{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002554504,0.0009045065,0.001345239,0.0003480233,0.000325462,0.001268254,0.002299123,0.0003874508,0.0001733236],"category_scores_gemma":[0.001566048,0.0007823223,0.0004235672,0.0007689664,0.0002393734,0.002805464,0.004218744,0.001578733,0.000006467271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005965765,"about_ca_system_score_gemma":0.0005882349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003814573,"about_ca_topic_score_gemma":0.0008278696,"domain_scores_codex":[0.9932873,0.0006374626,0.00179974,0.002271265,0.0008608986,0.001143296],"domain_scores_gemma":[0.9915535,0.002507139,0.00204798,0.002517483,0.001113522,0.0002603946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008146544,0.003465777,0.01895413,0.00388244,0.001461225,0.001058128,0.2657428,0.008254628,0.5135249,0.005274665,0.001255229,0.1763113],"study_design_scores_gemma":[0.0002147429,0.0003198369,0.0002912421,0.001831632,0.00003947965,0.0001924871,0.02579887,0.2574035,0.7107095,0.001512823,0.0002770274,0.001408816],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4665614,0.00005936678,0.5300196,0.0005290695,0.0007329318,0.0005310758,0.000005838734,0.0002641089,0.001296595],"genre_scores_gemma":[0.9555755,0.000009848325,0.0434821,0.0002126152,0.0001107748,0.0001147841,0.0000469502,0.00007438694,0.0003730542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.489014,"threshold_uncertainty_score":0.9997685,"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."}}