{"id":"W2293140407","doi":"10.1145/1993636.1993666","title":"Dueling algorithms","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Computer science; Mathematical optimization; Binary search algorithm; Algorithm; Ranking (information retrieval); Binary number; Mathematics; Search algorithm; Artificial intelligence","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":["insufficient_payload"],"category_scores_codex":[0.001863484,0.00009220904,0.000157009,0.000260658,0.0001235534,0.00009309182,0.0008958341,0.000048481,0.01290426],"category_scores_gemma":[0.001845528,0.0000588093,0.00007492071,0.0007880225,0.0001093092,0.0004485145,0.0002245704,0.0001453649,0.006329103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000211404,"about_ca_system_score_gemma":0.00004163397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000570406,"about_ca_topic_score_gemma":0.00001601653,"domain_scores_codex":[0.9973026,0.00007737599,0.0003767482,0.000419128,0.001476444,0.0003477006],"domain_scores_gemma":[0.9983173,0.0004730071,0.00006163311,0.000611359,0.0003731837,0.0001635071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003436072,0.0001174297,0.003846108,0.000001238015,0.00001575109,0.0001000902,0.001331736,0.0001045132,0.0002407838,0.004015279,0.0112761,0.9789166],"study_design_scores_gemma":[0.001129669,0.0003120866,0.03213299,0.0000101034,0.000006975937,0.0000814372,0.00475674,0.07841907,0.03918976,0.709062,0.1341474,0.0007517415],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00461645,0.00007139317,0.8376883,0.0001423064,0.0003791153,0.0001202074,0.000002832968,0.00011088,0.1568685],"genre_scores_gemma":[0.6724693,0.00002023058,0.2658251,0.0003046606,0.0002566107,0.00002033805,0.000001147648,0.00002626688,0.06107634],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9781649,"threshold_uncertainty_score":0.9944446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5436472135121365,"score_gpt":0.4912489599546517,"score_spread":0.05239825355748484,"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."}}