{"id":"W2954365962","doi":"10.48550/arxiv.1806.05819","title":"BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Learning to rank; Computer science; Ranking (information retrieval); Regret; Rank (graph theory); Online learning; Relevance (law); Quality (philosophy); Base (topology); Information retrieval; Machine learning; Artificial intelligence; World Wide Web; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004831026,0.002387753,0.00323998,0.001199822,0.001116631,0.00198603,0.003784451,0.002896758,0.005001928],"category_scores_gemma":[0.02553901,0.0009039316,0.0006702413,0.00171183,0.002093804,0.005418203,0.002114631,0.003053461,0.002901317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001102714,"about_ca_system_score_gemma":0.002514421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003334139,"about_ca_topic_score_gemma":0.004699826,"domain_scores_codex":[0.9964837,0.001580047,0.0001651708,0.000612984,0.000755342,0.0004027934],"domain_scores_gemma":[0.9784749,0.01462384,0.001450145,0.003006245,0.001662711,0.0007821324],"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":[0.001327428,0.0008999298,0.00535843,0.0005511271,0.0001888834,0.0002259958,0.0003390838,0.50712,0.00384939,0.03186651,0.02105532,0.4272179],"study_design_scores_gemma":[0.00009783847,0.0002929675,0.0002483529,0.00003138581,0.00002456116,0.00009410676,0.00003418741,0.9710924,0.001452047,0.02491668,0.001691048,0.00002441201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0441747,0.001383539,0.945343,0.0009343983,0.0001803486,0.0002451408,0.000356379,0.003796851,0.003585651],"genre_scores_gemma":[0.6977338,0.0007442248,0.2876677,0.0009777972,0.0004448674,0.000558854,0.001201105,0.0006800258,0.009991672],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005001928,"threshold_uncertainty_score":0.02554923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.213937048042641,"score_gpt":0.332489253193239,"score_spread":0.118552205150598,"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."}}