{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":436,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":436,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"a2addb5837d6","filters":{"topic":"Advanced Bandit Algorithms Research"}},"results":[{"id":"W2192203593","doi":"10.1109/jproc.2015.2494218","title":"Taking the Human Out of the Loop: A Review of Bayesian Optimization","year":2015,"lang":"en","type":"review","venue":"Proceedings of the IEEE","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5868,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Bayesian optimization; Loop (graph theory); Bayesian probability; Human-in-the-loop; Computer science; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2723421006942705,"gpt":0.4942171047619189,"spread":0.2218750040676484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.008354706,0.0003408393,0.001900953,0.0002112437,0.0002248002,0.00008071012,0.006457658,0.0001797685,0.0001435356],"category_scores_gemma":[0.01035051,0.0001288745,0.0009367475,0.002380195,0.0006797542,0.0002706755,0.0009587722,0.0006325917,0.000009534857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001173682,"about_ca_system_score_gemma":0.0003961449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001254713,"about_ca_topic_score_gemma":0.000002526982,"domain_scores_codex":[0.9932911,0.0001855382,0.002002495,0.0004917643,0.003717652,0.000311433],"domain_scores_gemma":[0.9892479,0.0006891713,0.005971641,0.0009777179,0.003046168,0.00006741074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007040569,0.00008676783,0.00002927449,0.05695901,0.0001541489,2.427414e-7,0.0004911663,0.0002727263,0.0000246782,0.0003744079,0.02156592,0.9200346],"study_design_scores_gemma":[0.0002622007,0.00009828569,0.00001172081,0.1842074,0.0008498965,0.00002671864,0.0002774597,0.0008627038,0.0004408007,0.00602986,0.8065073,0.0004256644],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003770679,0.9920694,0.0008349728,0.0003618014,0.0005098327,0.002071152,0.00003919725,0.00001069166,0.004099198],"genre_scores_gemma":[0.00009756815,0.9967065,0.0008970113,0.00004811194,0.0001807573,0.0000730531,0.000001222546,0.00004568539,0.001950098],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.919609,"threshold_uncertainty_score":0.9989179,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119738618","doi":"","title":"Improved Algorithms for Linear Stochastic Bandits","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":916,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Logarithm; Computer science; Constant (computer programming); Simple (philosophy); Algorithm; Mathematical optimization; Multi-armed bandit; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.3179026584292263,"gpt":0.4621502314159748,"spread":0.1442475729867485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001932964,0.0001809425,0.0003070276,0.0003181619,0.0002098499,0.00008932203,0.001040187,0.0001025172,0.002551286],"category_scores_gemma":[0.004526408,0.0001198385,0.0001614839,0.0006372106,0.0001600539,0.0004457079,0.0002048121,0.0001665843,0.000764601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003965834,"about_ca_system_score_gemma":0.000109089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004168634,"about_ca_topic_score_gemma":0.00002456806,"domain_scores_codex":[0.9970291,0.00006059357,0.0005644316,0.00068245,0.0010678,0.0005955708],"domain_scores_gemma":[0.9966971,0.001339869,0.000131581,0.0007262835,0.0008402856,0.0002649202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000953062,0.0007006625,0.000228387,0.00002160733,0.0001360175,0.00003247132,0.00264001,0.001536715,0.002509969,0.003806965,0.02698158,0.9604526],"study_design_scores_gemma":[0.002185194,0.0008867707,0.001163585,0.000008604841,0.00001447417,0.00001868349,0.0007438004,0.8639171,0.01231539,0.1043812,0.01384855,0.0005166981],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000894949,0.00003705011,0.9950824,0.000125253,0.0005562847,0.0006984963,0.00004483985,0.00009861482,0.002462146],"genre_scores_gemma":[0.4156465,0.000006764012,0.5122555,0.0003400656,0.0009702462,0.0004079075,0.00001623683,0.00008791894,0.07026884],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9599358,"threshold_uncertainty_score":0.9983605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206530644","doi":"10.1017/9781108571401","title":"Bandit Algorithms","year":2020,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":851,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Markov decision process; Intuition; Mathematical proof; Bayesian probability; Thompson sampling; Artificial intelligence; Focus (optics); Machine learning; Operations research; Markov process; Management science; Mathematical optimization; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1148289934412215,"gpt":0.330816909380413,"spread":0.2159879159391914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007940043,0.0006261509,0.001065312,0.0006843009,0.0004369043,0.0003726521,0.003900326,0.0006348997,0.0000718549],"category_scores_gemma":[0.0007352409,0.0006188633,0.000571006,0.0001445475,0.0007126711,0.0003537022,0.002102896,0.001548109,0.0009731679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007459811,"about_ca_system_score_gemma":0.001125805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004031886,"about_ca_topic_score_gemma":0.000001711019,"domain_scores_codex":[0.993063,0.0003477292,0.0006209292,0.001768891,0.003438138,0.0007612815],"domain_scores_gemma":[0.9947739,0.001312921,0.000555442,0.001678719,0.0009078553,0.000771136],"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":[0.0001194607,0.00001455856,0.00000114239,0.00002822916,0.0001113799,0.001772307,0.00006649935,0.00003620432,0.000009526237,0.04197409,0.9389485,0.01691807],"study_design_scores_gemma":[0.0007876003,0.0001133456,0.00001276388,0.00005410996,0.00007220427,0.00002602051,0.00009302978,0.001790579,0.000206267,0.0001716167,0.9960379,0.0006345817],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000003580173,0.0002097513,0.03946491,0.0001286426,0.0006729875,0.0006799015,0.00109216,0.0002435723,0.9575045],"genre_scores_gemma":[0.00003275026,0.00007456076,0.0008754599,0.0001433426,0.0008358354,0.000001964183,0.0001150282,0.00008492787,0.9978361],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.05708935,"threshold_uncertainty_score":0.9998047,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1931877416","doi":"10.1184/r1/6550949","title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":846,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; Multidisciplinary University Research Initiative","keywords":"Regret; Computer science; Benchmark (surveying); Artificial intelligence; Imitation; Online learning; Reduction (mathematics); Machine learning; Sequence (biology); Iterative learning control; Online machine learning; Convergence (economics); Mathematical optimization; Active learning (machine learning); Mathematics; Economics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1356271737258775,"gpt":0.3110003567384468,"spread":0.1753731830125693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001146912,0.0002510058,0.0004221514,0.000979949,0.0002589669,0.0001113269,0.0005688624,0.0004190466,0.0001615473],"category_scores_gemma":[0.004130423,0.0002521154,0.0001240779,0.001057128,0.0002310599,0.0004001057,0.0009298501,0.001896592,0.00004660359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001422417,"about_ca_system_score_gemma":0.0001333641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009616858,"about_ca_topic_score_gemma":0.00008528208,"domain_scores_codex":[0.9971559,0.000413093,0.0004441627,0.001169287,0.0005269282,0.000290612],"domain_scores_gemma":[0.9968894,0.0004551426,0.0005744551,0.000505413,0.001358108,0.000217525],"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":[0.0003146637,0.00004727169,0.01092806,0.00003954491,0.00004765552,0.00001902941,0.0007753959,0.9585677,0.007031327,0.0002532856,0.0001047667,0.02187133],"study_design_scores_gemma":[0.001112026,0.0006025998,0.04346682,0.0001723432,0.00009221758,0.00002064048,0.004289613,0.9085107,0.001662961,0.03491992,0.004577286,0.0005728782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8585063,0.00002566303,0.1400253,0.00005738841,0.000680681,0.0003696202,0.00005654406,0.00008003973,0.0001984492],"genre_scores_gemma":[0.9903265,0.0001255512,0.003572705,0.000003730981,0.0002259719,0.000001059176,0.00008803107,0.00002383633,0.005632589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1364526,"threshold_uncertainty_score":0.9999931,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073384958","doi":"10.1007/978-3-031-01551-9","title":"Algorithms for Reinforcement Learning","year":2010,"lang":"en","type":"book","venue":"Synthesis lectures on artificial intelligence and machine learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":750,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Learning classifier system; Hyper-heuristic; Instance-based learning; Active learning (machine learning); Term (time); Unsupervised learning; Core (optical fiber); Robot learning; Robot","retraction":null,"screen_n_in":null,"score":{"opus":0.1604075222470484,"gpt":0.4127314576545998,"spread":0.2523239354075514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004555956,0.0007870023,0.001126881,0.00121853,0.001457514,0.0008893858,0.001212902,0.0008103002,0.002728669],"category_scores_gemma":[0.03027448,0.0006092855,0.0004740034,0.0003885282,0.0004870007,0.0002215203,0.0003676066,0.004151944,0.0008933957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000172805,"about_ca_system_score_gemma":0.0003446728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005377089,"about_ca_topic_score_gemma":0.0002053225,"domain_scores_codex":[0.9931322,0.0004202843,0.001442199,0.001675491,0.00235286,0.0009770135],"domain_scores_gemma":[0.9839671,0.01348529,0.0008395881,0.0007374529,0.0006279221,0.0003426232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002635195,0.0000316598,0.00000569363,0.0000336499,0.00006838303,0.00001612743,0.0003673072,0.1156893,0.0002184405,0.003485348,0.001245341,0.8785752],"study_design_scores_gemma":[0.00005206037,0.0007606797,0.000004463859,0.0001625652,0.00006149846,0.00001438454,0.0002104228,0.1951062,0.01613816,0.1602779,0.6264191,0.0007924819],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00005680025,0.0008677423,0.9364544,0.001363987,0.001074617,0.001608481,0.00005046165,0.0002805956,0.05824294],"genre_scores_gemma":[0.06788354,0.0009999631,0.006355473,0.0005108693,0.003023016,0.000502524,0.0001883981,0.0003712871,0.9201649],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9300989,"threshold_uncertainty_score":0.9998845,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142971854","doi":"10.1016/j.tcs.2009.01.016","title":"Exploration–exploitation tradeoff using variance estimates in multi-armed bandits","year":2009,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":566,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Variance (accounting); Stochastic game; Upper and lower bounds; Logarithm; Mathematical optimization; Computer science; Multi-armed bandit; Interval (graph theory); Mathematics; Mathematical economics; Machine learning; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.2025090972907981,"gpt":0.4631392662511002,"spread":0.2606301689603022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004961226,0.0001914336,0.0003035006,0.0006995567,0.000421003,0.0007090758,0.001706918,0.00006412726,0.0001115561],"category_scores_gemma":[0.003552325,0.0001460072,0.00005309462,0.0037928,0.00208444,0.002605985,0.0002164279,0.0002780382,0.0001256053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001589192,"about_ca_system_score_gemma":0.0001891846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003252734,"about_ca_topic_score_gemma":0.000002405841,"domain_scores_codex":[0.9950902,0.0002316002,0.0006439523,0.0009440239,0.002380779,0.0007093957],"domain_scores_gemma":[0.9970365,0.001455825,0.0001241576,0.000624703,0.0004865764,0.0002722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001266582,0.0005823241,0.0006630308,0.000005642567,0.000003935347,0.0001123606,0.004644006,0.2623552,0.01075951,0.4575307,0.00007088121,0.2631457],"study_design_scores_gemma":[0.0003203843,0.0001068653,0.006729311,0.00001971784,0.000001105849,0.00001022147,0.00005283072,0.6571352,0.002933874,0.3325493,0.00001185038,0.0001293375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05795958,0.00002653591,0.9399899,0.001227842,0.0003182754,0.000268552,0.000002364089,0.00006324568,0.0001436943],"genre_scores_gemma":[0.7182841,0.000002867622,0.281456,0.0001675178,0.00006754688,0.000004698677,7.909129e-7,0.00000566004,0.00001083677],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6603246,"threshold_uncertainty_score":0.7680205,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160163723","doi":"","title":"Parametric Bandits: The Generalized Linear Case","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":261,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Parameterized complexity; Generalized linear model; Parametric statistics; Computer science; Mathematical optimization; Linear model; Applied mathematics; Mathematics; Algorithm; Machine learning; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1076079387823779,"gpt":0.4263062865630172,"spread":0.3186983477806393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003246237,0.0001779939,0.0002566251,0.0005631961,0.0008733105,0.002153674,0.0008540953,0.0001304333,0.00009173872],"category_scores_gemma":[0.005069297,0.00009459903,0.00007962906,0.002472267,0.0001825837,0.004402479,0.0001226237,0.0006314017,0.0006446071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003561412,"about_ca_system_score_gemma":0.0001355263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134124,"about_ca_topic_score_gemma":0.00002064283,"domain_scores_codex":[0.9960746,0.0001934967,0.001139695,0.0002315069,0.001972346,0.0003883459],"domain_scores_gemma":[0.9964095,0.0008644827,0.0006324826,0.0006480583,0.001291725,0.0001537166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001056898,0.00006157581,0.001311525,0.0001640537,0.00002478456,0.0002097258,0.00368672,0.1124968,0.0004732816,0.00131327,0.0204496,0.8597029],"study_design_scores_gemma":[0.0004229725,0.00003182846,0.0001848757,0.000009490534,0.000004553628,0.002480609,0.001724589,0.8686839,0.0002440734,0.0002895885,0.1257678,0.0001557158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8072849,0.0005909152,0.17741,0.002383584,0.005350001,0.001879979,0.00007737861,0.0004591566,0.00456406],"genre_scores_gemma":[0.9973146,0.000003452257,0.0008132784,0.0002541494,0.0004370875,0.0000809413,0.00001203165,0.00001079966,0.001073675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8595473,"threshold_uncertainty_score":0.9988822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W53582479","doi":"","title":"Regret Bounds for the Adaptive Control of Linear Quadratic Systems","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":213,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Logarithm; Mathematical optimization; Set (abstract data type); Upper and lower bounds; Quadratic equation; Mathematics; Control (management); Computer science; Control theory (sociology); Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.3701429153791539,"gpt":0.4472209630766811,"spread":0.07707804769752713,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00329828,0.0001020105,0.0003103545,0.0001234366,0.000190773,0.00006244148,0.0009281397,0.0000564144,0.0003091141],"category_scores_gemma":[0.003291918,0.00004685808,0.0001237539,0.000422869,0.000301351,0.0002279489,0.00006569282,0.0001071442,0.0001256406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002379672,"about_ca_system_score_gemma":0.0001083451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000214276,"about_ca_topic_score_gemma":0.00005857934,"domain_scores_codex":[0.9975359,0.000172002,0.0005657709,0.000285234,0.001167683,0.0002733596],"domain_scores_gemma":[0.9920534,0.005938163,0.0002237875,0.0006937771,0.001016014,0.00007483819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009356047,0.001448039,0.007775884,0.0001831925,0.00176015,0.0000634773,0.02614845,0.0299595,0.002040209,0.5137246,0.09751157,0.3100289],"study_design_scores_gemma":[0.001463844,0.0007969422,0.0009889356,0.00001739383,0.00002475986,0.000005447127,0.008943573,0.9409765,0.001705113,0.02884296,0.01607778,0.0001567723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005894133,0.0006153731,0.9937804,0.0001824531,0.0003398384,0.0009209413,0.00004497142,0.00001960849,0.00350694],"genre_scores_gemma":[0.9834533,0.00001093884,0.006611512,0.00004592372,0.0001133072,0.0001228663,5.116194e-7,0.00001115367,0.009630441],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.987169,"threshold_uncertainty_score":0.3940971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160367301","doi":"10.1145/1566374.1566412","title":"A unified framework for dynamic pari-mutuel information market design","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":167,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"","keywords":"Mathematical optimization; Computer science; Function (biology); Logarithm; Popularity; Convex optimization; Mechanism design; Simple (philosophy); Regular polygon; Minification; Mathematical economics; Economics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1202788275421259,"gpt":0.4558329411854775,"spread":0.3355541136433516,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003091712,0.0001359452,0.0002161327,0.0003802234,0.0002059537,0.0004305541,0.0007705916,0.0001416111,0.001023934],"category_scores_gemma":[0.008901502,0.00009541857,0.00009196555,0.0009170771,0.00005646203,0.001490715,0.00005687082,0.0001950385,0.0005228415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008518975,"about_ca_system_score_gemma":0.0001067792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002403374,"about_ca_topic_score_gemma":0.000003486352,"domain_scores_codex":[0.9973059,0.0001315146,0.000571568,0.0002769757,0.001295135,0.000418941],"domain_scores_gemma":[0.9948184,0.003744561,0.000158339,0.0005905642,0.0005499605,0.0001381929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004754613,0.00006133218,0.00003170898,0.00000459771,0.00001142933,0.000002631,0.0003141823,0.00445922,0.00003911901,0.0265171,0.05252013,0.9155631],"study_design_scores_gemma":[0.0003686453,0.0002040604,0.003056505,0.000007062315,0.000002339928,0.000002917549,0.0003418816,0.2995306,0.0001894592,0.6731281,0.02303676,0.0001316259],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001969065,0.00002451957,0.9907419,0.002225257,0.0001622417,0.0007330949,0.00001254993,0.00009061967,0.005812913],"genre_scores_gemma":[0.2446742,0.00002279216,0.7464706,0.001137274,0.00005905548,0.00006035661,0.00001180647,0.000009143057,0.007554787],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9154314,"threshold_uncertainty_score":0.9998893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1917528016","doi":"","title":"Contextual Multi-Armed Bandits","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Regret; Stochastic game; Multi-armed bandit; Context (archaeology); Metric space; Metric (unit); Computer science; Space (punctuation); Lipschitz continuity; Action (physics); Mathematics; Thompson sampling; Function (biology); Theoretical computer science; Mathematical optimization; Combinatorics; Discrete mathematics; Mathematical economics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.2128862204345478,"gpt":0.5039623446227086,"spread":0.2910761241881608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001967878,0.0001202634,0.0002078895,0.0002449387,0.0001729309,0.0002368206,0.001020035,0.0001000385,0.01170548],"category_scores_gemma":[0.009221193,0.00007516307,0.00006679836,0.0005934854,0.0002713644,0.0004266489,0.000223119,0.0004562532,0.006826063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001405422,"about_ca_system_score_gemma":0.00008828868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003040085,"about_ca_topic_score_gemma":0.0006122328,"domain_scores_codex":[0.9969215,0.00008151539,0.0003994549,0.0005077902,0.001678121,0.000411607],"domain_scores_gemma":[0.9966654,0.00171754,0.00007503064,0.0007537949,0.0005259534,0.0002622527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001114112,0.000453923,0.01190749,0.000003496217,0.00003327284,0.0001244971,0.0007926279,0.000166334,0.07950337,0.006260823,0.1053999,0.7952429],"study_design_scores_gemma":[0.004980662,0.0002713888,0.1117887,0.000005497629,0.000008048734,0.0000874309,0.001840397,0.06486276,0.05215107,0.02941668,0.7337623,0.000825163],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2466856,0.0000485559,0.7191325,0.00203472,0.002783025,0.0005814793,0.00003381109,0.000262044,0.0284383],"genre_scores_gemma":[0.9191105,0.000002616151,0.01958762,0.0002179733,0.0002169906,0.00001580397,0.000002179026,0.00001301786,0.06083328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7944177,"threshold_uncertainty_score":0.9991246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2193897973","doi":"10.1109/mwc.2016.7498076","title":"Multi-armed bandits with application to 5G small cells","year":2016,"lang":"en","type":"article","venue":"IEEE Wireless Communications","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Selfishness; Cellular network; Wireless; Resource allocation; Wireless network; Distributed computing; Computer network; Next-generation network; Resource (disambiguation); Small cell; Mobile computing; Telecommunications; The