0.00001111605],"category_scores_gemma":[0.00114146,0.00014015,0.00006382976,0.0001532824,0.00003904012,0.001724418,0.0001684011,0.0004305172,1.653333e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008636907,"about_ca_system_score_gemma":0.0003955014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001281407,"about_ca_topic_score_gemma":0.00001421639,"domain_scores_codex":[0.9985807,0.0001566798,0.0003557304,0.0004104095,0.0002695742,0.0002269326],"domain_scores_gemma":[0.9986477,0.0003663314,0.0001559694,0.0003899725,0.0003808353,0.00005919088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002420358,0.0002912297,0.004434403,0.00007587839,0.00003337266,0.000004516181,0.08496854,0.01342685,0.03542578,0.8239231,0.0001193237,0.03729462],"study_design_scores_gemma":[0.0007793721,0.00007297807,0.0002774205,0.0001508925,0.00002482113,0.00001705142,0.146706,0.7975351,0.04714907,0.006705665,0.0001762379,0.0004054841],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4694388,0.00005448575,0.5269899,0.0001633162,0.0004482811,0.0000971972,0.00001294901,0.000183449,0.002611627],"genre_scores_gemma":[0.5295423,0.000001075485,0.4699648,0.00007133121,0.0002886819,0.0000276137,0.00005928971,0.000007007782,0.00003792968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8172174,"threshold_uncertainty_score":0.5715152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01405824346634783,"score_gpt":0.3124344167760603,"score_spread":0.2983761733097125,"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."}}