{"id":"W3208693767","doi":"10.1007/978-3-030-88900-5_27","title":"Explainable Artificial Intelligence (XAI): How the Visualization of AI Predictions Affects User Cognitive Load and Confidence","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in information systems and organisation","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"CLARITY; Computer science; Visualization; Transparency (behavior); Artificial intelligence; Cognitive load; Cognition; Presentation (obstetrics); Psychology","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":[0.000530981,0.0004836447,0.0002221292,0.0003579077,0.0002488856,0.002337195,0.0005633131,0.0007249733,0.01637359],"category_scores_gemma":[0.01058108,0.0002779093,0.0002461035,0.000616328,0.0003596345,0.002867599,0.0006958363,0.001010987,0.001410306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003273058,"about_ca_system_score_gemma":0.0002113605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002047399,"about_ca_topic_score_gemma":0.002027472,"domain_scores_codex":[0.9998183,0.00007100543,0.000006822078,0.00003787188,0.00005444784,0.00001160414],"domain_scores_gemma":[0.9949006,0.00451752,0.0002149672,0.0001806706,0.0001331621,0.00005296075],"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":[0.001133529,0.0003568331,0.03130464,0.001099199,0.0002024272,0.0004136955,0.01025916,0.02971135,0.03581363,0.07055815,0.06137762,0.7577698],"study_design_scores_gemma":[0.0001726605,0.0005992151,0.1153769,0.000410958,0.0003497722,0.001026376,0.002975826,0.5413193,0.03615666,0.2518587,0.04947475,0.0002790146],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5656009,0.004020434,0.3046393,0.006169814,0.0006497165,0.0002058033,0.004135318,0.01297145,0.1016072],"genre_scores_gemma":[0.9126315,0.0008938939,0.0708351,0.0002468755,0.00007116533,0.0001193829,0.001298619,0.0008997178,0.01300388],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01637359,"threshold_uncertainty_score":0.05477518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02349838693404572,"score_gpt":0.2561526430772192,"score_spread":0.2326542561431735,"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."}}