{"id":"W2472075195","doi":"10.1017/s0261444815000233","title":"Review of washback research literature within Kane's argument-based validation framework","year":2015,"lang":"en","type":"article","venue":"Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Empirical research; Argument (complex analysis); Maturity (psychological); Systematic review; English language; Psychology; Political science; Epistemology; Mathematics education; Medicine; Philosophy; Law; Developmental psychology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05135575,0.001097062,0.003434882,0.01831709,0.001615299,0.007423318,0.003091957,0.003056044,0.004298945],"category_scores_gemma":[0.1683104,0.001165207,0.002071928,0.015549,0.00570466,0.01002717,0.00410487,0.003104799,0.0009539415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005699094,"about_ca_system_score_gemma":0.01597768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002772161,"about_ca_topic_score_gemma":0.004763206,"domain_scores_codex":[0.9562926,0.02481888,0.006562093,0.00169091,0.01000777,0.0006277218],"domain_scores_gemma":[0.7631053,0.2048813,0.009693179,0.003402306,0.0182517,0.0006661583],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00009728548,0.0001133503,0.001236695,0.109047,0.0004675871,0.0004554709,0.009397997,0.0004234482,0.0003415936,0.02856335,0.009895733,0.8399606],"study_design_scores_gemma":[0.00008605568,0.000295413,0.007582978,0.5670429,0.001329129,0.001355223,0.01567238,0.0007069353,0.001093848,0.04126912,0.3634501,0.0001159144],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00282772,0.9820151,0.003471089,0.004914734,0.0006040175,0.0001756233,0.0000510355,0.00002726536,0.005913349],"genre_scores_gemma":[0.0560399,0.9300365,0.009087312,0.002560428,0.0003676231,0.000533677,0.0001452979,0.00003265778,0.00119662],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9486442,"threshold_uncertainty_score":0.2715984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08897567591661655,"score_gpt":0.4676807480738409,"score_spread":0.3787050721572244,"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."}}