{"id":"W2090290510","doi":"10.3138/cmlr.64.1.009","title":"AFL Research in the L2 Classroom and Evidence of Usefulness: Taking Formative Assessment to the Next Level","year":2007,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Assessment for learning; Mathematics education; Psychology; Curriculum; Pedagogy; Bridge (graph theory)","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":[],"consensus_categories":[],"category_scores_codex":[0.0106884,0.0001841327,0.000355209,0.0003305282,0.0006114084,0.0001702933,0.0009912907,0.00008869395,0.00006950532],"category_scores_gemma":[0.001728973,0.0001266817,0.00008310501,0.001185937,0.00046119,0.0003516937,0.00008954675,0.0004309898,0.000009597355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007731929,"about_ca_system_score_gemma":0.0004727678,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.4403425,"about_ca_topic_score_gemma":0.9675052,"domain_scores_codex":[0.9969258,0.0009164999,0.0004357957,0.000314114,0.0003831481,0.001024606],"domain_scores_gemma":[0.9966396,0.002051632,0.0001713854,0.0004526493,0.0002452791,0.000439419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001716664,0.00003935793,0.02267307,0.001953881,0.00006244834,0.0005808625,0.7654226,0.000005665282,0.000904787,0.017393,0.001867381,0.1890797],"study_design_scores_gemma":[0.0003019885,0.0001609726,0.4102632,0.01616888,0.00009671182,0.00005324414,0.5117558,0.0002106771,0.00003400872,0.001227034,0.05914835,0.0005791428],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9074288,0.0704557,0.0003977606,0.007621207,0.0001458436,0.00195242,0.0000477945,0.00001734523,0.01193315],"genre_scores_gemma":[0.9910566,0.006778504,0.0004962279,0.001030686,0.0001946963,0.0001171087,0.000007822695,0.00001859609,0.0002997936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5271627,"threshold_uncertainty_score":0.5633843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1996400635777524,"score_gpt":0.4220425672263123,"score_spread":0.2224025036485599,"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."}}