{"id":"W4416125918","doi":"10.48550/arxiv.2504.04221","title":"Evaluating Graphical Perception with Multimodal LLMs","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Task (project management); Perception; Task analysis; Multimodality; Graphical display","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":[0.004282851,0.00173949,0.0007715571,0.001165372,0.0003081227,0.002585729,0.001470983,0.001719115,0.007787825],"category_scores_gemma":[0.03979608,0.0003788027,0.0009010084,0.0006613879,0.0006629843,0.003691078,0.002418941,0.001840602,0.002076723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009465321,"about_ca_system_score_gemma":0.0005794002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003644736,"about_ca_topic_score_gemma":0.003457124,"domain_scores_codex":[0.9975344,0.001212282,0.0001215363,0.0006659481,0.0003472889,0.0001186046],"domain_scores_gemma":[0.9833844,0.01323398,0.0006380785,0.001365857,0.0009534368,0.0004242962],"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":[0.003656644,0.001009104,0.0175846,0.001959765,0.0005692404,0.0004460683,0.001833453,0.2568615,0.04548953,0.006243095,0.01891436,0.6454327],"study_design_scores_gemma":[0.00009270068,0.000911339,0.004756663,0.0001192596,0.00008930552,0.0001285951,0.000500384,0.9658957,0.01425216,0.01003351,0.003136671,0.0000835924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5852388,0.003178726,0.3720326,0.001458708,0.000471881,0.0004091513,0.003314824,0.02356071,0.01033457],"genre_scores_gemma":[0.8998679,0.0004439268,0.09322999,0.0003861372,0.00009006868,0.0001720711,0.003237791,0.000646466,0.001925699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007787825,"threshold_uncertainty_score":0.02605289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09317410924726038,"score_gpt":0.3894718387441124,"score_spread":0.296297729496852,"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."}}