{"id":"W4415390017","doi":"10.1016/j.cag.2025.104458","title":"Evaluating graphical perception capabilities of Vision Transformers","year":2025,"lang":"en","type":"article","venue":"Computers & Graphics","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universität Ulm","keywords":"Perception; Visualization; Visual perception; Convolutional neural network; Benchmark (surveying); Transformer; Human visual system model; Graphical model","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.002176126,0.0006606301,0.000358893,0.0006506243,0.0001505449,0.001285249,0.000893169,0.000728831,0.005221849],"category_scores_gemma":[0.0171242,0.0002579885,0.0003580784,0.0002280313,0.0006638583,0.002474494,0.001831732,0.0007780134,0.0007270406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005623255,"about_ca_system_score_gemma":0.0003567973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001616373,"about_ca_topic_score_gemma":0.001422272,"domain_scores_codex":[0.999312,0.0001916275,0.00005496538,0.0001875786,0.0001686785,0.00008511945],"domain_scores_gemma":[0.9948584,0.003052731,0.0004771261,0.0006467954,0.0005983483,0.0003666934],"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":[0.00420236,0.0005775494,0.05267131,0.001615684,0.0003934235,0.0002887991,0.001318235,0.1321656,0.1537737,0.01548958,0.005981794,0.6315221],"study_design_scores_gemma":[0.0001850612,0.003069379,0.03578287,0.0001200805,0.0002054232,0.0004447262,0.0006375639,0.8756086,0.06377009,0.01659737,0.003491057,0.00008781188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8943725,0.0006938213,0.09304956,0.0002727188,0.0001222443,0.0001888942,0.0003873395,0.00177093,0.009141888],"genre_scores_gemma":[0.9858232,0.0001072697,0.01301794,0.00004959077,0.000009083658,0.00002534856,0.000301623,0.00004858709,0.0006174717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005221849,"threshold_uncertainty_score":0.01746881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02334548695330664,"score_gpt":0.3018931063226519,"score_spread":0.2785476193693453,"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."}}