{"id":"W3042974867","doi":"10.1016/j.artint.2021.103503","title":"Toward personalized XAI: A case study in intelligent tutoring systems","year":2021,"lang":"en","type":"preprint","venue":"Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Personalization; Computer science; Context (archaeology); Constraint (computer-aided design); Perception; Intelligent tutoring system; Value (mathematics); Cognition; Human–computer interaction; World Wide Web; Psychology; Machine learning","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":[0.002910599,0.0003410379,0.000245044,0.0006440943,0.001785535,0.002356882,0.001393143,0.002592177,0.004429883],"category_scores_gemma":[0.01679324,0.0002133124,0.000273019,0.00104234,0.0009211655,0.002631276,0.001792262,0.002036144,0.001016324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009212567,"about_ca_system_score_gemma":0.00070526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001358675,"about_ca_topic_score_gemma":0.002865835,"domain_scores_codex":[0.9973017,0.001763376,0.0001091846,0.0002391412,0.0004203656,0.0001662481],"domain_scores_gemma":[0.9875457,0.009064988,0.0006477464,0.001380168,0.0007644406,0.0005971039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001015536,0.006144486,0.09249783,0.001434239,0.0001705267,0.02906078,0.2161762,0.02612521,0.02592773,0.05117031,0.0174628,0.5328144],"study_design_scores_gemma":[0.0006046565,0.004615218,0.07950113,0.0006476669,0.0004504559,0.04088721,0.125887,0.2494694,0.09057045,0.07011306,0.3369523,0.0003015279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.912858,0.000355086,0.05795131,0.001920264,0.00004112415,0.0003514861,0.0002028,0.001118393,0.0252016],"genre_scores_gemma":[0.9563387,0.0001808209,0.03249899,0.0002103103,0.00002253246,0.0001044632,0.0002195309,0.000157302,0.01026735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004429883,"threshold_uncertainty_score":0.0153929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1953536433642545,"score_gpt":0.3621619238272482,"score_spread":0.1668082804629937,"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."}}