{"id":"W3187572640","doi":"10.24963/ijcai.2021/481","title":"Toward Optimal Solution for the Context-Attentive Bandit Problem","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Thompson sampling; Regret; Computer science; Context (archaeology); Dialog box; Variety (cybernetics); Machine learning; Artificial intelligence; Recommender system; Baseline (sea); Sampling (signal processing); World Wide Web","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":[0.004463718,0.001959388,0.002819533,0.001043348,0.0008479301,0.001729315,0.001971432,0.003246422,0.004244442],"category_scores_gemma":[0.01501287,0.0009011694,0.0009944371,0.001404669,0.001665443,0.002216644,0.001831543,0.003412263,0.001037168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001256138,"about_ca_system_score_gemma":0.002353293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005839764,"about_ca_topic_score_gemma":0.006283155,"domain_scores_codex":[0.9983675,0.0009830414,0.00006995097,0.0002971588,0.0001407752,0.0001415471],"domain_scores_gemma":[0.9886544,0.009971836,0.0004645151,0.0002835997,0.0003922671,0.0002334907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005831044,0.0004277781,0.003049616,0.0004199252,0.0001837508,0.0001488125,0.000303737,0.7955399,0.0009746352,0.05966058,0.009872368,0.1288358],"study_design_scores_gemma":[0.00004270262,0.00004936557,0.0001520066,0.00003353913,0.00001566712,0.00001944868,0.00003343323,0.9715186,0.0001542888,0.02740912,0.000564439,0.000007377623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04028783,0.001869941,0.9511175,0.001404213,0.0001277213,0.0001869862,0.0002077289,0.000467357,0.004330742],"genre_scores_gemma":[0.5944111,0.001215806,0.3965838,0.001290452,0.0003354307,0.0006787952,0.0008309056,0.000255746,0.004397987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005839764,"threshold_uncertainty_score":0.02360666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2170217059857182,"score_gpt":0.4445649393414074,"score_spread":0.2275432333556892,"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."}}