{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001254295,0.0006663236,0.0009175054,0.000374404,0.0003284105,0.0004581174,0.002092491,0.0003408616,0.00007158576],"category_scores_gemma":[0.0006638624,0.0007023893,0.0003707368,0.001161392,0.0002810229,0.002531169,0.002989855,0.001271026,0.000007482054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007099349,"about_ca_system_score_gemma":0.0004332767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001516758,"about_ca_topic_score_gemma":0.0003950539,"domain_scores_codex":[0.995425,0.0005612827,0.0007680572,0.002124518,0.0002636536,0.0008574271],"domain_scores_gemma":[0.994005,0.00141395,0.001499719,0.002015057,0.0008216834,0.0002446019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002326699,0.006111981,0.1264327,0.005422866,0.003637364,0.01170761,0.1947983,0.3064232,0.2296184,0.06470986,0.0009174175,0.04789363],"study_design_scores_gemma":[0.0003910978,0.000313504,0.000266414,0.001370086,0.00009122666,0.00008604097,0.02218999,0.8161675,0.1534844,0.004068528,0.0001519943,0.001419223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5111753,0.00002602285,0.4872549,0.00008596156,0.0003987594,0.0002940186,0.000006876683,0.000147732,0.0006104391],"genre_scores_gemma":[0.9955564,0.00001838692,0.00390756,0.00007367662,0.00005700061,0.000004407258,0.00003055564,0.0000498605,0.0003021298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5097442,"threshold_uncertainty_score":0.9995427,"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."}}