{"id":"W2965415665","doi":"10.24963/ijcai.2019/532","title":"Learning Multi-Objective Rewards and User Utility Function in Contextual Bandits for Personalized Ranking","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National University of Singapore","keywords":"Computer science; Ranking (information retrieval); Weighting; Context (archaeology); Function (biology); Machine learning; Artificial intelligence; Learning to rank","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004191521,0.000143375,0.0003525015,0.0003140165,0.0001704497,0.0001614024,0.0002095467,0.0001051125,0.001106193],"category_scores_gemma":[0.00549784,0.0001051424,0.00008558483,0.0004914557,0.0001353287,0.0006346368,0.0001295496,0.0003128595,0.000116329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008149256,"about_ca_system_score_gemma":0.00007791881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009366166,"about_ca_topic_score_gemma":0.0002756389,"domain_scores_codex":[0.9972513,0.0003278431,0.000399301,0.0007073563,0.0009401119,0.000374032],"domain_scores_gemma":[0.9959046,0.003188208,0.0001102859,0.0002314184,0.0004791674,0.00008636479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005621303,0.0002448171,0.6013199,0.00004834024,0.00008623531,0.000009798107,0.008281542,0.002306503,0.002793766,0.001408143,0.001483063,0.3763966],"study_design_scores_gemma":[0.01587873,0.0009047494,0.5199004,0.00005110045,0.00001181477,0.000009450328,0.02468638,0.3617764,0.0009923842,0.006410463,0.06888463,0.0004935768],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4925495,0.0001438785,0.5050118,0.0001282363,0.0002595885,0.0009568511,0.000009389687,0.00004439129,0.0008963611],"genre_scores_gemma":[0.9679478,0.000009064954,0.003261505,0.0000553484,0.00004412691,0.00004581886,0.000004833355,0.00001370798,0.0286178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5017503,"threshold_uncertainty_score":0.9998069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1100089455721881,"score_gpt":0.4211775392848835,"score_spread":0.3111685937126954,"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."}}