{"id":"W2905870394","doi":"10.5539/elt.v12n1p176","title":"Revisiting the Writing Assessment Process at a Saudi English Language Institute: Problems and Solutions","year":2018,"lang":"en","type":"article","venue":"English Language Teaching","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rubric; Grading (engineering); Writing assessment; Psychology; Honesty; Mathematics education; Standards-based assessment; Pedagogy; Context (archaeology); Consistency (knowledge bases); Educational assessment; Computer science; Social psychology","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":[0.002924156,0.0002950602,0.0002784526,0.0001163427,0.004297796,0.0008563109,0.0003323364,0.00007614132,0.0004194193],"category_scores_gemma":[0.001788684,0.0002238354,0.00009018948,0.00006773637,0.0004238478,0.0007428167,0.0002857639,0.001395945,0.00001849684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001256183,"about_ca_system_score_gemma":0.00004242277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007053347,"about_ca_topic_score_gemma":0.0009614829,"domain_scores_codex":[0.9976914,0.0004536397,0.0004080438,0.0004665195,0.0003566348,0.0006237618],"domain_scores_gemma":[0.998796,0.0003241062,0.000241208,0.0003898258,0.0001415374,0.0001072492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00000398295,0.000025348,0.001520323,0.0001454786,0.00004288288,0.00001540374,0.9532205,0.00003743028,0.0002670125,0.02347282,0.0002499717,0.02099885],"study_design_scores_gemma":[0.0006503233,0.00009211578,0.0003486032,0.0009747331,0.0001033778,0.0000224731,0.8597333,0.001607929,0.00006377288,0.0001065999,0.1356738,0.0006229403],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8348286,0.001389036,0.0002200094,0.0002906958,0.0006935111,0.0002776642,0.00001585996,0.0006824007,0.1616022],"genre_scores_gemma":[0.9831145,0.000008695491,0.0004361075,0.0003127592,0.01263545,0.00004936807,0.00005507764,0.00005991124,0.003328165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1582741,"threshold_uncertainty_score":0.9969985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0237390184300451,"score_gpt":0.284118379274981,"score_spread":0.2603793608449358,"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."}}