{"id":"W4404521715","doi":"10.1177/02655322241291764","title":"Review of the Canadian English Language Proficiency Index Program (CELPIP)","year":2024,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Language proficiency; Index (typography); Language assessment; Linguistics; Mathematics education; Computer science; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.0008019099,0.00007301444,0.0000946068,0.00006603318,0.0002904725,0.00009248687,0.0002993015,0.00005246398,0.0003693493],"category_scores_gemma":[0.006670138,0.00005301023,0.000055435,0.001021299,0.0001315451,0.00006578924,0.00002684972,0.0001938374,0.00002129558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201846,"about_ca_system_score_gemma":0.001719958,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.52345,"about_ca_topic_score_gemma":0.3617387,"domain_scores_codex":[0.9990414,0.000130754,0.0001757909,0.0001409557,0.0002245486,0.000286565],"domain_scores_gemma":[0.999315,0.0001739821,0.00005688514,0.0001958712,0.0001245906,0.0001336352],"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":[3.003819e-7,0.00003652089,0.00646415,0.002309049,0.000007950159,0.00001297997,0.4624062,0.000001014016,0.00009973927,0.004638097,0.00342061,0.5206034],"study_design_scores_gemma":[0.000154009,0.00004967563,0.009794569,0.01948521,0.0000804322,0.000009522319,0.1107338,0.0009294776,0.0004657567,0.0001335711,0.8576055,0.0005584374],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2110727,0.06271833,0.000001386185,0.002894062,0.001402289,0.001285487,0.00002472232,0.00056519,0.7200358],"genre_scores_gemma":[0.9939931,0.0000995364,0.0003642062,0.001491181,0.0006807329,0.00003448559,0.000004396866,0.00001238293,0.003319982],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8541849,"threshold_uncertainty_score":0.798526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06094631709999317,"score_gpt":0.4570166644197495,"score_spread":0.3960703473197564,"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."}}