{"id":"W1970572514","doi":"10.5539/elt.v5n8p76","title":"Problematizing Rating Scales in EFL Academic Writing Assessment: Voices from Iranian Context","year":2012,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Rating scale; Context (archaeology); Accountability; Agency (philosophy); Language proficiency; Pedagogy; Sociology; Political science; Social science; Developmental 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07866446,0.0005699796,0.0005040471,0.002115059,0.005115554,0.005252709,0.002414272,0.00144361,0.001065199],"category_scores_gemma":[0.09917708,0.0004516713,0.0003204482,0.002502174,0.009460567,0.004049377,0.004558283,0.003146223,0.0002522829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003636,"about_ca_system_score_gemma":0.004889376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006987081,"about_ca_topic_score_gemma":0.01241639,"domain_scores_codex":[0.9376866,0.04291737,0.003563635,0.002750369,0.01109033,0.001991646],"domain_scores_gemma":[0.9198768,0.04983277,0.007671216,0.004726362,0.01627982,0.001612976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00009284054,0.0001355146,0.06754156,0.0004082577,0.00002012489,0.001312155,0.7915744,0.0001861004,0.002883379,0.01148278,0.002826621,0.1215363],"study_design_scores_gemma":[0.00002010154,0.0002273407,0.03969194,0.000651819,0.00002455233,0.002500522,0.9007374,0.001371741,0.002224719,0.005665815,0.04678729,0.00009669187],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9503973,0.00309344,0.0161505,0.0125885,0.0004297971,0.0002247747,0.00004685785,0.00005368535,0.01701503],"genre_scores_gemma":[0.9912136,0.0005648472,0.006339937,0.0008057759,0.0000965588,0.00009245665,0.00001562003,0.00002904526,0.0008421747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07866446,"threshold_uncertainty_score":0.4160224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0197186510102331,"score_gpt":0.2831805692599415,"score_spread":0.2634619182497083,"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."}}