{"id":"W3173206275","doi":"10.1145/3450613.3456814","title":"Bayesian Preference Elicitation with Keyphrase-Item Coembeddings for Interactive Recommendation","year":2021,"lang":"en","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Preference elicitation; Preference; Bayesian probability; Artificial intelligence; Information retrieval; Natural language processing; Machine learning; Statistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001842674,0.0001140146,0.0001398172,0.00007085554,0.0001047897,0.0002498766,0.0002166025,0.00004403971,0.00004370485],"category_scores_gemma":[0.00004892979,0.00009166168,0.00003882602,0.0002397863,0.000008328372,0.0008972054,0.00007007237,0.00007090128,0.000005207387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006225158,"about_ca_system_score_gemma":0.00005814611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000583612,"about_ca_topic_score_gemma":0.00009214187,"domain_scores_codex":[0.999099,0.00006195133,0.0002063257,0.0003672129,0.0001039668,0.0001615685],"domain_scores_gemma":[0.9989848,0.0002732121,0.0001239809,0.0002593626,0.0003065545,0.000052156],"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":[0.00007209655,0.0002840215,0.002040955,0.0001414233,0.0001443434,0.00001049061,0.005052015,0.00001345123,0.004941626,0.2534074,0.03241425,0.7014779],"study_design_scores_gemma":[0.001952274,0.001198316,0.002781793,0.0004202538,0.0000319227,0.000168414,0.001748644,0.4526092,0.3354498,0.03243703,0.1701172,0.001085149],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001450946,0.000006793886,0.9799279,0.002546035,0.0001607185,0.000314756,0.000003446359,0.0002669183,0.01532249],"genre_scores_gemma":[0.7263831,0.000005712272,0.2721896,0.0004914036,0.00003065124,0.0001410091,0.00003362465,0.000008436124,0.0007164457],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7249323,"threshold_uncertainty_score":0.3737855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03441191552746346,"score_gpt":0.2826170399557813,"score_spread":0.2482051244283179,"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."}}