{"id":"W4413069729","doi":"10.1007/978-3-031-98414-3_29","title":"Personalizing Explanations of AI-Driven Hints to Users’ Characteristics: An Empirical Evaluation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Empirical research; Human–computer interaction; Information retrieval; Epistemology","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":[0.01516948,0.0009456506,0.0005964093,0.00159731,0.0005742465,0.002531698,0.001912784,0.002443748,0.003774225],"category_scores_gemma":[0.2188943,0.0006298706,0.0007227148,0.001185969,0.0009317358,0.004130232,0.001994083,0.002352167,0.001035778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007948531,"about_ca_system_score_gemma":0.001286087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002187627,"about_ca_topic_score_gemma":0.001549931,"domain_scores_codex":[0.9891194,0.007272877,0.0006550532,0.00109957,0.001619599,0.0002335335],"domain_scores_gemma":[0.5284176,0.4283023,0.01298761,0.02120434,0.00651887,0.002569181],"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":[0.02299174,0.008592276,0.3158577,0.00390625,0.001555487,0.0006312358,0.0355495,0.03369966,0.01439688,0.005822489,0.00595158,0.5510452],"study_design_scores_gemma":[0.005324514,0.02307989,0.3832391,0.001656957,0.005249138,0.00196125,0.01725817,0.4595445,0.04375191,0.03187037,0.02640173,0.0006625247],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9703093,0.0007914989,0.02334999,0.0003372754,0.00003840288,0.0005413529,0.0005304351,0.00196441,0.002137364],"genre_scores_gemma":[0.9771476,0.0002516785,0.02022644,0.0001065209,0.00003029805,0.0002412914,0.0008297306,0.0001724805,0.0009939854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01516948,"threshold_uncertainty_score":0.08022487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06512646958833557,"score_gpt":0.3558005587983916,"score_spread":0.2906740892100561,"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."}}