{"id":"W4388446603","doi":"10.5206/cjils-rcsib.v46i2.15723","title":"Using folk theories of recommender systems to inform human-centered explainable AI (HCXAI)","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Information and Library Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Recommender system; Computer science; Folk psychology; Psychology; Cognitive science; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.006754439,0.0006349416,0.0004996069,0.002005413,0.001270504,0.004010688,0.00178562,0.001417565,0.005648289],"category_scores_gemma":[0.02446026,0.00038364,0.0009350388,0.001102746,0.005688628,0.006410806,0.002392184,0.00304004,0.0007595399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002814094,"about_ca_system_score_gemma":0.002407567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005660649,"about_ca_topic_score_gemma":0.006140088,"domain_scores_codex":[0.9957566,0.002631453,0.0001486301,0.0005222057,0.0007867281,0.0001544111],"domain_scores_gemma":[0.9736536,0.01896802,0.001552438,0.003284362,0.002130145,0.0004114766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005436998,0.0001030365,0.005603695,0.0002418487,0.0001225195,0.00012906,0.003989113,0.01379369,0.000473462,0.9386519,0.002552771,0.03428447],"study_design_scores_gemma":[0.0000383693,0.0000714007,0.002037172,0.0001460735,0.00006223559,0.0001124643,0.001124456,0.05932395,0.0008942016,0.9169607,0.01918516,0.00004391752],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0679762,0.001838971,0.8397856,0.01742528,0.0002860074,0.0002322945,0.0004153117,0.0004597283,0.07158048],"genre_scores_gemma":[0.819267,0.0008974324,0.1715035,0.001664779,0.0001496501,0.0002719483,0.0004637405,0.00008308314,0.005698805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006754439,"threshold_uncertainty_score":0.03572136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05464557464243531,"score_gpt":0.2907357204093162,"score_spread":0.2360901457668809,"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."}}