{"id":"W2803847628","doi":"10.48550/arxiv.1805.09247","title":"Cleaning up the neighborhood: A full classification for adversarial partial monitoring","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Generalization; Adversarial system; Bartok; Computer science; Class (philosophy); Mathematical optimization; Artificial intelligence; Algorithm; Mathematics; Mathematical economics; Machine learning","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"],"consensus_categories":[],"category_scores_codex":[0.002464359,0.0003457397,0.0004278135,0.0003817323,0.0007898191,0.0004355881,0.002942719,0.0003979919,0.0002121418],"category_scores_gemma":[0.002609676,0.0002771618,0.0004042057,0.0009619076,0.0004659094,0.0005036368,0.001687075,0.0008240693,0.00036904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003923934,"about_ca_system_score_gemma":0.0003985415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004289521,"about_ca_topic_score_gemma":0.00002595828,"domain_scores_codex":[0.9961334,0.0004050957,0.0005227861,0.001630715,0.0006656161,0.0006423753],"domain_scores_gemma":[0.994023,0.002151021,0.0006403581,0.001821617,0.001148604,0.0002153761],"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":[0.008352321,0.0004997191,0.02832846,0.0001492564,0.0009550865,0.0002110801,0.00545188,0.7765324,0.001423602,0.06813061,0.02209764,0.08786791],"study_design_scores_gemma":[0.001313251,0.0001828262,0.002708856,0.0000637246,0.0001051861,0.000002761912,0.00268933,0.8471181,0.0005847932,0.1336237,0.01111186,0.000495594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1077033,0.00003699908,0.8846433,0.0002626145,0.005124665,0.001029869,0.00007740181,0.0001174554,0.001004429],"genre_scores_gemma":[0.9927552,0.00005518179,0.0007431131,0.00001672305,0.002454243,0.00001145161,0.00001854056,0.00003775954,0.003907746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.885052,"threshold_uncertainty_score":0.9999681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4156347707665758,"score_gpt":0.3521115529404013,"score_spread":0.06352321782617454,"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."}}