{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001798346,0.000177097,0.0003099958,0.0002215883,0.0001686265,0.0002516586,0.001628168,0.00005753729,0.000002546719],"category_scores_gemma":[0.00006814057,0.0001193353,0.00004163153,0.002297193,0.00008128235,0.0004464181,0.0001762381,0.0002976896,0.00002511009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192562,"about_ca_system_score_gemma":0.000202436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007655458,"about_ca_topic_score_gemma":0.001151054,"domain_scores_codex":[0.9973971,0.0005879737,0.0006707735,0.0005006471,0.0004896128,0.0003539],"domain_scores_gemma":[0.9983736,0.0002394167,0.0001387501,0.001014627,0.0001846455,0.00004899154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002573532,0.003513389,0.1181015,0.0005518548,0.0001539082,0.0009580637,0.09372596,0.02514553,0.001024284,0.6816358,0.0003222355,0.07461009],"study_design_scores_gemma":[0.0001465777,0.001317523,0.01446585,0.0007016998,0.00003008563,0.00004600542,0.1251977,0.8380796,0.01500039,0.00455941,0.00004706134,0.0004080896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8097694,0.00003930604,0.1855207,0.000359085,0.0003944002,0.000900202,9.847431e-7,0.0004371597,0.002578796],"genre_scores_gemma":[0.9980114,5.122102e-7,0.001767682,0.00007230485,0.00003952964,0.00008296793,6.58323e-7,0.000007917981,0.0000170776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.812934,"threshold_uncertainty_score":0.4866352,"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."}}