{"id":"W4292583031","doi":"10.5539/elt.v15n9p82","title":"Examining the Dependability and Practicality of Analytic Rubric of Summary Writing Using Multivariate Generalizability Theory: Focusing on Japanese University Students with Lower-Intermediate Proficiency in English","year":2022,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rubric; Generalizability theory; Psychology; Mathematics education; Context (archaeology); Constructive; Language proficiency; Dependability; 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":[0.005958868,0.0001326263,0.0002325972,0.0001649458,0.0003287428,0.00003687391,0.0007374557,0.00004049611,0.000007145671],"category_scores_gemma":[0.001479193,0.0001078174,0.00003502053,0.000440374,0.0001763108,0.0003789593,0.0007985423,0.0007274997,2.995458e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002330927,"about_ca_system_score_gemma":0.0001178567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004397459,"about_ca_topic_score_gemma":0.00003387927,"domain_scores_codex":[0.9969156,0.001712959,0.0003003036,0.0004343467,0.0004162521,0.0002205044],"domain_scores_gemma":[0.9978644,0.001206459,0.0002988972,0.0005244892,0.00006941039,0.00003629987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001415232,0.001287567,0.686575,0.00009720041,0.00006684628,0.00006121968,0.2868918,0.002753518,0.001507557,0.01659777,0.000001010607,0.004018952],"study_design_scores_gemma":[0.002136469,0.0007545499,0.3093899,0.0003677401,0.0001119798,0.00001978678,0.6489278,0.03499109,0.001380674,0.001322942,0.00001282907,0.0005842029],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954737,0.00005104541,0.003627008,0.00004842466,0.0001437544,0.0002692767,0.000008089249,0.00006236932,0.0003163402],"genre_scores_gemma":[0.9964302,8.850584e-7,0.003494195,0.00002018691,0.00002890594,0.000004379822,0.000002593398,0.000006823284,0.00001189551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3771851,"threshold_uncertainty_score":0.4396664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01854952372686935,"score_gpt":0.2954321271611949,"score_spread":0.2768826034343255,"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."}}