{"id":"W3093958547","doi":"10.1109/mcg.2020.3017064","title":"Challenges in Evaluating Interactive Visual Machine Learning Systems","year":2020,"lang":"en","type":"article","venue":"IEEE Computer Graphics and Applications","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Human–computer interaction; Usability; Artificial intelligence; Machine learning; Multimedia","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":[0.1247216,0.001210477,0.002021047,0.003464022,0.001783956,0.01767728,0.006043181,0.004998427,0.006568013],"category_scores_gemma":[0.3246097,0.0007396441,0.000815966,0.00308129,0.004416755,0.01314613,0.008021501,0.002807378,0.001906968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003995562,"about_ca_system_score_gemma":0.003324694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004355596,"about_ca_topic_score_gemma":0.003282906,"domain_scores_codex":[0.7657915,0.165538,0.01452723,0.005975752,0.04640748,0.001759999],"domain_scores_gemma":[0.6050854,0.3108119,0.009783662,0.02227267,0.04770869,0.004337654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002335486,0.001424197,0.01384822,0.005895747,0.0007605531,0.0002131978,0.008813596,0.03710407,0.00841542,0.05583326,0.02712324,0.8382329],"study_design_scores_gemma":[0.001966175,0.009610008,0.03040866,0.007398929,0.000655883,0.001039536,0.02457125,0.3359666,0.03142375,0.3910249,0.1648398,0.001094495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2134925,0.04294102,0.6172429,0.03637556,0.002595595,0.004058722,0.002517258,0.006061818,0.07471462],"genre_scores_gemma":[0.681914,0.004400553,0.3028863,0.002908409,0.0007759053,0.001769964,0.001477547,0.001100053,0.002767226],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1247216,"threshold_uncertainty_score":0.6595989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09900912250097373,"score_gpt":0.3588387416213695,"score_spread":0.2598296191203958,"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."}}