{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005484178,0.0002133799,0.0001969639,0.0001149605,0.000624606,0.0007486553,0.0002250085,0.00007595622,0.001131914],"category_scores_gemma":[0.000008406101,0.0001323814,0.00004451845,0.00009667943,0.0001385073,0.0003650283,0.00002646692,0.0006493533,0.00006871385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001981689,"about_ca_system_score_gemma":0.00002470066,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006839872,"about_ca_topic_score_gemma":0.00741013,"domain_scores_codex":[0.9986045,0.0002143442,0.0001621862,0.0003529482,0.0002666618,0.0003993184],"domain_scores_gemma":[0.9990612,0.0002692427,0.00009699659,0.0004512317,0.00003096972,0.00009036184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001080775,0.00003964519,0.0004961847,0.00003001023,0.00007648129,0.0002267584,0.8525257,0.00001097249,0.0005724882,0.02496104,0.00137938,0.1196706],"study_design_scores_gemma":[0.0004785633,0.0006584169,0.002713481,0.00006172082,0.00005636114,0.00002070967,0.9796958,0.0009874803,0.000025679,0.0001303006,0.01483835,0.0003331432],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9849994,0.000317055,0.0003732293,0.0007247393,0.0001626314,0.0001842617,0.000016343,0.0005715318,0.01265087],"genre_scores_gemma":[0.9922587,0.000002258946,0.0003904813,0.001166112,0.0008330718,0.00004671986,0.000131703,0.00005089961,0.005120045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1271702,"threshold_uncertainty_score":0.9997812,"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."}}