{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002227615,0.0001102667,0.0001486984,0.0001214095,0.0001198969,0.0002166124,0.000332735,0.00003782812,9.715883e-7],"category_scores_gemma":[0.000008784597,0.0001100345,0.00002828991,0.0004606211,0.00002774166,0.000237794,0.0001659366,0.0002004048,0.00001215066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008637624,"about_ca_system_score_gemma":0.00001888154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001376325,"about_ca_topic_score_gemma":0.000008211649,"domain_scores_codex":[0.9989818,0.00009070716,0.0002349526,0.0004005267,0.0001576862,0.0001343199],"domain_scores_gemma":[0.999438,0.0001090195,0.000100841,0.0001656545,0.00008016142,0.0001062689],"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":[0.000003839506,0.0001561029,0.001421719,0.0001137469,0.00003862219,0.000004753044,0.002222776,0.004664305,0.0002995216,0.8352011,0.0001285583,0.1557449],"study_design_scores_gemma":[0.0001904595,0.00008436667,0.0005639763,0.00002283071,0.000004228164,0.000004687571,0.00004984015,0.9887367,0.00002299045,0.0005652086,0.009632185,0.0001225605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002985087,0.0007123456,0.9943066,0.001370299,0.00007427738,0.0002268746,0.000004237381,0.0001225061,0.0001977501],"genre_scores_gemma":[0.9948521,0.001086637,0.003161191,0.0006051789,0.0001943843,0.00006442156,0.00001859079,0.00001017111,0.000007275873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9918671,"threshold_uncertainty_score":0.4487077,"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."}}