{"id":"W2888029456","doi":"10.1109/tvcg.2018.2865138","title":"Evaluating ‘Graphical Perception’ with CNNs","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; National Science Foundation","keywords":"Computer science; Visualization; Convolutional neural network; Perception; Task (project management); Artificial intelligence; Visual perception; Data visualization; Human–computer interaction","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002850048,0.0002244736,0.0001802382,0.0004679054,0.0006101022,0.0003893458,0.0003417795,0.0001032466,0.00005587393],"category_scores_gemma":[0.000003263166,0.000196025,0.00006523992,0.001472343,0.0002468467,0.000543711,0.000007927993,0.0001601213,0.00003366081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001878935,"about_ca_system_score_gemma":0.00005897277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009184841,"about_ca_topic_score_gemma":0.00003026148,"domain_scores_codex":[0.998257,0.0001495877,0.000301914,0.0005484245,0.0004955918,0.0002474879],"domain_scores_gemma":[0.9988479,0.00007051558,0.00009647987,0.0004341565,0.000376346,0.0001745801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003305419,0.000380284,0.000199729,0.00002765662,0.00007759252,0.000003868368,0.001923645,0.0003668769,0.00006248805,0.9654107,0.0004043774,0.03110969],"study_design_scores_gemma":[0.0006255798,0.00107362,0.0006982736,0.0000504048,0.00002972104,0.00003233189,0.00003803429,0.9949126,0.0003653194,0.0005894098,0.001302872,0.0002818007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01141581,0.00000564129,0.9874315,0.0001233658,0.0003701877,0.0001600401,0.000007891933,0.0003553526,0.0001302145],"genre_scores_gemma":[0.9822559,0.00009615251,0.01386019,0.003461648,0.0001464809,0.00001536314,0.00001528663,0.00002552094,0.0001234808],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9945458,"threshold_uncertainty_score":0.7993668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.043289634611307,"score_gpt":0.3476999976530299,"score_spread":0.304410363041723,"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."}}