{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001959622,0.0003926125,0.0007681781,0.00153982,0.0003533145,0.0003406016,0.004061396,0.0003866181,0.0001854523],"category_scores_gemma":[0.0041886,0.0003993936,0.0002581699,0.001038745,0.000245821,0.0006473802,0.004457309,0.00197972,0.0007139656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004514724,"about_ca_system_score_gemma":0.0003439254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004150115,"about_ca_topic_score_gemma":0.0008108923,"domain_scores_codex":[0.9955888,0.0004325325,0.0005229362,0.002006571,0.0007186888,0.0007304902],"domain_scores_gemma":[0.9952799,0.001017472,0.0004598325,0.002190933,0.000625235,0.0004266052],"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":[0.0001391259,0.0001028622,0.000703137,0.000007225087,0.00001869376,0.000365014,0.0003493969,0.9918748,0.000005112718,0.0007330445,0.0002076545,0.005493996],"study_design_scores_gemma":[0.0006595529,0.00006169849,0.002044474,0.0001162287,0.00001303047,0.000002211864,0.0005580829,0.8280902,0.000004991114,0.1673565,0.000708146,0.0003848462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3627128,0.00005004293,0.634823,0.0001766819,0.0005664622,0.0005204321,0.0000569374,0.00007094208,0.001022694],"genre_scores_gemma":[0.9677402,0.00007363586,0.0007088899,0.00003691301,0.0001440005,0.000002181234,0.00002236212,0.00003653679,0.03123524],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6341141,"threshold_uncertainty_score":0.9998458,"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."}}