{"id":"W4415794686","doi":"10.1145/3772071","title":"Designing and Personalising Hybrid Health Explanations for Lay Users","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Interactive Intelligent Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Fonds Wetenschappelijk Onderzoek","keywords":"Modalities; Set (abstract data type); Modality (human–computer interaction); Preference; Coaching; Recommender system; Feature (linguistics); Design science; Preference elicitation","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":[0.007050233,0.001083017,0.0004454878,0.0008935274,0.0006210734,0.002051041,0.001209505,0.002220134,0.00541409],"category_scores_gemma":[0.03641712,0.0005006071,0.001042599,0.0003663038,0.0007616389,0.002928429,0.002739006,0.001173144,0.001646995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004966132,"about_ca_system_score_gemma":0.0008906997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009326733,"about_ca_topic_score_gemma":0.00231805,"domain_scores_codex":[0.9958946,0.002784739,0.0003288203,0.0003917072,0.0004196562,0.0001804402],"domain_scores_gemma":[0.9668947,0.02755952,0.001165345,0.002285653,0.001720339,0.0003745214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00151374,0.001630468,0.07413991,0.007949304,0.0003674835,0.002584947,0.130913,0.008900764,0.04318155,0.01258008,0.01512002,0.7011187],"study_design_scores_gemma":[0.001368423,0.006206438,0.08506525,0.00844864,0.002218007,0.006733845,0.1028191,0.1935601,0.07202356,0.0568983,0.4635601,0.001098226],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4951103,0.001293543,0.479605,0.003106303,0.0001631739,0.00244373,0.0009273906,0.006237002,0.01111338],"genre_scores_gemma":[0.5189564,0.0006857903,0.4708475,0.0005989781,0.00006281408,0.001431211,0.001020661,0.0002904937,0.006106294],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007050233,"threshold_uncertainty_score":0.03728563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0489261400052198,"score_gpt":0.3378237363270465,"score_spread":0.2888975963218268,"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."}}