{"id":"W2964072175","doi":"10.14288/1.0044651","title":"Online learning under delayed feedback","year":2015,"lang":"en","type":"article","venue":"Open Collections","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Online learning; Multiplicative function; Feedback loop; Adversarial system; Black box; Artificial intelligence; Machine learning; Mathematical optimization; Mathematics; Multimedia","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":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00176153,0.0001117205,0.0002245223,0.0002028761,0.002049636,0.003074542,0.00122102,0.00006772253,0.002663935],"category_scores_gemma":[0.004271632,0.00008916679,0.00005967616,0.00433756,0.0001030542,0.0007159343,0.0007271202,0.0003861082,0.0007976955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00022118,"about_ca_system_score_gemma":0.0004920886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002537008,"about_ca_topic_score_gemma":0.004360516,"domain_scores_codex":[0.9972905,0.0003223597,0.0003770432,0.0004569236,0.001227409,0.0003257967],"domain_scores_gemma":[0.9973278,0.0008312666,0.0001095246,0.0004620732,0.0009614637,0.000307895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001105231,0.0002202831,0.00008127338,2.780211e-7,0.00002781965,0.000009491454,0.0002089375,0.0761482,0.00001607027,0.00005584281,0.9133675,0.009753751],"study_design_scores_gemma":[0.00166986,0.0004090539,0.0007895834,0.000006586667,0.000009094771,0.00005511106,0.01013678,0.04472781,0.0001236703,0.07783684,0.8639784,0.0002572083],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00457761,0.0001249203,0.3452262,0.003317876,0.001208192,0.001144149,0.00009283567,0.0001622712,0.644146],"genre_scores_gemma":[0.02783828,0.00001053245,0.01027042,0.0001321643,0.0001526688,0.00004882641,0.00001533415,0.00002042039,0.9615114],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3349558,"threshold_uncertainty_score":0.9999803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2615616721285479,"score_gpt":0.4801871304299516,"score_spread":0.2186254583014037,"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."}}