{"id":"W4412505466","doi":"10.1016/j.system.2025.103784","title":"Automated scoring in the era of artificial intelligence: An empirical study with Turkish essays","year":2025,"lang":"en","type":"article","venue":"System","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; Leuphana Universität Lüneburg","keywords":"Turkish; Artificial intelligence; Computer science; Empirical research; Natural language processing; Mathematics education; Psychology; Linguistics; Statistics; Mathematics; Philosophy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0154007,0.0005490463,0.0006100014,0.003175504,0.001445449,0.002541886,0.001436702,0.0008186011,0.001507892],"category_scores_gemma":[0.1103675,0.0002428915,0.0003029347,0.003621408,0.001626611,0.002220843,0.001992027,0.000803353,0.0008931651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001499354,"about_ca_system_score_gemma":0.0009664844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002750788,"about_ca_topic_score_gemma":0.004009625,"domain_scores_codex":[0.9790387,0.01245814,0.002050319,0.001496715,0.004343784,0.000612348],"domain_scores_gemma":[0.8667276,0.07942688,0.01587136,0.008797248,0.02706432,0.002112557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001587862,0.002282282,0.5037058,0.00176903,0.0002004191,0.003453912,0.1755887,0.003473557,0.007190036,0.002346037,0.007593597,0.2908087],"study_design_scores_gemma":[0.0001499419,0.002296712,0.8297444,0.0007475116,0.0001718427,0.003778461,0.1004681,0.01583032,0.008634017,0.002082038,0.03585445,0.0002421001],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9980595,0.0001371034,0.000631623,0.0000472879,0.00001127543,0.00004324699,0.00007399602,0.00001611225,0.0009798052],"genre_scores_gemma":[0.9977847,0.0001122427,0.001282448,0.00002733825,0.00001506133,0.00005987503,0.0002210209,0.00002069589,0.0004766648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0154007,"threshold_uncertainty_score":0.08144772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04233942530495005,"score_gpt":0.3434102288782708,"score_spread":0.3010708035733207,"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."}}