{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002665408,0.0000684021,0.00009987384,0.0001295232,0.0002594558,0.00003893728,0.0003006952,0.00001843299,0.000212572],"category_scores_gemma":[0.0001962449,0.00007470635,0.00003736441,0.0005511601,0.00002415993,0.0006057757,0.0002670785,0.00009536153,0.00001896991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001688734,"about_ca_system_score_gemma":0.00009344561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001981119,"about_ca_topic_score_gemma":0.00006840994,"domain_scores_codex":[0.9976233,0.0006976085,0.0002343136,0.000246052,0.001047806,0.0001509729],"domain_scores_gemma":[0.9987167,0.0001083671,0.0001313051,0.0002116345,0.0008011431,0.0000308699],"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":[0.000003017954,0.00003300872,0.00001985065,0.000001317623,0.000007425304,9.341558e-7,0.00384196,0.5023574,0.001337529,0.3918963,0.00001835379,0.100483],"study_design_scores_gemma":[0.00007708683,0.0001056548,0.00003212947,0.000002002306,0.00001067977,0.000003303971,0.004001108,0.9192865,0.03812866,0.0381776,0.00009639296,0.00007882905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03960758,0.00007093244,0.9480671,0.0001272029,0.0001358002,0.0002204306,3.743913e-7,0.00009320062,0.01167736],"genre_scores_gemma":[0.9976867,0.000002853013,0.001919956,0.0001517152,0.00001117304,0.00003664524,0.000004295781,0.000006274159,0.0001803882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9580791,"threshold_uncertainty_score":0.3046436,"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."}}