{"id":"W2161790782","doi":"10.1145/1553374.1553500","title":"A simpler unified analysis of budget perceptrons","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Perceptron; Computer science; Regret; Mathematical proof; Regularization (linguistics); Algorithm; Set (abstract data type); Mathematical optimization; Artificial intelligence; Machine learning; Artificial neural network; Mathematics","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":[],"category_scores_codex":[0.001285614,0.00009376489,0.0004065508,0.001216572,0.00007051712,0.00006842587,0.0007360253,0.0000505974,0.009032915],"category_scores_gemma":[0.001564797,0.00006047092,0.0002527774,0.005388065,0.0001051394,0.0002295202,0.00007700755,0.0001070899,0.0002321536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002875723,"about_ca_system_score_gemma":0.00005294759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004025306,"about_ca_topic_score_gemma":0.000130052,"domain_scores_codex":[0.9970044,0.0001181936,0.0005126979,0.000377429,0.001700027,0.0002872888],"domain_scores_gemma":[0.9975969,0.0008955306,0.0001052106,0.0007841488,0.0004902466,0.0001279421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002400832,0.0008078318,0.02522278,0.000002774574,0.001105833,0.00004445673,0.002905073,0.08370818,0.01335458,0.01472272,0.056398,0.8014877],"study_design_scores_gemma":[0.000595355,0.0003350052,0.7732027,0.00000210007,0.0002042977,0.000002305641,0.002757441,0.1472187,0.002366317,0.05210702,0.02090524,0.0003035578],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3309022,0.00005833373,0.6146734,0.002926566,0.00007422112,0.0002478985,0.00005450557,0.00008108461,0.05098185],"genre_scores_gemma":[0.9819496,0.000006872507,0.005604958,0.0001910755,0.00002058739,0.000001558734,0.000006252415,0.000003345981,0.01221575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8011841,"threshold_uncertainty_score":0.991873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1343045785337509,"score_gpt":0.4873831615531908,"score_spread":0.3530785830194398,"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."}}