{"id":"W3206556855","doi":"10.1145/3450337.3483487","title":"Explainability via Interactivity? Supporting Nonexperts' Sensemaking of Pretrained CNN by Interacting with Their Daily Surroundings","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interactivity; Sensemaking; Computer science; Human–computer interaction; Artificial intelligence; Computer vision; Computer graphics (images); 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":[0.001615801,0.001135517,0.0002744466,0.000295172,0.0003550216,0.001893973,0.001481882,0.001053578,0.009519005],"category_scores_gemma":[0.01071381,0.0003548701,0.0005777478,0.0001189421,0.001370241,0.003814316,0.002699417,0.001353734,0.001129668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003670454,"about_ca_system_score_gemma":0.0003576132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007380448,"about_ca_topic_score_gemma":0.001576318,"domain_scores_codex":[0.9992008,0.0003988197,0.00002773809,0.000184234,0.0001022908,0.00008612415],"domain_scores_gemma":[0.994866,0.003849456,0.000232262,0.0006950421,0.0001607356,0.0001964876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001502815,0.001195889,0.04170936,0.00201535,0.0002734327,0.003961524,0.08471112,0.04711171,0.2278901,0.07265105,0.01509529,0.5018823],"study_design_scores_gemma":[0.0003070846,0.001299033,0.0239859,0.000811673,0.0003175235,0.002190687,0.01567092,0.4336028,0.1078368,0.2054946,0.2081517,0.0003312892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.432776,0.0003683031,0.5296446,0.002766341,0.00007383954,0.0002509732,0.0002850083,0.008635414,0.02519951],"genre_scores_gemma":[0.8735115,0.0002260635,0.1194844,0.0003053053,0.00002050148,0.0002263302,0.0002849036,0.0004068418,0.005534177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009519005,"threshold_uncertainty_score":0.03184426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05515011285457429,"score_gpt":0.217032444084014,"score_spread":0.1618823312294397,"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."}}