{"id":"W3180797935","doi":"10.1145/3450337.3483487","title":"Explainability via Interactivity? Supporting Nonexperts’ Sensemaking of pre-trained CNN by Interacting with Their Daily Surroundings","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sensemaking; Interactivity; Computer science; Convolutional neural network; Leverage (statistics); Artificial intelligence; Human–computer interaction; Data science; 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":[0.001832549,0.00127959,0.0003106256,0.0003403753,0.0003691873,0.002186807,0.001460249,0.001132264,0.0108625],"category_scores_gemma":[0.01249719,0.0003723368,0.0005956151,0.0001305738,0.001521192,0.003975478,0.00280784,0.001311629,0.001438454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003528163,"about_ca_system_score_gemma":0.0003513125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000646531,"about_ca_topic_score_gemma":0.001324506,"domain_scores_codex":[0.9989756,0.0005390751,0.0000340339,0.0002216463,0.0001241478,0.0001055281],"domain_scores_gemma":[0.9931513,0.00527527,0.0002794642,0.0008750426,0.0001935378,0.0002254297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00165367,0.001201241,0.04164954,0.002493238,0.0002709341,0.003840017,0.1192279,0.03216022,0.2425405,0.05940879,0.01486045,0.4806933],"study_design_scores_gemma":[0.0003976827,0.001592149,0.031084,0.00119903,0.0003768369,0.002829764,0.02398462,0.3371631,0.128056,0.1901929,0.2827022,0.0004216804],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4507978,0.0004669394,0.5062684,0.002762784,0.00008257769,0.0002901888,0.0003401579,0.009995815,0.02899523],"genre_scores_gemma":[0.8783242,0.0002637251,0.1137077,0.0003238863,0.00002374957,0.0002687071,0.0003274649,0.0005384986,0.006222174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0108625,"threshold_uncertainty_score":0.03633869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02075778356643372,"score_gpt":0.2931841801396342,"score_spread":0.2724263965732004,"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."}}