{"meta":{"query_hash":"7549d71632e2","filters":{"venue":"European Workshop on Reinforcement Learning"},"cohort_total":1,"direct_labels_cover":0,"predictions_cover":1,"exported":1,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/7549d71632e2","api":"https://metacan.xera.ac/api/v1/cohort?venue=European+Workshop+on+Reinforcement+Learning"},"results":[{"id":"W2136723863","doi":"","title":"An Empirical Analysis of Off-policy Learning in Discrete MDPs","year":2012,"lang":"en","type":"article","venue":"European Workshop on Reinforcement Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Dynamic programming; Variance (accounting); Sampling (signal processing); Population; Mathematical optimization; Monte Carlo method; Policy analysis; Artificial intelligence; Algorithm; Statistics; Mathematics; Economics","score_opus":0.10710063990214132,"score_gpt":0.45902569817125777,"score_spread":0.35192505826911646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136723863","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6798519,0.00028540034,0.2291816,0.00064551714,0.00022418448,0.00048741855,0.0000029888301,0.00022831111,0.08909265],"genre_scores_gemma":[0.98375547,0.00009230338,0.00042329318,0.00017666505,0.0002768363,0.0000064871215,0.000047207763,0.00005123543,0.015170499],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9918799,0.0025580886,0.0013334474,0.0006662299,0.002532211,0.0010301189],"domain_scores_gemma":[0.9960097,0.0018641377,0.0005970396,0.0008874975,0.0002101729,0.00043142255],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009275687,0.0003096567,0.00067250157,0.00330378,0.0002980579,0.0002212232,0.0010782907,0.00007730678,0.0013214846],"category_scores_gemma":[0.008941299,0.0002473272,0.00030103239,0.0070686084,0.00017907869,0.00089239783,0.00045161045,0.0013085512,0.00061089115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009129043,0.00005564754,0.09694895,0.0000021393107,0.00008571392,0.000012793517,0.0025843945,0.78953665,0.000082662715,0.00013403148,0.000085053936,0.11038065],"study_design_scores_gemma":[0.0008099185,0.00044313754,0.25981784,0.00007190767,0.000076443655,0.0000017503515,0.0051645916,0.6482854,0.00012330314,0.000024494351,0.084709324,0.00047189186],"about_ca_topic_score_codex":0.000021565154,"about_ca_topic_score_gemma":0.000009795866,"teacher_disagreement_score":0.30390355,"about_ca_system_score_codex":0.00019218444,"about_ca_system_score_gemma":0.00006764719,"threshold_uncertainty_score":0.9999979},"labels":[],"label_agreement":null}]}