{"id":"W7106825513","doi":"10.48448/29g8-ed73","title":"Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Visualization; Benchmark (surveying); Scalability; Chart; Data visualization; Natural language; Outlier; Key (lock); Code (set theory)","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":[],"consensus_categories":[],"category_scores_codex":[0.005827444,0.004198253,0.001023083,0.003997027,0.001229958,0.004081042,0.004226385,0.00310356,0.01111105],"category_scores_gemma":[0.04965394,0.0007077108,0.002263488,0.003199862,0.001376336,0.005458594,0.004023263,0.002944832,0.006533404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001932344,"about_ca_system_score_gemma":0.002835873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01395593,"about_ca_topic_score_gemma":0.01592199,"domain_scores_codex":[0.9931763,0.002463428,0.0005867503,0.001472066,0.0019752,0.000326271],"domain_scores_gemma":[0.9759912,0.0150948,0.0009072029,0.003740733,0.003404064,0.0008620811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002592168,0.001548202,0.01357564,0.005895183,0.0006042074,0.001081544,0.001723993,0.1157616,0.0152672,0.02290008,0.5181121,0.300938],"study_design_scores_gemma":[0.0006035966,0.0007058839,0.005017764,0.0004603363,0.0001135529,0.0003814849,0.0008425324,0.838939,0.02450541,0.03370814,0.09453665,0.0001855946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.115192,0.004542561,0.2955837,0.00402224,0.001546859,0.0015855,0.09084658,0.4595626,0.02711809],"genre_scores_gemma":[0.3112089,0.001405991,0.4106105,0.001192408,0.0002788052,0.001667565,0.2417621,0.02355224,0.008321541],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01395593,"threshold_uncertainty_score":0.03717017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.049480073981814,"score_gpt":0.3562641713069392,"score_spread":0.3067840973251252,"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."}}