Internet; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1564926192755867,"gpt":0.4209362025593321,"spread":0.2644435832837454,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001209721,0.0002033214,0.0003040438,0.0003894044,0.0005198455,0.000157033,0.004456999,0.0000933327,0.00007356492],"category_scores_gemma":[0.0004649297,0.0001212935,0.00007138021,0.001477796,0.0004455133,0.0003462296,0.0004154976,0.0002330353,0.002871509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00015799,"about_ca_system_score_gemma":0.0001530259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006174629,"about_ca_topic_score_gemma":0.001516998,"domain_scores_codex":[0.9969379,0.0003771835,0.0005800828,0.0006200745,0.001026674,0.0004581245],"domain_scores_gemma":[0.9903153,0.002988117,0.0002314924,0.005190343,0.0009400799,0.0003346775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001232576,0.0007229606,0.002937045,0.000006681001,0.00005547652,0.000004756233,0.001255338,0.002248671,0.373149,0.0009417069,0.003782941,0.6147721],"study_design_scores_gemma":[0.007353257,0.0006661505,0.05139161,0.0003937167,0.00006349689,0.00004545006,0.002127161,0.08326544,0.3826169,0.007227579,0.4624815,0.002367732],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04498994,0.00006580862,0.9470714,0.005976242,0.0001209425,0.0009140387,0.00009021087,0.0001380322,0.0006333281],"genre_scores_gemma":[0.9354277,0.0001382227,0.05918308,0.0001817127,0.0000588285,0.0005996645,0.0000078664,0.00003740556,0.004365517],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8904378,"threshold_uncertainty_score":0.9979049,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963110737","doi":"","title":"Portfolio allocation for Bayesian optimization","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayesian optimization; Computer science; Bayesian probability; Gaussian process; Machine learning; Portfolio; Function (biology); Parameterized complexity; Mathematical optimization; Portfolio optimization; Artificial intelligence; Gaussian; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2496469089177329,"gpt":0.4408040778022478,"spread":0.1911571688845149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00122955,0.00006936734,0.0001089319,0.0002401095,0.0001072924,0.00007059029,0.0004165336,0.00004915778,0.005233518],"category_scores_gemma":[0.001675301,0.00004942949,0.00005450485,0.0005244887,0.00004793959,0.0005045469,0.0000495832,0.00004273031,0.0001660537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002637239,"about_ca_system_score_gemma":0.00005485451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000189121,"about_ca_topic_score_gemma":0.00001436283,"domain_scores_codex":[0.9984162,0.00003926305,0.0003282871,0.0003168886,0.0006913781,0.0002079608],"domain_scores_gemma":[0.998523,0.0003139431,0.0000901382,0.0003795354,0.0006006956,0.00009269524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000374563,0.0004364225,0.003764533,0.00001083503,0.00004774216,0.0000108567,0.001746942,0.1417714,0.0003022005,0.03805081,0.07334824,0.7401355],"study_design_scores_gemma":[0.0004703387,0.0001494085,0.001813033,0.000002492118,0.000004201409,0.000004607577,0.0005301164,0.8840075,0.005529952,0.09690581,0.01041542,0.000167163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001250982,0.000012165,0.970221,0.0001694027,0.0001417214,0.0003206737,0.000003509283,0.00004820948,0.02895819],"genre_scores_gemma":[0.3021641,0.00001041219,0.6738082,0.0001485821,0.0001044414,0.0000867359,0.00001420467,0.00001744056,0.02364586],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7422361,"threshold_uncertainty_score":0.9956759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1987292194","doi":"10.1287/moor.2014.0663","title":"Partial Monitoring—Classification, Regret Bounds, and Algorithms","year":2014,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Logarithm; Minimax; Mathematics; Outcome (game theory); Action (physics); Mathematical optimization; Mathematical economics; Statistics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.4399227455027039,"gpt":0.5509132329952277,"spread":0.1109904874925237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01331864,0.0001398347,0.0003619232,0.0007266058,0.0007185513,0.0007027714,0.0009872518,0.000105246,0.0002510945],"category_scores_gemma":[0.01849598,0.0001055416,0.000057395,0.001454317,0.0008139422,0.0005053089,0.0003940274,0.0004196684,0.0002935521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000605054,"about_ca_system_score_gemma":0.0001861152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003706817,"about_ca_topic_score_gemma":0.0000227815,"domain_scores_codex":[0.993762,0.0006443029,0.0009071517,0.0005319063,0.003678105,0.00047655],"domain_scores_gemma":[0.9920276,0.003616151,0.00008345014,0.001233094,0.002815476,0.0002241752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001017524,0.00243794,0.008668742,0.0003902378,0.0001870971,0.00001780123,0.01859344,0.01066301,0.06138299,0.4737054,0.01676194,0.4070896],"study_design_scores_gemma":[0.0006105094,0.000304937,0.003805149,0.00007394556,0.00000702436,0.0000190896,0.004450608,0.8376048,0.02250534,0.1170473,0.01332193,0.0002493899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3317425,0.000330385,0.6536236,0.004022265,0.0003224887,0.001248085,0.00004804568,0.00007511886,0.008587533],"genre_scores_gemma":[0.8922712,0.00009161435,0.1027601,0.000006189352,0.0002646275,0.0001251567,0.000005760638,0.00002628303,0.004449041],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8269418,"threshold_uncertainty_score":0.9897717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103581319","doi":"","title":"Online Optimization in X-Armed Bandits","year":2008,"lang":"en","type":"article","venue":"RePEc: Research Papers in Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Stochastic game; Regret; Mathematical optimization; Bounded function; Lipschitz continuity; Euclidean space; Function (biology); Combinatorics; Hypercube; Dimension (graph theory); Discrete mathematics; Mathematical economics; Pure mathematics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.1316744920066128,"gpt":0.431294036276807,"spread":0.2996195442701942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004798828,0.000182681,0.000438292,0.001800896,0.0002462842,0.0001123057,0.001194588,0.0001826384,0.0006856733],"category_scores_gemma":[0.008922496,0.0001665341,0.00008790065,0.001560876,0.0005595332,0.0005940814,0.0004296184,0.000925077,0.0001014725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007672518,"about_ca_system_score_gemma":0.0005385188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004820575,"about_ca_topic_score_gemma":0.0006757429,"domain_scores_codex":[0.9951015,0.000587264,0.001001738,0.0009495241,0.001351023,0.001008954],"domain_scores_gemma":[0.9952697,0.003051413,0.0001284988,0.0009378422,0.0003533354,0.0002592004],"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":[0.0001464259,0.000409768,0.02726238,0.000004580826,0.000008042372,0.0002410571,0.0004678086,0.736811,0.0000511917,0.00003419946,0.0002221742,0.2343413],"study_design_scores_gemma":[0.002874648,0.0002433661,0.1244468,0.00004689948,9.050705e-7,0.00008037555,0.001832851,0.8386262,0.0003130266,0.003157685,0.02790012,0.0004770693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9583387,0.0001649886,0.001796263,0.00128305,0.0004048558,0.001125631,0.00006972689,0.00006009731,0.03675669],"genre_scores_gemma":[0.9742044,0.006587285,0.009366245,0.00009866214,0.0002477817,0.00009937343,0.00004490841,0.00005516367,0.009296234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2338642,"threshold_uncertainty_score":0.9994258,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964007796","doi":"","title":"{Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits}","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Stochastic game; Upper and lower bounds; Combinatorics; Mathematics; Constant (computer programming); Combinatorial optimization; Discrete mathematics; Mathematical optimization; Computer science; Mathematical economics","retraction":null,"screen_n_in":null,"score":{"opus":0.2749472121146019,"gpt":0.4837384434734039,"spread":0.208791231358802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003840966,0.0001933882,0.0003857032,0.0003195566,0.0002355452,0.0004365564,0.001111677,0.0001372981,0.0005143999],"category_scores_gemma":[0.01321719,0.0001303017,0.0001333852,0.0008715993,0.0002349067,0.0005691227,0.0002308026,0.0002089794,0.0008898574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001689214,"about_ca_system_score_gemma":0.0004290447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001940517,"about_ca_topic_score_gemma":0.00002488951,"domain_scores_codex":[0.9952238,0.0001320132,0.0005732274,0.000657925,0.002807823,0.0006052182],"domain_scores_gemma":[0.9943799,0.002688484,0.0001477588,0.0007933612,0.001478438,0.000511998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008359877,0.0002571255,0.00030989,0.000007616881,0.00004828667,0.00002428881,0.0008265041,0.003415837,0.0001465249,0.05527543,0.919773,0.01907953],"study_design_scores_gemma":[0.003542617,0.0005542379,0.00007194551,0.000007296758,0.000007738437,0.00001498717,0.0006039245,0.0231155,0.000782885,0.7750989,0.1959137,0.0002862992],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003497857,0.0001330417,0.9798943,0.00133653,0.004442195,0.0007228196,0.00005235331,0.0001242856,0.009796612],"genre_scores_gemma":[0.9343542,0.000002419884,0.0107506,0.0002084042,0.001868597,0.0001773116,0.0000293766,0.00005262629,0.05255643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9691437,"threshold_uncertainty_score":0.9998881,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963582321","doi":"","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Reinforcement learning; Computer science; Bridge (graph theory); State (computer science); Mathematical optimization; Algorithm; Artificial intelligence; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1348757675199226,"gpt":0.4272213443219531,"spread":0.2923455768020305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003263447,0.000222998,0.0003641992,0.0004068513,0.003243982,0.006460275,0.0007948293,0.0001296414,0.00001407121],"category_scores_gemma":[0.004696167,0.0001655907,0.00007012072,0.0002666835,0.0002491075,0.009944907,0.0002445624,0.0003219703,0.00005600717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000128363,"about_ca_system_score_gemma":0.000144295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006792674,"about_ca_topic_score_gemma":0.000006990971,"domain_scores_codex":[0.9964268,0.00007328281,0.001137829,0.000298318,0.001547526,0.0005162232],"domain_scores_gemma":[0.9961886,0.0003914144,0.001526036,0.0005954858,0.001113852,0.0001846034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000178985,0.00001238203,0.004662934,0.0008027201,0.00002379052,0.000004207585,0.005301728,0.1096131,0.0001122893,0.001692256,0.00181715,0.8757784],"study_design_scores_gemma":[0.0008668543,0.0001652092,0.001114932,0.0001703778,0.0000067305,0.00004062248,0.003804845,0.9007249,0.0001508037,0.0009675877,0.09174553,0.0002415661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06905583,0.0008329116,0.9094979,0.002391006,0.001970556,0.002618249,0.00003095617,0.0003608538,0.0132417],"genre_scores_gemma":[0.9941895,0.00002170264,0.0005779187,0.00007812714,0.0001754356,0.0001094627,0.00002942583,0.00001574375,0.004802662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9251337,"threshold_uncertainty_score":0.9980537,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000850397","doi":"10.1109/tac.2013.2292137","title":"Online