{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001854029,0.0001137424,0.0001999498,0.00008093697,0.0003905824,0.0003652619,0.0006327327,0.0000595517,0.001962967],"category_scores_gemma":[0.002730788,0.000060946,0.0001762753,0.0005985154,0.0001845285,0.0003864371,0.0002844781,0.0001606304,0.0004355044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006629997,"about_ca_system_score_gemma":0.0002017541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000220411,"about_ca_topic_score_gemma":0.0001030107,"domain_scores_codex":[0.9972686,0.0001268918,0.0003854024,0.0005147783,0.001292169,0.0004121857],"domain_scores_gemma":[0.9945515,0.003457463,0.00009437071,0.0004740617,0.001331712,0.00009083645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002456515,0.0001711514,0.0003412243,0.00001193209,0.0001295838,0.00004474338,0.001986615,0.003067192,0.001625461,0.007977441,0.1716906,0.8127084],"study_design_scores_gemma":[0.003128568,0.0002943806,0.002581115,0.00002085924,0.00003249274,0.00007370726,0.01738115,0.2651927,0.02761878,0.05489406,0.6283628,0.0004194427],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009638014,0.0004355109,0.9838049,0.01161729,0.0003366196,0.0005864102,0.00003668659,0.00003674612,0.002182067],"genre_scores_gemma":[0.8166755,0.00007093976,0.07158538,0.000831533,0.0004654852,0.0003678275,0.00002134631,0.00002907501,0.109953],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9122195,"threshold_uncertainty_score":0.9989493,"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."}}