{"id":"W4413226423","doi":"10.18280/isi.300624","title":"AI-Driven Assessment Systems in Higher Education: Effectiveness for Enhancing Critical Thinking and Creativity","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Engineering Education and Technology","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Creativity; Critical thinking; Psychology; Mathematics education; Engineering ethics; Pedagogy; Engineering; Social psychology","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":[0.0004216406,0.00009873945,0.0001578591,0.0003689351,0.0001533322,0.0003262288,0.0002024355,0.00009843892,0.000002169946],"category_scores_gemma":[0.0001963899,0.0001016157,0.00002045177,0.0003902032,0.00004574107,0.001635724,0.00007834832,0.000116636,0.000001820524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003398363,"about_ca_system_score_gemma":0.0002741344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005215359,"about_ca_topic_score_gemma":0.00001026808,"domain_scores_codex":[0.9992713,0.00005832163,0.0002848245,0.0001323891,0.00009047223,0.0001626829],"domain_scores_gemma":[0.9991591,0.0003739957,0.00005973686,0.0001963605,0.0001815019,0.0000293212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000002672712,0.00003069658,0.004581489,0.001002058,0.000008957883,1.533865e-7,0.0006955829,0.0005346035,0.0001269064,0.9772515,0.0001137978,0.01565153],"study_design_scores_gemma":[0.00145093,0.0002324507,0.4364236,0.004129745,0.00003607394,0.00004288261,0.002172094,0.2905449,0.002613345,0.2435078,0.01807167,0.0007745571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02955392,0.0001992484,0.9640182,0.0009849246,0.001722434,0.0004550581,0.000001672755,0.0002051635,0.002859376],"genre_scores_gemma":[0.9833801,0.000004299156,0.01587022,0.0002504261,0.000024827,0.0004157695,0.000007689672,0.000003261769,0.00004344451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9538261,"threshold_uncertainty_score":0.4143767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296434650763409,"score_gpt":0.3007527836646693,"score_spread":0.2877884371570353,"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."}}