Markov Decision Processes Under Bandit Feedback","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Markov decision process; Markov chain; State (computer science); Computer science; Markov process; Function (biology); Mathematical economics; Discrete mathematics; Combinatorics; Mathematical optimization; Mathematics; Artificial intelligence; Algorithm; Machine learning; Statistics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.04329478899436651,"gpt":0.3667983632348631,"spread":0.3235035742404966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001955609,0.0003416131,0.0006459312,0.0007254864,0.0004606249,0.000362731,0.001024378,0.0001666199,0.003551582],"category_scores_gemma":[0.001704011,0.000246867,0.0002333298,0.001585769,0.0002050399,0.0005424485,0.000004497582,0.0003690331,0.002009625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001445872,"about_ca_system_score_gemma":0.0002410928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001469122,"about_ca_topic_score_gemma":0.0002879927,"domain_scores_codex":[0.9944181,0.0003872005,0.001049556,0.0007937693,0.002746422,0.0006049403],"domain_scores_gemma":[0.9868866,0.01071249,0.0002498053,0.001115936,0.000718261,0.0003169322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001525382,0.0006083559,0.00001379932,0.00002407791,0.00005636388,0.000005917247,0.00009847568,0.06946191,0.000200153,0.00001207472,0.001134561,0.9282318],"study_design_scores_gemma":[0.005014583,0.0004719015,0.002837587,0.0001356546,0.00006299834,0.00003723185,0.0003188898,0.9653881,0.001554249,0.01853693,0.005186111,0.0004558167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02148839,0.00005010255,0.9747925,0.001530899,0.0007774307,0.0006319428,0.0001131907,0.0002832024,0.0003323022],"genre_scores_gemma":[0.9846848,0.00002141201,0.01143914,0.0006468864,0.0001372448,0.0001011012,0.000002857466,0.00004529736,0.002921241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9633534,"threshold_uncertainty_score":0.9999983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156211713","doi":"10.1287/moor.1090.0397","title":"Markov Decision Processes with Arbitrary Reward Processes","year":2009,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Regret; Hindsight bias; Reinforcement learning; Mathematical optimization; Mathematics; Q-learning; Markov process; Realization (probability); Function (biology); Trajectory; Markov chain; Process (computing); Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.205043330395209,"gpt":0.5069362652545172,"spread":0.3018929348593081,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005981836,0.0002159745,0.000483933,0.001278002,0.0006492659,0.0007381237,0.001850633,0.0001090678,0.000551271],"category_scores_gemma":[0.0491695,0.0001346057,0.00005413499,0.006631904,0.0005196418,0.001168688,0.0002331456,0.0005318077,0.0002831775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007448259,"about_ca_system_score_gemma":0.002212335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001257019,"about_ca_topic_score_gemma":0.0003074862,"domain_scores_codex":[0.9910055,0.0002257569,0.001019356,0.0006615821,0.006440941,0.000646831],"domain_scores_gemma":[0.9822537,0.00698715,0.0001032933,0.001283109,0.009140673,0.0002321256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003492234,0.02207252,0.003188232,0.006688403,0.0004561912,0.0007507571,0.05096899,0.1515315,0.01873965,0.04335505,0.07353304,0.6252235],"study_design_scores_gemma":[0.003538978,0.005989485,0.003038308,0.002677854,0.00003969661,0.0003287962,0.01844151,0.06616969,0.1143317,0.7757308,0.008209879,0.001503256],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3998399,0.0013592,0.5688211,0.004250044,0.00006961729,0.002887183,0.00009140901,0.0001466088,0.02253491],"genre_scores_gemma":[0.6772392,0.000274021,0.3175356,0.00003598225,0.00008609535,0.0001142259,0.00001029622,0.00003215648,0.00467244],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7323758,"threshold_uncertainty_score":0.9588398,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2615616721285479,"gpt":0.4801871304299516,"spread":0.2186254583014037,"validation_status":"score_only:v0-immature-baseline"},"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"},"labels":[],"label_agreement":null},{"id":"W2157016390","doi":"","title":"Online Markov Decision Processes under Bandit Feedback","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Computer science; Markov process; State (computer science); Markov chain; Mathematical optimization; Online learning; Reinforcement learning; Adversary; Function (biology); Action (physics); Artificial intelligence; Mathematics; Algorithm; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.08846169459235069,"gpt":0.4450109408182472,"spread":0.3565492462258965,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001768201,0.0002069261,0.0003031984,0.0004295078,0.000248245,0.0004532158,0.001547545,0.0001624998,0.01549713],"category_scores_gemma":[0.01300375,0.0001269714,0.00008957407,0.001960883,0.0002632757,0.0008039876,0.0004242027,0.0005772382,0.003017848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003055524,"about_ca_system_score_gemma":0.0003181225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000224762,"about_ca_topic_score_gemma":0.001808446,"domain_scores_codex":[0.9949963,0.00006221714,0.0006355422,0.0007894279,0.002988847,0.0005276378],"domain_scores_gemma":[0.9925805,0.004554091,0.0001335509,0.001066484,0.001347481,0.0003178499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002176756,0.00074387,0.00434759,0.00001412027,0.00002268125,0.00004556599,0.0001329549,0.0008989897,0.003458509,0.0007470953,0.0825868,0.9067842],"study_design_scores_gemma":[0.002535532,0.0003036254,0.09904185,0.00004023132,0.00001228321,0.0001389178,0.001960583,0.01248573,0.01350072,0.4538599,0.4151506,0.0009700626],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4466851,0.0001413653,0.5336622,0.003357016,0.00157712,0.0004846028,0.00006962427,0.0002171841,0.01380572],"genre_scores_gemma":[0.8373506,0.00006453094,0.1110869,0.0006000394,0.000679378,0.00001912709,0.00001967251,0.0000444325,0.0501353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9058141,"threshold_uncertainty_score":0.9977584,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161571887","doi":"10.1145/1553374.1553524","title":"Piecewise-stationary bandit problems with side observations","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Israel Science Foundation; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Regret; Piecewise; Baseline (sea); Mathematics; Piecewise linear function; Contrast (vision); Adversarial system; Distribution (mathematics); Computer science; Mathematical optimization; Artificial intelligence; Statistics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.2241001579878948,"gpt":0.4240967083286237,"spread":0.1999965503407289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008402973,0.0001335948,0.0001866731,0.000276304,0.0002611385,0.0002319773,0.0006008209,0.00004592991,0.001031706],"category_scores_gemma":[0.001010729,0.00008077458,0.00004711118,0.001565949,0.0001061498,0.001019875,0.00004670348,0.0001668478,0.0006243602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005142995,"about_ca_system_score_gemma":0.000157336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001530608,"about_ca_topic_score_gemma":0.00008520506,"domain_scores_codex":[0.9965981,0.00007527931,0.0004271376,0.0004798054,0.002066701,0.0003529737],"domain_scores_gemma":[0.9975057,0.0009398941,0.000109053,0.0005654795,0.0007159166,0.0001639872],"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":[0.000275236,0.0009540028,0.02374174,0.00001070015,0.00007208037,0.0001950978,0.001996678,0.2293693,0.004032731,0.03078133,0.1294951,0.5790759],"study_design_scores_gemma":[0.001393398,0.0008832873,0.4201594,0.00002652954,0.000008782567,0.00004785301,0.001022722,0.04217491,0.001157147,0.4195401,0.1130846,0.0005012463],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0310245,0.0001361822,0.9088507,0.01689352,0.0001185917,0.000804631,0.00002994543,0.0002514943,0.04189045],"genre_scores_gemma":[0.8358264,0.00002081209,0.09734081,0.00141739,0.0001581734,0.00005241043,0.00003707494,0.0000194697,0.06512745],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8115098,"threshold_uncertainty_score":0.9998815,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146412174","doi":"","title":"Optimal Bayesian Recommendation Sets and Myopically Optimal Choice Query Sets","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Submodular set function; Query optimization; Mathematical optimization; Set (abstract data type); Multinomial logistic regression; Greedy algorithm; Bayesian probability; Data mining; Algorithm; Machine learning; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05953119479209398,"gpt":0.4010226266591596,"spread":0.3414914318670657,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001939966,0.0002276366,0.0003118643,0.0004741333,0.0005561064,0.002511445,0.000515435,0.0001998202,0.0001187326],"category_scores_gemma":[0.00249093,0.0001764009,0.0000500529,0.0007114742,0.0001544467,0.008740244,0.0001702205,0.0006260595,0.0001554263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005295148,"about_ca_system_score_gemma":0.0001485167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004806507,"about_ca_topic_score_gemma":0.00001653298,"domain_scores_codex":[0.9964994,0.0001510917,0.001189553,0.0003578467,0.00136561,0.0004365507],"domain_scores_gemma":[0.9972197,0.0005730354,0.0006389269,0.000348937,0.000962247,0.0002571629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007632629,0.000036168,0.002924249,0.000171176,0.00001108597,0.000003547457,0.002019982,0.0188143,0.0006889064,0.0001104018,0.004150956,0.9709929],"study_design_scores_gemma":[0.0005570308,0.0001018891,0.006399446,0.0000374614,0.000004586907,0.0001528346,0.001029208,0.9402477,0.0001829285,0.0001071204,0.0509233,0.000256515],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6994618,0.00008454847,0.2915715,0.003029553,0.00218457,0.0009544429,0.00006675567,0.0003172815,0.002329519],"genre_scores_gemma":[0.9910201,0.000004388096,0.008039988,0.0002424245,0.0002064451,0.00005797422,0.00007586862,0.00001550615,0.0003373378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9707364,"threshold_uncertainty_score":0.9985241,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170307371","doi":"","title":"On correlation and budget constraints in model-based bandit optimization with application to automatic machine learning","year":2014,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Frequentist inference; Bayesian optimization; Computer science; Machine learning; Bayesian probability; Artificial intelligence; Constraint (computer-aided design); Feature (linguistics); Function (biology); Mathematical