{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001708448,0.0002271456,0.0003428049,0.000360883,0.000237857,0.0004155871,0.003028539,0.00005672059,0.000005175631],"category_scores_gemma":[0.0007796657,0.0001956483,0.00009923457,0.001490397,0.0001161949,0.0009888402,0.000783939,0.0001682994,0.00004303551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006549791,"about_ca_system_score_gemma":0.0003551099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008530843,"about_ca_topic_score_gemma":0.00004600647,"domain_scores_codex":[0.9967116,0.0001233419,0.001189995,0.000831748,0.0007422302,0.0004011488],"domain_scores_gemma":[0.9938873,0.003690514,0.0002854557,0.001132903,0.0008921082,0.0001117355],"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":[0.000003496886,0.0001309212,0.0001097783,0.00006998507,0.00005838561,0.000005562999,0.01134865,0.7403998,0.0002222725,0.2376566,0.004891615,0.005102867],"study_design_scores_gemma":[0.00002853235,0.0001537613,0.00006016812,0.0001309141,0.00002148857,0.000009630559,0.007663341,0.9768471,0.003301108,0.009369201,0.002315124,0.00009967393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02590669,0.0004750637,0.9707506,0.0005601436,0.0006944782,0.001245358,0.000136005,0.000111332,0.0001203776],"genre_scores_gemma":[0.9286919,0.000009906202,0.07053284,0.0001210389,0.00009060289,0.0001581797,0.00004545741,0.00002586045,0.0003241806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9027852,"threshold_uncertainty_score":0.7978306,"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."}}