{"id":"W4317826891","doi":"10.1109/iv56949.2022.00066","title":"Evaluation of Deep Learning Context-Sensitive Visualization Models","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Visualization; Artificial intelligence; Machine learning; Classifier (UML); Debugging; Natural language processing; Artificial neural network; Context (archaeology); Quality (philosophy); Creative visualization; Transformer","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":[0.005336491,0.001886704,0.001236506,0.002126092,0.0003619522,0.001860895,0.001718478,0.001840161,0.002276389],"category_scores_gemma":[0.02177922,0.0004709781,0.001241913,0.001095983,0.0006062081,0.001718764,0.001528122,0.001603128,0.0003038116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002239191,"about_ca_system_score_gemma":0.0008838325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008375434,"about_ca_topic_score_gemma":0.005990176,"domain_scores_codex":[0.9977704,0.00111503,0.0001765972,0.000329709,0.0004751036,0.0001332081],"domain_scores_gemma":[0.9845995,0.01132718,0.0007968485,0.001064387,0.00181376,0.000398244],"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":[0.0007985421,0.0002174181,0.004165639,0.000372697,0.00026294,0.0001310801,0.000124449,0.8866568,0.002650413,0.002374234,0.002293146,0.09995266],"study_design_scores_gemma":[0.00001609042,0.00007450187,0.0003150048,0.00001851197,0.00001547974,0.00001184058,0.00001301709,0.9970015,0.001329385,0.001034571,0.0001635119,0.000006557474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6057322,0.005958335,0.3648114,0.002160513,0.0004801978,0.0002823745,0.002605463,0.01227239,0.005697141],"genre_scores_gemma":[0.929225,0.0005662263,0.06686576,0.0001175677,0.00004245445,0.00009476732,0.001735407,0.0001937532,0.001159033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008375434,"threshold_uncertainty_score":0.02822238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07864008344659594,"score_gpt":0.329978200570619,"score_spread":0.251338117124023,"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."}}