optimization; Bayesian inference; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.100663809997761,"gpt":0.4084052332996377,"spread":0.3077414233018767,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001027689,0.000152706,0.0001872088,0.000474108,0.0001292304,0.0002927018,0.0002332084,0.00005968089,0.0002514753],"category_scores_gemma":[0.003545202,0.0001246847,0.00001150242,0.0002898249,0.0002261836,0.0001500004,0.00003883908,0.0002407994,0.00007836451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006312464,"about_ca_system_score_gemma":0.00007198884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000268961,"about_ca_topic_score_gemma":0.0002606476,"domain_scores_codex":[0.9977874,0.000159489,0.0004830483,0.0004707915,0.0009197857,0.0001794468],"domain_scores_gemma":[0.9971771,0.001868611,0.0001681678,0.0001638054,0.0005014008,0.0001209432],"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":[0.0001284999,0.00003647511,0.0002756029,0.000002016048,0.000002307793,0.000001726444,0.0001289168,0.6343229,0.00003154029,0.1309274,0.000007707282,0.234135],"study_design_scores_gemma":[0.00009329148,0.0003511424,0.0002989195,0.00004482931,0.000002434735,0.000002225305,0.0001595191,0.8606589,0.0001701428,0.1380725,0.00002229363,0.0001237989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004389176,0.00000202369,0.9934682,0.0007588559,0.0000719133,0.0002859669,0.00008504647,0.00002322086,0.0009156473],"genre_scores_gemma":[0.9234951,0.00001025836,0.07606488,0.0001933581,0.00002124999,0.00003325807,0.00006847082,0.00001021523,0.0001032279],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9191059,"threshold_uncertainty_score":0.5084496,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2952908320","doi":"","title":"Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations","year":2012,"lang":"en","type":"preprint","venue":"UvA-DARE (University of Amsterdam)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Institute for Computing, Information and Cognitive Systems","keywords":"Regret; Mathematics; Complement (music); Exponential function; Dimension (graph theory); Gaussian; Combinatorics; Function (biology); Constant (computer programming); Gaussian process; Space (punctuation); Exponential family; Discrete mathematics; Applied mathematics; Mathematical analysis; Statistics; Computer science; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1870917374975287,"gpt":0.3866931792783039,"spread":0.1996014417807752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001154332,0.0004317666,0.0008945831,0.0007182611,0.0007386587,0.0002615938,0.002608298,0.0004124733,0.0006054594],"category_scores_gemma":[0.0006515117,0.0004055002,0.0003379012,0.0007533733,0.0007522317,0.0009925504,0.001229645,0.0006247593,0.00006864886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002048681,"about_ca_system_score_gemma":0.0008226739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001055307,"about_ca_topic_score_gemma":0.0005649014,"domain_scores_codex":[0.9951512,0.0001908063,0.0005181239,0.001170831,0.002242202,0.0007268465],"domain_scores_gemma":[0.994529,0.0008812545,0.0009923559,0.001467236,0.001749945,0.0003802014],"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":[0.02325344,0.006320166,0.1055331,0.01124776,0.004771782,0.002023014,0.1586961,0.04119782,0.002008117,0.006427559,0.110571,0.5279502],"study_design_scores_gemma":[0.02289055,0.004540445,0.4191875,0.004715091,0.00232031,0.0002914579,0.0850728,0.1000336,0.001666268,0.1508565,0.1997861,0.008639302],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2693606,0.00018236,0.7204539,0.001682343,0.001244753,0.002428893,0.00223311,0.0001498663,0.002264206],"genre_scores_gemma":[0.9667742,0.00001864991,0.02311205,0.00003174162,0.0003185915,0.00001518737,0.0003631382,0.0000546339,0.009311835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6974136,"threshold_uncertainty_score":0.9998397,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2602868127","doi":"10.24963/ijcai.2017/278","title":"Bernoulli Rank-1 Bandits for Click Feedback","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Bernoulli's principle; Rank (graph theory); Position (finance); Computer science; Bounded function; Product (mathematics); Mathematics; Algorithm; Combinatorics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.3279068753148421,"gpt":0.5299592419994449,"spread":0.2020523666846028,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005639473,0.0005263555,0.001144284,0.000568228,0.0007602947,0.002177547,0.00618203,0.0007122125,0.002926982],"category_scores_gemma":[0.01479473,0.0003706185,0.0007299201,0.0002065483,0.000450761,0.0004575482,0.003895822,0.001079821,0.003218768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001644138,"about_ca_system_score_gemma":0.000600388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001115339,"about_ca_topic_score_gemma":0.0001929534,"domain_scores_codex":[0.9919838,0.0001961963,0.00119621,0.002069404,0.003583955,0.0009704586],"domain_scores_gemma":[0.988667,0.003772859,0.0008853051,0.004408743,0.001854051,0.000412002],"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":[0.0003722463,0.0001841393,0.001234697,0.0001111495,0.0001931809,0.00003874295,0.0003237678,0.004509761,0.00004059291,0.001132207,0.5605967,0.4312628],"study_design_scores_gemma":[0.001642257,0.0001169938,0.003571575,0.000080571,0.00002696615,0.000008627107,0.0001341037,0.01821712,0.00110529,0.4441391,0.5302209,0.0007365999],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.002801461,0.0008036362,0.93163,0.006211245,0.005899351,0.003499433,0.0009337723,0.0002240043,0.04799706],"genre_scores_gemma":[0.1351413,0.0007145871,0.09808184,0.0005153912,0.005084095,0.001370353,0.0003338369,0.000250762,0.7585079],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8335482,"threshold_uncertainty_score":0.9998746,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2095762034","doi":"10.5555/1577069.1577089","title":"Online Learning with Sample Path Constraints","year":2009,"lang":"en","type":"article","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Hindsight bias; Path (computing); Heuristic; Mathematical optimization; Convex hull; Sample (material); Constraint (computer-aided design); Computer science; Decision maker; Function (biology); Measure (data warehouse); Term (time); Mathematics; Regular polygon; Operations research; Data mining; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.04860125274093496,"gpt":0.3624277436117635,"spread":0.3138264908708285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001053997,0.0004176728,0.0008371194,0.001808175,0.000368997,0.0001113097,0.001955357,0.0004598195,0.0002547573],"category_scores_gemma":[0.008851621,0.0003088655,0.0001535242,0.003735803,0.002451274,0.000778941,0.0003061757,0.001270284,0.0001053093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001377483,"about_ca_system_score_gemma":0.0003101417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002257209,"about_ca_topic_score_gemma":0.0000980966,"domain_scores_codex":[0.9949912,0.00009151419,0.0008831189,0.001046352,0.002100932,0.0008868104],"domain_scores_gemma":[0.9964592,0.0004283617,0.0006027195,0.001419481,0.0008753366,0.0002148691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001688143,0.0007390518,0.02969866,0.00001485592,0.0001330588,0.0003790513,0.0002760902,0.006126211,0.003391887,0.007770478,0.002152897,0.949149],"study_design_scores_gemma":[0.00589367,0.004243222,0.03305351,0.0004331739,0.00009132984,0.0004140711,0.003638154,0.006791587,0.01708621,0.09043638,0.8361249,0.00179379],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5565321,0.0007494973,0.41186,0.02356937,0.0005743642,0.001158166,0.000510718,0.00128398,0.003761722],"genre_scores_gemma":[0.8692268,0.00006925179,0.1294781,0.0001225196,0.00007015603,0.00001403965,0.00003342237,0.00002680184,0.0009589074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9473552,"threshold_uncertainty_score":0.9999363,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105336508","doi":"","title":"A Convergent Form of Approximate Policy Iteration","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Lipschitz continuity; Convergence (economics); Operator (biology); Action (physics); Mathematics; Constant (computer programming); Mathematical optimization; Function (biology); Applied mathematics; Bellman equation; State (computer science); Computer science; Algorithm; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.1833628301305216,"gpt":0.4441139764675269,"spread":0.2607511463370052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006613783,0.00006626507,0.0001493824,0.0003593595,0.00005781622,0.00006829479,0.0003563267,0.00003340969,0.00666677],"category_scores_gemma":[0.001415993,0.000043076,0.0000612132,0.0009041767,0.00007770101,0.0004007349,0.00009898443,0.00005799532,0.0007521902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003970194,"about_ca_system_score_gemma":0.0000222254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002982966,"about_ca_topic_score_gemma":0.00001089892,"domain_scores_codex":[0.9979058,0.00004428199,0.0004114911,0.0002189794,0.001210141,0.0002093006],"domain_scores_gemma":[0.9988318,0.0002754209,0.0001009458,0.0003808252,0.0003273062,0.00008367298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005902591,0.0004678283,0.002958045,0.00002556098,0.00003549022,0.00001444713,0.005577375,0.001056421,0.005800228,0.04902202,0.05517959,0.879804],"study_design_scores_gemma":[0.0009440474,0.0002106379,0.001797771,0.000008126662,0.00000247226,0.00001476957,0.0005771981,0.7455637,0.03780047,0.1693975,0.04347346,0.0002098362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05597288,0.0001637324,0.8673233,0.00418224,0.0002623348,0.0005702148,0.00002797438,0.00008142239,0.07141583],"genre_scores_gemma":[0.9647919,0.00003522326,0.005776619,0.0001125747,0.00008588855,0.00001139579,0.000001443627,0.000006235561,0.0291787],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.908819,"threshold_uncertainty_score":0.9942413,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1577851669","doi":"10.1007/978-3-642-34106-9_25","title":"Partial Monitoring with Side