{"id":"W3119940242","doi":"10.5539/ijel.v11n1p266","title":"The Practice of Cross-Grading in Assessing Writing: The Case of EFL Teachers and Students in a Saudi Arabian Context","year":2021,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; English as a foreign language; Mathematics education; English language; Context (archaeology); Perception; Pedagogy; Medical education; Medicine","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003513708,0.00006339874,0.0001580428,0.00008438309,0.0001290016,0.0003941191,0.0004082604,0.00004643421,0.00000696747],"category_scores_gemma":[0.130979,0.00004750262,0.00005538257,0.0001789299,0.0002779061,0.0001647334,0.00009738514,0.0003414068,8.41838e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273634,"about_ca_system_score_gemma":0.0002376559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000479714,"about_ca_topic_score_gemma":0.001729019,"domain_scores_codex":[0.9981889,0.0003216315,0.0006366604,0.00007939711,0.0006470465,0.0001263383],"domain_scores_gemma":[0.9882506,0.003114258,0.0006893236,0.00006475295,0.007844454,0.00003663199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005951812,0.0002506251,0.912468,0.000006927361,0.0001518884,0.000998399,0.05830419,0.00007528286,0.00002203766,0.02366766,0.0001340955,0.003861373],"study_design_scores_gemma":[0.002875755,0.00007803881,0.2174984,0.0006727789,0.00009577262,0.0000629838,0.7002289,0.0001313715,0.0001721911,0.002410467,0.07559573,0.0001776116],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9719644,0.0007826273,0.00001730961,0.0003521623,0.003025843,0.00006428391,0.000002214076,0.000001965259,0.02378924],"genre_scores_gemma":[0.997686,0.0003905104,0.0003737185,0.00006109599,0.001434093,7.4573e-7,4.363813e-7,0.000005114193,0.00004830126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6949697,"threshold_uncertainty_score":0.8763411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03303773342466218,"score_gpt":0.4377414418712045,"score_spread":0.4047037084465422,"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."}}