{"id":"W4323544073","doi":"10.1080/15434303.2023.2184266","title":"Aligning Language Frameworks: An Example with the CLB and CEFR","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Rasch model; Benchmarking; Dimension (graph theory); Computer science; German; Argument (complex analysis); Linguistics; Vocabulary; Certificate; Natural language processing; Computational linguistics; Language proficiency; Artificial intelligence; Psychology; Mathematics education","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.02701222,0.0007620074,0.0006920103,0.008431097,0.006819684,0.008710169,0.00244239,0.002290601,0.00721273],"category_scores_gemma":[0.07585738,0.0005260843,0.0006020141,0.01304957,0.009718081,0.006842485,0.008984303,0.004057551,0.001512418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01748711,"about_ca_system_score_gemma":0.02539293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2938808,"about_ca_topic_score_gemma":0.3671863,"domain_scores_codex":[0.9576035,0.02317956,0.001561584,0.002366807,0.01254604,0.002742643],"domain_scores_gemma":[0.9657239,0.01131534,0.001253413,0.006226084,0.01422957,0.001251593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000986126,0.0001094095,0.007945474,0.0002833651,0.00001937144,0.0004960372,0.09645028,0.002067208,0.002496927,0.647805,0.01061321,0.2316151],"study_design_scores_gemma":[0.0000437103,0.0001314777,0.02071795,0.001141197,0.00004224747,0.0006152316,0.107568,0.008786783,0.005651643,0.1661758,0.6889187,0.0002072858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1069079,0.001371336,0.4822515,0.01350898,0.0006634633,0.001253147,0.001105093,0.001488622,0.39145],"genre_scores_gemma":[0.4770626,0.000422284,0.5005577,0.0009912142,0.00004041865,0.0008494413,0.001089604,0.000829996,0.01815676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2938808,"threshold_uncertainty_score":0.5843405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02005334755489001,"score_gpt":0.2752021690098073,"score_spread":0.2551488214549173,"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."}}