{"id":"W4404360542","doi":"10.18280/ts.410540","title":"Exploring Multimodal Large Language Models ChatGPT-4 and Bard for Visual Complexity Evaluation of Mobile User Interfaces","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Human–computer interaction; Visual language; Artificial intelligence; Linguistics","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":[0.003268243,0.001410272,0.0006487126,0.001333901,0.0002975956,0.002209644,0.001228213,0.001091681,0.004771122],"category_scores_gemma":[0.01942552,0.0003614836,0.00115401,0.0003866758,0.000554506,0.002422275,0.002353542,0.001279952,0.0009206478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027144,"about_ca_system_score_gemma":0.0005406883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002720991,"about_ca_topic_score_gemma":0.002833378,"domain_scores_codex":[0.9967873,0.001840296,0.0001708562,0.0003367789,0.000766942,0.00009781762],"domain_scores_gemma":[0.9881197,0.00909056,0.0004013327,0.0008738014,0.001144775,0.0003696845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006162061,0.001394262,0.01423667,0.004348214,0.0006405817,0.000969035,0.004364739,0.1606009,0.1530108,0.0128303,0.01400238,0.62744],"study_design_scores_gemma":[0.0001592102,0.00159849,0.009536105,0.0001487302,0.0001326481,0.0003982793,0.0005857265,0.9500895,0.02506047,0.005815267,0.006333561,0.0001419709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4297348,0.001542593,0.5405959,0.0005497689,0.0002038629,0.0009710373,0.002081225,0.01572154,0.008599336],"genre_scores_gemma":[0.829483,0.0002277599,0.1641351,0.0001485965,0.00002902233,0.0006025584,0.002259764,0.0005465818,0.002567659],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004771122,"threshold_uncertainty_score":0.01728433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1293376928250662,"score_gpt":0.3634635961324159,"score_spread":0.2341259033073496,"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."}}