{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02231932,0.000840267,0.0006302095,0.007159703,0.001020774,0.006440415,0.001463741,0.002517844,0.004560086],"category_scores_gemma":[0.2758821,0.0006765082,0.00116746,0.00474923,0.0008063084,0.007659638,0.002568908,0.001424852,0.001373207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001413819,"about_ca_system_score_gemma":0.003422198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006427418,"about_ca_topic_score_gemma":0.0115936,"domain_scores_codex":[0.971349,0.01391207,0.004042818,0.002168905,0.007956318,0.000570821],"domain_scores_gemma":[0.6209229,0.2976952,0.02311773,0.01722907,0.03881373,0.002221502],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003838737,0.002009858,0.2395544,0.004836112,0.001063379,0.001063037,0.01059587,0.09354042,0.01461371,0.03757111,0.06670561,0.5246077],"study_design_scores_gemma":[0.0005911432,0.001186538,0.04233022,0.001637581,0.0008899781,0.000678353,0.00519938,0.8303255,0.02159217,0.04660416,0.04873679,0.0002282307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5906126,0.001229556,0.3425315,0.003240069,0.0004566449,0.001884161,0.01453767,0.02913138,0.01637639],"genre_scores_gemma":[0.7341,0.0003369104,0.2450843,0.0002206994,0.00005790418,0.0006549079,0.01578424,0.001579472,0.002181522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9776807,"threshold_uncertainty_score":0.1180372,"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."}}