{"id":"W2923578044","doi":"10.1186/s40468-019-0078-7","title":"The language assessment literacy needs of Iranian EFL teachers with a focus on reformed assessment policies","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Rubric; Psychology; Literacy; Curriculum; Pedagogy; Active listening; Mathematics education; Language assessment; Alternative assessment; Perception; Focus group; Sociology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003266443,0.0001394934,0.0002746806,0.0007862643,0.00136874,0.00176567,0.0004048916,0.0008837045,0.001192379],"category_scores_gemma":[0.01332522,0.0001950122,0.0001529513,0.0007216848,0.001038046,0.001820602,0.0009734715,0.0009819649,0.0002046536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002814357,"about_ca_system_score_gemma":0.00564144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01895434,"about_ca_topic_score_gemma":0.02334942,"domain_scores_codex":[0.997486,0.0006705332,0.0002039868,0.0001406949,0.000695676,0.0008032107],"domain_scores_gemma":[0.9919971,0.00207048,0.002037278,0.0001793156,0.002790152,0.0009256622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001971038,0.0006450421,0.5118874,0.0003284755,0.00001331636,0.002225328,0.3725817,0.0004047985,0.003756138,0.001595103,0.002323462,0.1040421],"study_design_scores_gemma":[0.00002139716,0.0004122324,0.4118794,0.0002147078,0.00001242617,0.001207254,0.5721058,0.0007444667,0.0009969135,0.0008084585,0.01154403,0.0000529656],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967217,0.0001577577,0.00006030128,0.001566105,0.000006430713,0.000009949355,0.00001403025,0.000003472164,0.001460222],"genre_scores_gemma":[0.9990589,0.0001259335,0.0001324543,0.0002134802,0.000004504955,0.00001207317,0.00001532296,0.000001203761,0.0004361631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01895434,"threshold_uncertainty_score":0.03768802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01648693977985285,"score_gpt":0.3597537479867195,"score_spread":0.3432668082068666,"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."}}