{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01402294,0.0004314795,0.0006201923,0.002496013,0.006347322,0.005694394,0.001248517,0.001071438,0.001303814],"category_scores_gemma":[0.03393566,0.0003759294,0.0003251778,0.002708719,0.002807134,0.002125021,0.003046829,0.001342286,0.0004259875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00601588,"about_ca_system_score_gemma":0.006700035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02917035,"about_ca_topic_score_gemma":0.04037596,"domain_scores_codex":[0.9922506,0.003626776,0.0007587448,0.0004339481,0.001801255,0.001128609],"domain_scores_gemma":[0.958581,0.01536947,0.005559858,0.001768367,0.01367003,0.005051373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0002511487,0.001503929,0.2198032,0.0001732191,0.00003258623,0.000845135,0.719385,0.0001803783,0.0015774,0.0007186782,0.0004511069,0.05507828],"study_design_scores_gemma":[0.00002633464,0.0009563733,0.1836383,0.0001850204,0.00003581371,0.0008570749,0.8020625,0.0009369224,0.002192842,0.0003034892,0.008727683,0.00007764297],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9988008,0.0001105936,0.0001493228,0.000200071,0.000006010753,0.00002275839,0.000007861488,0.000003957402,0.0006987153],"genre_scores_gemma":[0.9990906,0.0001366679,0.0001842097,0.000127159,0.000004236493,0.00001353926,0.000008408256,0.00000366661,0.0004314492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02917035,"threshold_uncertainty_score":0.07416129,"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."}}