{"id":"W4405559952","doi":"10.1111/coin.70015","title":"Mining User Study Data to Judge the Merit of a Model for Supporting User‐Specific Explanations of <scp>AI</scp> Systems","year":2024,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Value (mathematics); Computer science; Focus (optics); User modeling; Artificial intelligence; Order (exchange); Machine learning; User interface","routes":{"ca_aff":true,"ca_fund":true,"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":[0.04271891,0.001015313,0.0009040827,0.002888007,0.000877712,0.005551741,0.002054116,0.002566583,0.00216752],"category_scores_gemma":[0.2365386,0.0006004285,0.001114862,0.001506774,0.001393861,0.006137583,0.002014251,0.002174874,0.0003904922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002003015,"about_ca_system_score_gemma":0.001372081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002519617,"about_ca_topic_score_gemma":0.003103582,"domain_scores_codex":[0.9547887,0.03711946,0.002094306,0.001904172,0.00353957,0.0005538499],"domain_scores_gemma":[0.4897999,0.4508721,0.01218802,0.03242873,0.01305043,0.001660681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.009689574,0.0066006,0.5126449,0.003200431,0.001412818,0.0007669426,0.05813121,0.0770528,0.02831546,0.02139434,0.0049001,0.2758909],"study_design_scores_gemma":[0.0005531018,0.004806197,0.08497156,0.0006449983,0.0003850674,0.0004939879,0.01058405,0.8542025,0.01964031,0.01618996,0.00714604,0.0003821973],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8641058,0.00009857127,0.1281488,0.001242908,0.00002585529,0.00157199,0.001024929,0.001501313,0.002279871],"genre_scores_gemma":[0.906165,0.00003183114,0.09221148,0.0001073617,0.000007263092,0.0006496917,0.0006162244,0.00004693595,0.0001642969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04271891,"threshold_uncertainty_score":0.2259219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2099870469706137,"score_gpt":0.3958272314168007,"score_spread":0.185840184446187,"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."}}