{"id":"W4414192480","doi":"10.1007/978-3-032-04630-7_1","title":"Evaluating Compliance with Visualization Guidelines in Diagrams for Scientific Publications Using Large Vision Language Models","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Visualization; Set (abstract data type); Misinformation; Data visualization; Field (mathematics); Creative visualization; Data set; Quality (philosophy)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00224214,0.0003699491,0.0004113035,0.001550319,0.0005149848,0.001734029,0.002175286,0.0001702382,0.000006366783],"category_scores_gemma":[0.0004055427,0.0003314303,0.00007261826,0.002451753,0.0003159968,0.001497112,0.000840992,0.0002476885,0.00000315151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002923755,"about_ca_system_score_gemma":0.001034028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002370507,"about_ca_topic_score_gemma":0.0004194507,"domain_scores_codex":[0.9961479,0.00004796072,0.0007405289,0.001526115,0.0009827312,0.0005547566],"domain_scores_gemma":[0.9966179,0.000318075,0.0003952047,0.001227357,0.00134044,0.000101037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006287856,0.00008517827,0.00008523371,0.0001467537,0.000009073253,0.000004898508,0.001042543,0.510316,0.0002290479,0.2529428,0.0001167573,0.2350154],"study_design_scores_gemma":[0.0004079636,0.00007119528,0.0000129505,0.001163081,0.0000100125,0.000004969672,0.000001338569,0.9652693,0.0001698842,0.03180053,0.0007195271,0.0003692141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009851834,0.0002900733,0.997254,0.0005189062,0.0005732395,0.0007450971,0.00004785611,0.0001324871,0.0003398029],"genre_scores_gemma":[0.02450892,0.00001941874,0.9721396,0.001381984,0.0001667981,0.00003000671,0.0002426468,0.00003715985,0.00147346],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4549533,"threshold_uncertainty_score":0.9999138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1453790523004303,"score_gpt":0.4387568907074157,"score_spread":0.2933778384069854,"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."}}