{"id":"W4411337926","doi":"10.1109/pacificvis64226.2025.00035","title":"Evaluating ‘Graphical Perception’ with Multimodal LLMs","year":2025,"lang":"en","type":"article","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perception; Computer science; Human–computer interaction; Psychology; Neuroscience","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":[0.004854924,0.001770236,0.0007666902,0.001111392,0.0003565416,0.002754689,0.00162353,0.002096832,0.008722278],"category_scores_gemma":[0.041962,0.0004030529,0.0009700684,0.0006641178,0.0007083187,0.004664173,0.002631698,0.001923768,0.002297018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009912716,"about_ca_system_score_gemma":0.0006346481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004637239,"about_ca_topic_score_gemma":0.003936321,"domain_scores_codex":[0.9970292,0.001534125,0.0001584242,0.0007369131,0.0004057806,0.0001355821],"domain_scores_gemma":[0.9785944,0.01754192,0.0006956569,0.001623345,0.001070456,0.0004742728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004387327,0.001287695,0.01685328,0.002180229,0.000663798,0.0005001315,0.002604194,0.2200963,0.05017135,0.005913002,0.01716348,0.6781791],"study_design_scores_gemma":[0.0001441317,0.001340799,0.006384818,0.0001847584,0.0001459673,0.0001929238,0.000853775,0.9540237,0.02060655,0.01109416,0.004898123,0.0001303754],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6065318,0.002519196,0.3463014,0.001224967,0.0004469732,0.0004329264,0.002901348,0.02778689,0.01185444],"genre_scores_gemma":[0.8843505,0.0003945248,0.1084303,0.0004156005,0.0000788408,0.0002084549,0.003363773,0.0007577842,0.002000094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008722278,"threshold_uncertainty_score":0.02917892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03078538251689153,"score_gpt":0.3408607932723709,"score_spread":0.3100754107554794,"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."}}