{"id":"W2160262323","doi":"10.48550/arxiv.1306.0686","title":"Online Learning under Delayed Feedback","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Online learning; Computer science; Multiplicative function; Feedback loop; Adversarial system; Black box; Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Multimedia; 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","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001161037,0.0004683167,0.0006747337,0.0008515182,0.0003629069,0.0004025077,0.00302583,0.0005488508,0.002779069],"category_scores_gemma":[0.001318589,0.0004395983,0.0003945129,0.001589082,0.0004126684,0.0005999074,0.003812285,0.002314588,0.004572197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004297769,"about_ca_system_score_gemma":0.0003152406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003576146,"about_ca_topic_score_gemma":0.0001697653,"domain_scores_codex":[0.9952468,0.0006225114,0.0005621913,0.001998376,0.0008070497,0.0007630747],"domain_scores_gemma":[0.9946808,0.001415909,0.0005546564,0.001734921,0.001174759,0.000439002],"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":[0.0000772049,0.0001432017,0.001423102,0.00001013381,0.00009833108,0.0001862216,0.00009993387,0.9889729,0.00002158156,0.002417061,0.002110294,0.004440012],"study_design_scores_gemma":[0.000825723,0.0001180577,0.008844144,0.00005216018,0.00005066118,0.000007461848,0.002066765,0.7034653,0.00005016324,0.2756966,0.008094645,0.0007282364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6101391,0.0001029533,0.3862461,0.000223971,0.000549491,0.0004047108,0.00006052287,0.0001834935,0.002089592],"genre_scores_gemma":[0.9263175,0.0002506448,0.001183456,0.00008164066,0.0002237714,0.0000012885,0.00007635786,0.00004925134,0.07181609],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3850627,"threshold_uncertainty_score":0.9999871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2569419831242067,"score_gpt":0.3170267194651759,"score_spread":0.06008473634096922,"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."}}