Information","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":69,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.07038242003984675,"gpt":0.3665795994389151,"spread":0.2961971793990684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002566014,0.0003610972,0.0004362993,0.001258658,0.0002954704,0.0008798486,0.00212949,0.0002257032,0.0001085816],"category_scores_gemma":[0.0008787677,0.0002445064,0.00007478316,0.0008996074,0.0009081747,0.002759811,0.00077511,0.0008828966,0.0005192742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003120372,"about_ca_system_score_gemma":0.0004684964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001385421,"about_ca_topic_score_gemma":0.00001986783,"domain_scores_codex":[0.9933953,0.00003862982,0.0006879632,0.0007518468,0.004354768,0.0007715535],"domain_scores_gemma":[0.9961013,0.001418878,0.0003869868,0.001095325,0.0007427329,0.0002547406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001830584,0.000006168218,0.0004370027,0.000004878087,0.000003587659,0.00001477863,0.0004874066,0.0680882,0.00001473089,0.0002040668,0.000007859953,0.930713],"study_design_scores_gemma":[0.002010197,0.001118685,0.007324367,0.001184528,0.00003588248,0.0003810725,0.0000118903,0.4388601,0.02440495,0.4112979,0.1099539,0.003416421],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002189917,0.0002411807,0.995196,0.000226161,0.001375704,0.0003181838,0.000007009869,0.00005352899,0.002363239],"genre_scores_gemma":[0.6656882,0.00007059826,0.3291735,0.0003758187,0.003453924,0.00002883541,0.000009481661,0.00005902379,0.00114065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9272966,"threshold_uncertainty_score":0.9970682,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2561282814","doi":"10.1016/j.tcs.2012.10.008","title":"Toward a classification of finite partial-monitoring games","year":2012,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":67,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Computer science; Algebra over a field; Calculus (dental); Mathematical economics; Pure mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1886192829944454,"gpt":0.4452306175989132,"spread":0.2566113346044678,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00736225,0.0001191123,0.0002376774,0.0003442263,0.0002102596,0.0002063857,0.001808611,0.0000468681,0.0002022359],"category_scores_gemma":[0.00377963,0.00008186966,0.0000719224,0.002072568,0.004132121,0.001019472,0.0006574076,0.0001851687,0.0002921351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005573051,"about_ca_system_score_gemma":0.00009904522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001234013,"about_ca_topic_score_gemma":4.129242e-8,"domain_scores_codex":[0.9953073,0.0002195722,0.0005174397,0.0004792919,0.002798354,0.0006781044],"domain_scores_gemma":[0.9956476,0.002446952,0.0001498104,0.0007867954,0.0005983842,0.0003704661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003750309,0.0001547196,0.01188832,0.000006389745,0.000004316914,0.000002402576,0.002018082,0.000736916,0.005267568,0.67327,0.00005050898,0.3065633],"study_design_scores_gemma":[0.0003667442,0.0002750093,0.1278889,0.00004790008,0.000007712249,0.00001792022,0.0003709767,0.5014997,0.1216466,0.2462394,0.001285068,0.000354015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1264108,0.00006344391,0.8710493,0.000363667,0.0008073623,0.0001133415,0.000002386704,0.00003570631,0.001154065],"genre_scores_gemma":[0.9615536,0.000005157028,0.03797325,0.00002210696,0.0004092663,0.000007247008,2.446432e-7,0.000006199581,0.00002290851],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8351429,"threshold_uncertainty_score":0.9985781,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2293140407","doi":"10.1145/1993636.1993666","title":"Dueling algorithms","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Computer science; Mathematical optimization; Binary search algorithm; Algorithm; Ranking (information retrieval); Binary number; Mathematics; Search algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5436472135121365,"gpt":0.4912489599546517,"spread":0.05239825355748484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001863484,0.00009220904,0.000157009,0.000260658,0.0001235534,0.00009309182,0.0008958341,0.000048481,0.01290426],"category_scores_gemma":[0.001845528,0.0000588093,0.00007492071,0.0007880225,0.0001093092,0.0004485145,0.0002245704,0.0001453649,0.006329103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000211404,"about_ca_system_score_gemma":0.00004163397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000570406,"about_ca_topic_score_gemma":0.00001601653,"domain_scores_codex":[0.9973026,0.00007737599,0.0003767482,0.000419128,0.001476444,0.0003477006],"domain_scores_gemma":[0.9983173,0.0004730071,0.00006163311,0.000611359,0.0003731837,0.0001635071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003436072,0.0001174297,0.003846108,0.000001238015,0.00001575109,0.0001000902,0.001331736,0.0001045132,0.0002407838,0.004015279,0.0112761,0.9789166],"study_design_scores_gemma":[0.001129669,0.0003120866,0.03213299,0.0000101034,0.000006975937,0.0000814372,0.00475674,0.07841907,0.03918976,0.709062,0.1341474,0.0007517415],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00461645,0.00007139317,0.8376883,0.0001423064,0.0003791153,0.0001202074,0.000002832968,0.00011088,0.1568685],"genre_scores_gemma":[0.6724693,0.00002023058,0.2658251,0.0003046606,0.0002566107,0.00002033805,0.000001147648,0.00002626688,0.06107634],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9781649,"threshold_uncertainty_score":0.9944446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963246254","doi":"","title":"Optimum Statistical Estimation with Strategic Data Sources","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Polynomial regression; Computer science; Regression; Regression analysis; Kernel (algebra); Linear regression; Range (aeronautics); Proper linear model; Mathematical optimization; Econometrics; Statistics; Mathematics; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.5456077650671064,"gpt":0.5258773785639367,"spread":0.01973038650316972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002375707,0.0001031898,0.0001705248,0.0001379741,0.00008311386,0.0004868607,0.00131793,0.00003723351,0.0009093566],"category_scores_gemma":[0.002411424,0.00005692643,0.000008376201,0.0005576206,0.000230168,0.0009678762,0.0003861863,0.0001400285,0.00138043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003186176,"about_ca_system_score_gemma":0.0003618951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004088895,"about_ca_topic_score_gemma":0.00007351554,"domain_scores_codex":[0.9962413,0.0001303891,0.000302321,0.0005509907,0.002495439,0.0002795562],"domain_scores_gemma":[0.9969198,0.001093197,0.00007411904,0.001175376,0.0004347067,0.0003027643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008267559,0.0005047561,0.006106871,0.0000144385,0.00008397733,0.0004350631,0.0009682518,0.3178747,0.00004240241,0.04233829,0.120052,0.5107525],"study_design_scores_gemma":[0.0004490832,0.000207464,0.0006703534,0.000002848732,0.000003741222,0.00002373035,0.002036104,0.879962,0.00004915238,0.1140192,0.002461429,0.0001148181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007214133,0.00003067608,0.9822283,0.0005493456,0.00006032647,0.000137117,0.0000749496,0.00005673674,0.009648376],"genre_scores_gemma":[0.5151808,0.000001564316,0.4806665,0.00004717947,0.000072488,0.000005994982,0.0001082611,0.00001235977,0.003904827],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5620874,"threshold_uncertainty_score":0.9993971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W191658262","doi":"","title":"{Toward Minimax Off-policy Value Estimation}","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Estimator; Minimax; Markov decision process; Multiplicative function; Mathematical optimization; Oracle; Computer science; Time horizon; Limit (mathematics); Sample size determination; Upper and lower bounds; Mathematics; Sample (material); Value (mathematics); Markov process; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.3651976247050544,"gpt":0.5253249721812989,"spread":0.1601273474762445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00266786,0.0001307192,0.0002328663,0.0005472691,0.00009107888,0.0002943794,0.001006016,0.00007045666,0.0007330045],"category_scores_gemma":[0.0204206,0.00008762778,0.00007521295,0.001659563,0.0001799056,0.0007037286,0.0003180579,0.0001495448,0.008909793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001795816,"about_ca_system_score_gemma":0.0006437635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001221741,"about_ca_topic_score_gemma":0.00001111738,"domain_scores_codex":[0.9955585,0.0001737774,0.0004866736,0.0004562957,0.002918824,0.0004059198],"domain_scores_gemma":[0.9969017,0.001049589,0.00009990436,0.0007090211,0.0007922433,0.0004475654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005704639,0.0001085507,0.0005912926,0.000003161584,0.00001558,0.0000441661,0.001443675,0.03552714,0.00004900308,0.02406199,0.1869234,0.751175],"study_design_scores_gemma":[0.0008094794,0.0001387395,0.001379533,0.000004355366,0.000002600212,0.00003732887,0.00136456,0.3852173,0.001313905,0.4326744,0.1768337,0.0002240616],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006838641,0.0001835381,0.868857,0.0109324,0.0004132479,0.0003005927,0.0000149082,0.0001698037,0.1122899],"genre_scores_gemma":[0.7132871,0.0000169153,0.1951555,0.0009562553,0.0006839443,0.00003925688,0.000008522326,0.00003462254,0.0898179],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.750951,"threshold_uncertainty_score":0.9918619,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964315724","doi":"10.48550/arxiv.1605.08988","title":"On Explore-Then-Commit Strategies","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Commit; Minimax; Mathematical optimization; Asymptotically optimal algorithm; Simple (philosophy); Gaussian; Computer science; Order (exchange); Time horizon; Empirical evidence; Horizon; Mathematical economics; Mathematics; Economics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.3686539785191696,"gpt":0.3317025144979235,"spread":0.03695146402124605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001337193,0.0004846768,0.0006414422,0.0009720168,0.000292552,0.0004744102,0.00387229,0.0004287937,0.001668899],"category_scores_gemma":[0.001139067,0.0003661813,0.0004068281,0.0009644918,0.0005405338,0.0008058205,0.002468818,0.001067485,0.004528654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003706044,"about_ca_system_score_gemma":0.0004690982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003387075,"about_ca_topic_score_gemma":0.00003337224,"domain_scores_codex":[0.9953985,0.0004991366,0.0004657879,0.0020297,0.0009007686,0.0007061084],"domain_scores_gemma":[0.9933577,0.002502554,0.0004367427,0.002707993,0.0006527039,0.0003423192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008831482,0.0004467542,0.00146738,0.00005413806,0.0002823452,0.002363292,0.0009365703,0.5008511,0.0001206951,0.4503167,0.01949167,0.02278621],"study_design_scores_gemma":[0.0006320141,0.0001268366,0.0006178094,0.0001044042,0.00001839104,0.000002345367,0.001600866,0.01603023,0.0002245915,0.9749893,0.005144272,0.0005089504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2549816,0.00006886682,0.7018714,0.0004193561,0.001202995,0.0005470373,0.0001356175,0.0002523762,0.04052078],"genre_scores_gemma":[0.9783825,0.0001314994,0.0001647301,0.00005836228,0.0002168514,0.00000273486,0.00000903415,0.00004089314,0.02099337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.723401,"threshold_uncertainty_score":0.999879,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2206616202","doi":"","title":"Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Lasso (programming language); Online algorithm; Algorithm; Set (abstract data type); Online