{"id":"W4409526834","doi":"10.5430/wjel.v15n5p285","title":"Investigate How AI Algorithms Can Be Used to Automate English Language Proficiency Assessments","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Algorithm; Natural language processing; Artificial intelligence; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0125712,0.0008084155,0.0004820293,0.001781211,0.0004384778,0.002936524,0.001061703,0.000965266,0.00216686],"category_scores_gemma":[0.1037724,0.0003259671,0.0004761125,0.001272728,0.0005224767,0.003743873,0.001240999,0.0008859412,0.001400847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007916884,"about_ca_system_score_gemma":0.001957717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003882267,"about_ca_topic_score_gemma":0.003855719,"domain_scores_codex":[0.9915138,0.004885511,0.0005857397,0.001028406,0.001702729,0.000283744],"domain_scores_gemma":[0.9431702,0.04315082,0.003678687,0.002708448,0.006735154,0.0005566391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005151662,0.001049447,0.1826333,0.0004811064,0.0003142991,0.000178406,0.003538387,0.04239786,0.01138158,0.0121649,0.002991875,0.7423537],"study_design_scores_gemma":[0.0002518476,0.002407667,0.1064647,0.0004654744,0.0003181391,0.0006075065,0.004172862,0.7800916,0.04112905,0.03350924,0.030347,0.0002349737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.454832,0.0004770508,0.5256962,0.001204972,0.0001471791,0.0009252728,0.0003732373,0.003187577,0.01315652],"genre_scores_gemma":[0.6771235,0.0002131416,0.3198635,0.0002640209,0.00002960975,0.0003677784,0.0003706887,0.0001253492,0.001642344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0125712,"threshold_uncertainty_score":0.06648368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01266609926995779,"score_gpt":0.3105538301804156,"score_spread":0.2978877309104578,"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."}}