{"id":"W1604689683","doi":"10.18806/tesl.v21i2.176","title":"Selecting and Using Computer-Based Language Tests (CBLTs) to Assess Language Proficiency: Guidelines for Educators","year":2004,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Checklist; Language assessment; Selection (genetic algorithm); Set (abstract data type); Foreign language; Language proficiency; Language education; Psychology; Computer science; Mathematics education; Language acquisition; Language industry; Comprehension approach; Pedagogy; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005593432,0.0001459879,0.0001702681,0.000125786,0.0009684658,0.0003624486,0.0001345267,0.00002329764,0.0003657512],"category_scores_gemma":[0.0003832342,0.00012438,0.00003937728,0.00005576232,0.00002864606,0.0001010297,0.00002012082,0.0002944294,7.296871e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002565931,"about_ca_system_score_gemma":0.001367943,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1359023,"about_ca_topic_score_gemma":0.1830087,"domain_scores_codex":[0.9989395,0.00004487436,0.0002709847,0.0001661151,0.0002371933,0.0003413017],"domain_scores_gemma":[0.999221,0.0001235815,0.0001380535,0.00008726859,0.0002493649,0.0001807803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000173436,0.0006012756,0.007094951,0.0009704659,0.0004142894,0.0009196321,0.4651129,0.1681996,0.02536322,0.01472769,0.159181,0.1572416],"study_design_scores_gemma":[0.009918415,0.002850218,0.004380826,0.004913498,0.0005820686,0.002486215,0.4034821,0.08410332,0.009097134,0.0008041661,0.4721512,0.005230833],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99104,0.001887574,0.004267187,0.001686737,0.0006946296,0.0001516292,0.00001467293,0.00004944637,0.0002081471],"genre_scores_gemma":[0.9622096,5.003152e-7,0.01969797,0.01540767,0.002408098,0.000004010698,0.000004941743,0.00003424036,0.000232948],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3129703,"threshold_uncertainty_score":0.8698518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1109585393156463,"score_gpt":0.3576108246165036,"score_spread":0.2466522853008573,"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."}}