{"id":"W2963280733","doi":"","title":"DCM bandits: learning to rank with multiple clicks","year":2016,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Logarithm; Online learning; Matching (statistics); Learning to rank; Rank (graph theory); Web page; Machine learning; Upper and lower bounds; Artificial intelligence; World Wide Web; Mathematics; Ranking (information retrieval); Statistics","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":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001749669,0.0002728642,0.0003221125,0.0007147383,0.0003261057,0.0004355161,0.001384531,0.00008123818,0.007037555],"category_scores_gemma":[0.01183065,0.0001543129,0.00009172624,0.0004633946,0.0001367362,0.0005363576,0.0003415857,0.0007819473,0.004352719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001628089,"about_ca_system_score_gemma":0.0001144623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008716188,"about_ca_topic_score_gemma":0.0001629262,"domain_scores_codex":[0.9948521,0.000421174,0.0005279975,0.0008853778,0.002817408,0.0004959271],"domain_scores_gemma":[0.9952353,0.002719152,0.0002707114,0.0003949841,0.001097372,0.000282472],"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":[0.001866625,0.0001283962,0.2484335,0.00000347655,0.0001089228,0.0001330408,0.001045567,0.04959701,0.009946195,0.005239718,0.0008222334,0.6826753],"study_design_scores_gemma":[0.00767687,0.00306478,0.06647196,0.0005634445,0.0000143922,0.00009714939,0.001890168,0.3196256,0.005362794,0.01147492,0.5823237,0.001434281],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2043674,0.00003381369,0.7331016,0.02202789,0.0007950065,0.000557915,0.00006453379,0.0003546367,0.03869724],"genre_scores_gemma":[0.9591618,0.00002821065,0.002240046,0.0002354624,0.0002477938,0.00004312704,0.00001496627,0.00003552652,0.03799311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7547944,"threshold_uncertainty_score":0.9964931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1116658508648908,"score_gpt":0.4292146443664688,"score_spread":0.3175487935015779,"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."}}