{"id":"W6922378787","doi":"10.11575/prism/49008","title":"Scaling the Great Wall of Canada: Technological Solutions for More Accessible and Equitable Language Proficiency Testing","year":2021,"lang":"en","type":"other","venue":"Open MIND","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Context (archaeology); Language assessment; Presentation (obstetrics); Language proficiency; Software; Language model","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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":[0.01088121,0.0008084109,0.0003477418,0.003166882,0.01122487,0.01014508,0.003471248,0.003814606,0.05648813],"category_scores_gemma":[0.0375055,0.0005778868,0.0006017943,0.004437557,0.005402924,0.006097721,0.009860697,0.004665753,0.01048721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03522621,"about_ca_system_score_gemma":0.1629598,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9309031,"about_ca_topic_score_gemma":0.9612706,"domain_scores_codex":[0.9890576,0.001931384,0.0002530063,0.0006910705,0.005999947,0.002066977],"domain_scores_gemma":[0.9627256,0.005506163,0.001135743,0.003768818,0.01602571,0.01083798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006833005,0.00008522096,0.005950954,0.0001265451,0.00001321683,0.0004344218,0.003297606,0.0005926439,0.001060676,0.09712553,0.6269411,0.2643038],"study_design_scores_gemma":[0.00002809094,0.00003378264,0.006105518,0.0002603924,0.000008925856,0.000160278,0.00439946,0.001595411,0.0006861101,0.01584432,0.9707902,0.00008738848],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.02363261,0.005151792,0.06784918,0.3651367,0.005742369,0.0007950581,0.004342888,0.006869754,0.5204797],"genre_scores_gemma":[0.2430277,0.007852402,0.1553804,0.06669603,0.001742634,0.00102899,0.00500523,0.003426906,0.5158397],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.06909692,"threshold_uncertainty_score":0.2555853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2202613200417557,"score_gpt":0.481945900297988,"score_spread":0.2616845802562323,"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."}}