{"id":"W1645137987","doi":"10.18806/tesl.v18i2.909","title":"Using the Canadian Language Benchmarks (CLB) to Benchmark College Programs/Courses and Language Proficiency Tests","year":2001,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Test of English as a Foreign Language; Benchmark (surveying); Computer science; Language assessment; Test (biology); Process (computing); Language proficiency; Mathematics education; Foreign language; Order (exchange); Natural language processing; Psychology; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01682353,0.001040288,0.0007946819,0.02125396,0.005876905,0.005893859,0.002833673,0.0008278405,0.003926531],"category_scores_gemma":[0.06260008,0.0003887911,0.0007059419,0.01881944,0.001732087,0.002205897,0.003426107,0.001979625,0.001657841],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.04004153,"about_ca_system_score_gemma":0.102277,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9109291,"about_ca_topic_score_gemma":0.9350967,"domain_scores_codex":[0.9699563,0.003826307,0.001529424,0.001219932,0.021913,0.001555016],"domain_scores_gemma":[0.9044484,0.005173205,0.003344457,0.003269528,0.07881245,0.004952058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001463753,0.0002946564,0.09734721,0.0006063189,0.00008000875,0.0001795766,0.004534203,0.004968193,0.002316209,0.04213014,0.1417691,0.7056279],"study_design_scores_gemma":[0.00007821327,0.0003422261,0.3790483,0.001073866,0.00007681059,0.0002117768,0.01084122,0.009781823,0.00791338,0.01048375,0.5796608,0.0004877773],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.1592365,0.006778995,0.2020197,0.02327433,0.002941926,0.01077795,0.04265788,0.004796339,0.5475163],"genre_scores_gemma":[0.5453191,0.00276117,0.362768,0.002633215,0.0001745077,0.00498165,0.02935397,0.00130206,0.0507063],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9599585,"threshold_uncertainty_score":0.2905231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02763543203184957,"score_gpt":0.2606801595379964,"score_spread":0.2330447275061468,"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."}}