{"id":"W2951455820","doi":"","title":"Online Learning to Rank in Stochastic Click Models","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Learning to rank; Rank (graph theory); Regret; Machine learning; Online learning; Convergence (economics); Artificial intelligence; Range (aeronautics); Class (philosophy); Theoretical computer science; Ranking (information retrieval); Mathematics; 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":[0.008085603,0.001691065,0.003582695,0.00145508,0.0010392,0.002510096,0.002955415,0.00262958,0.004908773],"category_scores_gemma":[0.03015659,0.001008543,0.001221659,0.002266727,0.002442546,0.005657933,0.001953273,0.003128888,0.001504699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002106332,"about_ca_system_score_gemma":0.002019815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006251622,"about_ca_topic_score_gemma":0.007504487,"domain_scores_codex":[0.9953739,0.002275707,0.000215464,0.0008402813,0.0007459357,0.0005487474],"domain_scores_gemma":[0.9734834,0.02152549,0.00179677,0.001599328,0.001023722,0.0005712477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005367937,0.0003255756,0.00285461,0.0003450686,0.00009559991,0.0002037915,0.0001222748,0.7880096,0.0008856006,0.1310596,0.009214957,0.06634647],"study_design_scores_gemma":[0.00002862075,0.00004877425,0.0001809253,0.000009236844,0.000009653384,0.00003701735,0.00001258892,0.9571877,0.0002473913,0.04187647,0.0003496778,0.00001200444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05917595,0.001371398,0.9333305,0.001266218,0.00009339803,0.0001189209,0.0004960888,0.001134524,0.003013096],"genre_scores_gemma":[0.8144631,0.00165807,0.1705179,0.0007524757,0.0005484193,0.000410364,0.001480129,0.0003064914,0.009863093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008085603,"threshold_uncertainty_score":0.04276127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3577127700268318,"score_gpt":0.3531140666372869,"score_spread":0.004598703389544934,"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."}}