{"id":"W4415444551","doi":"10.22329/jtl.v19i4.10012","title":"AI Formative Assessment in Saudi Education: A Study Across Universities","year":2025,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Realization (probability); Higher education; Qualitative research; Natural (archaeology); Documentation","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":[0.002097106,0.00006586461,0.0001575252,0.0002196384,0.0003970538,0.0002016118,0.0002254947,0.00002263488,8.828852e-7],"category_scores_gemma":[0.000112158,0.00005638147,0.00003701376,0.0001779856,0.00001496332,0.0005098298,0.0001213685,0.00179891,3.701448e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001016201,"about_ca_system_score_gemma":0.0003711051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007218031,"about_ca_topic_score_gemma":0.000007673042,"domain_scores_codex":[0.9989108,0.0005135748,0.0002272009,0.00008656356,0.0001466046,0.0001152963],"domain_scores_gemma":[0.9994367,0.0001823746,0.00019524,0.00007261068,0.00007939372,0.0000336595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002181304,0.0009551903,0.3439163,0.00007539435,0.0001555965,0.00006308014,0.2013226,0.02404389,0.00004389785,0.01974639,0.0007512624,0.4089046],"study_design_scores_gemma":[0.001888016,0.001123769,0.2480933,0.001003954,0.00004642463,0.00009240278,0.5815842,0.1390868,0.000005126903,0.00245721,0.02435299,0.0002657252],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9372602,0.0001568689,0.05376285,0.006978361,0.000193544,0.00002826383,6.823552e-8,0.00001571554,0.00160415],"genre_scores_gemma":[0.98827,0.000008844757,0.009447549,0.0002464848,0.00004601854,2.527596e-7,1.547433e-7,0.000001954433,0.001978743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4086388,"threshold_uncertainty_score":0.781547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0077115634617823,"score_gpt":0.3625283605594242,"score_spread":0.3548167970976419,"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."}}