learning; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1421157769493659,"gpt":0.4560052028147418,"spread":0.3138894258653759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001189412,0.0001316047,0.0002064235,0.000406285,0.0001884968,0.0001084004,0.0005194116,0.00005941687,0.0008498661],"category_scores_gemma":[0.002758978,0.0000960667,0.00003312982,0.001013526,0.00009085306,0.0004671031,0.0003694078,0.0001334682,0.005033597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005195905,"about_ca_system_score_gemma":0.00004837747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006163566,"about_ca_topic_score_gemma":0.00007699803,"domain_scores_codex":[0.9974337,0.0000690037,0.0003342888,0.0004667686,0.001207209,0.0004889795],"domain_scores_gemma":[0.9969792,0.001240937,0.00005899273,0.0005793135,0.0003150044,0.0008265782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005803002,0.001428969,0.02195817,0.00002757781,0.00009145971,0.00001813167,0.0156629,0.04713886,0.01385339,0.02232618,0.2756282,0.6012859],"study_design_scores_gemma":[0.003277651,0.001074057,0.3069449,0.00009684642,0.0000620678,0.0001449549,0.02334376,0.165134,0.007764854,0.04312858,0.44664,0.002388301],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08970872,0.00004695997,0.9067177,0.002082905,0.0002126839,0.0006194789,0.00006161517,0.00004592636,0.0005039787],"genre_scores_gemma":[0.9849985,0.000003962524,0.009343336,0.0007402891,0.0002190811,0.00005449564,0.000008993724,0.00001163044,0.004619703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8973744,"threshold_uncertainty_score":0.9957411,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009482316","doi":"10.1080/07474940600596695","title":"Sequential Generalized Likelihood Ratios and Adaptive Treatment Allocation for Optimal Sequential Selection","year":2006,"lang":"en","type":"article","venue":"Sequential Analysis","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National University of Singapore; University of Lethbridge; National Science Foundation","keywords":"Mathematics; Selection (genetic algorithm); Mathematical optimization; Sequential estimation; Sampling (signal processing); Exponential family; Constraint (computer-aided design); Population; Sequential analysis; Stopping rule; Statistics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08329802728424093,"gpt":0.3970339346573362,"spread":0.3137359073730952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00140066,0.0004062233,0.0007762409,0.001306688,0.0007075773,0.0006773046,0.0003886909,0.0002038528,0.0006640067],"category_scores_gemma":[0.0002321421,0.0003303762,0.0007279811,0.002865991,0.0002369557,0.0007942565,0.0001203413,0.0001454977,0.00006147219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005708117,"about_ca_system_score_gemma":0.0003028348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003299803,"about_ca_topic_score_gemma":0.005885683,"domain_scores_codex":[0.9947983,0.000497861,0.001074259,0.001299496,0.00160087,0.0007291982],"domain_scores_gemma":[0.9973224,0.0003573932,0.0004590711,0.0004929973,0.001145746,0.0002224075],"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":[0.002421742,0.0009836793,0.004041426,0.00001897067,0.006498287,0.00005093318,0.001004155,0.7641624,0.1065519,0.005650093,0.0029713,0.1056452],"study_design_scores_gemma":[0.003551661,0.000850947,0.00211558,0.000005547841,0.002502112,0.0000212353,0.0003655582,0.908379,0.05761039,0.01903205,0.004896256,0.0006696888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2356958,0.0001813841,0.7623686,0.0003777479,0.0002144115,0.0007870815,0.0001718633,0.00008427311,0.0001188412],"genre_scores_gemma":[0.9615157,0.00004732666,0.03239565,0.00003608788,0.001029274,0.0002999853,0.0005753352,0.00003748128,0.004063217],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7299729,"threshold_uncertainty_score":0.9999148,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1675620121","doi":"10.48550/arxiv.1402.7005","title":"Bayesian Multi-Scale Optimistic Optimization","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayesian optimization; Regret; Computer science; Mathematical optimization; Global optimization; Optimization problem; Convergence (economics); Gaussian process; Bayesian probability; Test functions for optimization; Derivative-free optimization; Function (biology); Continuous optimization; Random optimization; Gaussian; Algorithm; Multi-swarm optimization; Mathematics; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.2206405619657407,"gpt":0.3089465051702611,"spread":0.08830594320452045,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001550453,0.0004292114,0.0006465802,0.0008053701,0.0003270601,0.000346049,0.002723419,0.0005020204,0.001195417],"category_scores_gemma":[0.0017129,0.0004260814,0.0003332335,0.001239546,0.0003859529,0.0003869393,0.002119892,0.0009533199,0.0007693426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003484308,"about_ca_system_score_gemma":0.0002649608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006753765,"about_ca_topic_score_gemma":0.0000597067,"domain_scores_codex":[0.995625,0.0005518552,0.0005468131,0.002014232,0.0006530412,0.0006090535],"domain_scores_gemma":[0.9950204,0.0009575991,0.0005176229,0.002142459,0.0009310559,0.0004308381],"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":[0.0000456918,0.00008416711,0.0008325715,0.00001695409,0.00002703534,0.0001041779,0.00006543469,0.9970271,0.000005299088,0.0002156273,0.0005517053,0.001024231],"study_design_scores_gemma":[0.0006604333,0.00004153661,0.0003751359,0.00004115245,0.00003970184,0.000003805666,0.0001640765,0.9850785,0.00004369675,0.01231517,0.0007835017,0.000453363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00376805,0.00003609386,0.9928875,0.00008048776,0.0006725388,0.0004652709,0.00006276081,0.0001650447,0.00186223],"genre_scores_gemma":[0.9229508,0.0001073097,0.05944594,0.00005495305,0.000190904,0.000002408597,0.00005815583,0.00005153978,0.01713798],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9334416,"threshold_uncertainty_score":0.9998191,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964240248","doi":"","title":"Combinatorial cascading bandits","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Observability; Regret; Mathematical proof; Routing (electronic design automation); Theoretical computer science; Mathematical optimization; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.3963383477905725,"gpt":0.5102858031466518,"spread":0.1139474553560793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003282182,0.00008906741,0.0001841575,0.0002276597,0.00009932084,0.00024648,0.0007139159,0.0000593458,0.0008635415],"category_scores_gemma":[0.008257305,0.00005838753,0.00005190054,0.0008379899,0.00008931689,0.0005053458,0.0002352144,0.0001511097,0.003984169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008860133,"about_ca_system_score_gemma":0.0001459428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003606297,"about_ca_topic_score_gemma":0.00001305463,"domain_scores_codex":[0.9962918,0.0001413855,0.0003221099,0.0003535793,0.002565664,0.000325472],"domain_scores_gemma":[0.9975203,0.0009351509,0.00006085712,0.0004626836,0.0006488671,0.0003721909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002466195,0.0002373847,0.01058682,0.000002629966,0.00003386574,0.0002564687,0.001843221,0.002323301,0.0003147748,0.09369286,0.7319825,0.1584796],"study_design_scores_gemma":[0.001732833,0.0001685043,0.0008536639,0.000002969629,0.000001967076,0.00002843741,0.001184237,0.01010775,0.003145239,0.6292706,0.3532938,0.0002100326],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1022216,0.0002932489,0.4111122,0.002917354,0.01242503,0.0006130665,0.00001484222,0.0003756171,0.4700271],"genre_scores_gemma":[0.9838396,0.000001580128,0.001792444,0.00007506541,0.0005006365,0.000006790435,0.000001231365,0.00001019419,0.01377243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.881618,"threshold_uncertainty_score":0.9967914,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1838526237","doi":"10.1287/mnsc.2015.2153","title":"Robust Multiarmed Bandit Problems","year":2015,"lang":"en","type":"article","venue":"Management Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematical optimization; Computer science; Bellman equation; Robust optimization; Dynamic programming; Dynamic pricing; Decision maker; Multi-armed bandit; Regret; Mathematics; Operations research; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.3788463044400635,"gpt":0.4460406049573264,"spread":0.06719430051726294,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01053293,0.0001567375,0.0001930507,0.000962803,0.0004094267,0.000818258,0.003322052,0.00002928693,0.0002836807],"category_scores_gemma":[0.002451563,0.0001113661,0.0000507324,0.004955589,0.0009855174,0.001536119,0.001417781,0.000150741,0.002990739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002340501,"about_ca_system_score_gemma":0.0001143354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001755271,"about_ca_topic_score_gemma":0.00001669543,"domain_scores_codex":[0.9912472,0.00009126709,0.0004532227,0.001062702,0.006355248,0.0007903551],"domain_scores_gemma":[0.9973971,0.0002012936,0.0001412987,0.001165965,0.0005899898,0.000504365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008320082,0.0005008272,0.01442609,0.00003265156,0.0000345935,0.0003077593,0.00265445,0.4468516,0.0005004461,0.01238126,0.1033533,0.4188738],"study_design_scores_gemma":[0.002785653,0.0002898595,0.03959691,0.00004416171,0.00001402479,0.00002056124,0.005940289,0.3617596,0.001288521,0.09879869,0.4886388,0.0008228597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02138115,0.000158393,0.7890342,0.003135924,0.00212113,0.00164524,0.000008173848,0.0002877404,0.1822281],"genre_scores_gemma":[0.9237496,0.00001686948,0.03585848,0.0002582208,0.0001205823,0.00008448456,0.00000172262,0.00001666217,0.03989341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9023684,"threshold_uncertainty_score":0.9977856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154806059","doi":"","title":"Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Adversarial system; Mathematical optimization; Computer science; Shortest path problem; Path (computing); Mathematics; Graph; Markov process; Theoretical computer science; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.09547229580583252,"gpt":0.270794819568804,"spread":0.1753225237629715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008362065,0.0001880977,0.0002774641,0.0003812722,0.0002710759,0.0001384353,0.0006841978,0.0001103397,0.0005255857],"category_scores_gemma":[0.003206552,0.0001516327,0.00006826699,0.003513002,0.0002767522,0.001617349,0.0001386163,0.0004213669,0.0002107991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002789394,"about_ca_system_score_gemma":0.0003478482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002483123,"about_ca_topic_score_gemma":0.002024487,"domain_scores_codex":[0.9975822,0.0002716363,0.0003464018,0.0008870009,0.000477142,0.0004356508],"domain_scores_gemma":[0.996471,0.001662052,0.0001501212,0.0004968787,0.001024103,0.0001958385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0009215675,0.00116255,0.08742838,0.0000498238,0.00003467846,0.0002400455,0.0006842311,0.8692603,0.0001539202,0.0009159154,0.0002712579,0.03887735],"study_design_scores_gemma":[0.004910219,0.0007634845,0.4226949,0.0002264318,0.00003866932,0.00002188369,0.004359107,0.3705978,0.0003259136,0.1933522,0.001858214,0.0008512603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6124066,0.000009288739,0.3867233,0.000182465,0.00002783926,0.0003930951,0.00002405117,0.00005392599,0.0001793752],"genre_scores_gemma":[0.9958372,0.00004200714,0.003085784,0.00001663518,0.00003346277,0.000003702331,0.00004005854,0.00001197623,0.0009291801],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4986625,"threshold_uncertainty_score":0.61834,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2241126168","doi":"","title":"The adversarial stochastic shortest path problem with unknown transition probabilities","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Reinforcement learning; Shortest path problem; Computer science; Logarithm; State space; Mathematical optimization; Mathematics; Graph; Markov process; Artificial intelligence; Theoretical computer science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.06434972756859121,"gpt":0.3637676920026717,"spread":0.2994179644340805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002977577,0.0001655165,0.0001921136,0.00009832467,0.0005434271,0.0002876874,0.00056528,0.00005820289,0.0003530651],"category_scores_gemma":[0.0008517132,0.00007330171,0.00006645839,0.0006451419,0.0004844212,0.001009841,0.00007513092,0.0002295049,0.000243046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008333088,"about_ca_system_score_gemma":0.0001526719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002907114,"about_ca_topic_score_gemma":0.0001744489,"domain_scores_codex":[0.9962276,0.0002128997,0.0004116752,0.0003541097,0.002110003,0.0006837569],"domain_scores_gemma":[0.9963703,0.002316942,0.00008663452,0.0005543497,0.0004650058,0.0002067226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003659212,0.00194675,0.003979241,0.00004493809,0.0003031863,0.00003000471,0.03589255,0.2181226,0.0006472697,0.1430362,0.02297327,0.5693648],"study_design_scores_gemma":[0.009003382,0.004892909,0.01779954,0.0002132172,0.0001717683,0.0004210011,0.06305399,0.1886163,0.002202982,0.493261,0.2172256,0.00313839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01582341,0.0001866468,0.9742786,0.00188634,0.0003547717,0.001226383,0.00001557226,0.0001149176,0.00611339],"genre_scores_gemma":[0.9885115,0.000004254697,0.00584606,0.00004381794,0.0003620601,0.0001305036,0.000004008111,0.00001712318,0.005080652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9726881,"threshold_uncertainty_score":0.4179657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106233414","doi":"10.48550/arxiv.1205.0622","title":"No-Regret Learning in Extensive-Form Games with Imperfect Recall","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Recall; Computer science; Imperfect; Perfect information; Class (philosophy); Counterfactual thinking; Mathematical economics; Mathematics; Artificial intelligence; Psychology; Machine learning; Cognitive psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1408962463293117,"gpt":0.2858046201333195,"spread":0.1449083738040078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00165813,0.0002102825,0.0003291389,0.0005782013,0.0001942834,0.00007896851,0.0007355195,0.0001110744,0.000559491],"category_scores_gemma":[0.001737272,0.0001626162,0.00009452432,0.002128044,0.0002643971,0.001530126,0.0002875118,0.0005578948,0.001677785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002128728,"about_ca_system_score_gemma":0.00009908293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009535285,"about_ca_topic_score_gemma":0.0001300483,"domain_scores_codex":[0.99755,0.0003004426,0.0002438591,0.0006678925,0.0004498604,0.000787914],"domain_scores_gemma":[0.9973006,0.001136049,0.0001575566,0.0005988627,0.0004996705,0.0003072665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008713849,0.0002559694,0.8779716,0.00001322279,0.00005310358,0.0007545954,0.001097667,0.089749,0.0003938799,0.003868732,0.001299647,0.02367122],"study_design_scores_gemma":[0.007282253,0.001768998,0.5236578,0.0002022267,0.00006831569,0.0001546214,0.009135948,0.3154011,0.001865059,0.01764929,0.1206245,0.002189961],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9568207,0.00009505783,0.0335393,0.00005845133,0.0001687598,0.0002314604,0.000003336707,0.00008455871,0.008998344],"genre_scores_gemma":[0.9765587,0.00006942575,0.0004554025,0.00004897505,0.00009640031,8.470321e-7,0.00000248177,0.0000204032,0.02274732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3543138,"threshold_uncertainty_score":0.9990996,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110582581","doi":"10.48550/arxiv.1206.6457","title":"Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Exponential function; Mathematical economics; Applied mathematics; Mathematics; Gaussian; Process (computing); Gaussian process; Econometrics; Mathematical optimization; Statistical physics; Economics; Computer science; Statistics; Physics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.4019517217496925,"gpt":0.3403438641409024,"spread":0.06160785760879012,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001154892,0.0004544576,0.0006214497,0.000614698,0.0006109455,0.000410073,0.00227595,0.0003814909,0.0002483099],"category_scores_gemma":[0.001119863,0.0003861517,0.0002598037,0.001271235,0.0004985525,0.0008941838,0.0007865838,0.0006844122,0.0001284462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000262731,"about_ca_system_score_gemma":0.0007392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002880701,"about_ca_topic_score_gemma":0.0001668109,"domain_scores_codex":[0.9961184,0.000197749,0.0004982642,0.001624611,0.0007295111,0.0008314147],"domain_scores_gemma":[0.9949721,0.001137442,0.0006281201,0.001602561,0.001218006,0.0004417956],"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":[0.005265761,0.001829164,0.08460134,0.001091339,0.00109931,0.001494933,0.004952717,0.8265898,0.0001760463,0.05210849,0.008619096,0.01217204],"study_design_scores_gemma":[0.004878093,0.0006984707,0.03182301,0.0004491738,0.0006069489,0.0000529332,0.002587059,0.5084091,0.0005371974,0.4323353,0.0149858,0.002636936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2540251,0.00004959971,0.7424408,0.0001427039,0.0007253479,0.001198065,0.0003297789,0.0001179719,0.0009705576],"genre_scores_gemma":[0.9874266,0.00002142161,0.00209412,0.00003233045,0.0003948862,0.00002594721,0.0001252373,0.00005479125,0.009824689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7403467,"threshold_uncertainty_score":0.999859,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1569559301","doi":"10.1007/978-3-540-27819-1_46","title":"The Budgeted Multi-armed Bandit Problem","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Abstraction; Set (abstract data type); Mathematical optimization; Multi-armed bandit; Artificial intelligence; Operations research; Machine learning; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.07238701070652422,"gpt":0.3767942946054017,"spread":0.3044072838988775,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00531014,0.0006036992,0.0006738952,0.001141875,0.001114829,0.001659232,0.006657433,0.0003938449,0.000218164],"category_scores_gemma":[0.002796148,0.0003537197,0.0002287644,0.001628708,0.003650452,0.0005413105,0.00180966,0.001693863,0.0005389468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007549475,"about_ca_system_score_gemma":0.001529452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002961102,"about_ca_topic_score_gemma":0.0003845524,"domain_scores_codex":[0.9899113,0.0001105579,0.00113597,0.002161305,0.005434346,0.001246511],"domain_scores_gemma":[0.9907207,0.005093814,0.0005202977,0.002215745,0.001136509,0.0003128651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002190832,0.00002853887,0.00003826887,0.0000076959,0.00001116259,0.0001118755,0.0004376159,0.1163315,0.00005278017,0.001483771,0.00009168278,0.8813832],"study_design_scores_gemma":[0.0008092171,0.0001953489,0.0003147569,0.0002182437,0.000005832052,0.00005670367,0.000001306056,0.1547068,0.000925641,0.8213385,0.02073417,0.0006935218],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002476742,0.0008225557,0.9928694,0.001700288,0.001678614,0.0009210924,0.00001713958,0.00009058397,0.001875531],"genre_scores_gemma":[0.1624552,0.0005305138,0.8048841,0.00214974,0.002763513,0.0001313572,0.00002108413,0.0002635735,0.02680084],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8806897,"threshold_uncertainty_score":0.9998915,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969276875","doi":"10.1016/j.tcs.2014.09.029","title":"Near-optimal PAC bounds for discounted MDPs","year":2014,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Upper and lower bounds; Markov decision process; Logarithm; Sample complexity; Mathematics; Reinforcement learning; State space; Stochastic matrix; Markov chain; Matrix (chemical analysis); Space (punctuation); Markov process; Mathematical optimization; Applied mathematics; Combinatorics; Computer science; Statistics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.04680964409173786,"gpt":0.418173190851378,"spread":0.3713635467596401,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0102659,0.0002010489,0.0003404915,0.0002577129,0.001128494,0.001895366,0.003267357,0.00006454327,0.0002951193],"category_scores_gemma":[0.005638816,0.0001317964,0.0001277447,0.001898443,0.01001484,0.000813044,0.0009645198,0.0002417086,0.000415793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007674432,"about_ca_system_score_gemma":0.0002144769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001963391,"about_ca_topic_score_gemma":8.480578e-7,"domain_scores_codex":[0.9940432,0.0002155752,0.0005118966,0.001120045,0.003109525,0.0009997865],"domain_scores_gemma":[0.9934081,0.003937643,0.0001050587,0.001162785,0.0009205782,0.0004657753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007204263,0.00005991242,0.00009411832,0.000003085466,0.000003106158,0.000002604752,0.0002976786,0.003854122,0.0002526848,0.860999,0.0007684716,0.1335931],"study_design_scores_gemma":[0.0002754093,0.0003173349,0.0006071444,0.000006321325,0.000001948257,0.000009042983,0.00001784096,0.6586541,0.0009045144,0.3322718,0.006789017,0.0001455169],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04665288,0.000007926085,0.9491842,0.001522099,0.0006470817,0.0002910142,0.00001075557,0.0000805261,0.001603544],"genre_scores_gemma":[0.8297389,6.942789e-7,0.1694122,0.0003263806,0.0003304724,0.00001866684,0.000001433308,0.0000128614,0.0001583384],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7830861,"threshold_uncertainty_score":0.9991407,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951455820","doi":"","title":"Online Learning to Rank in Stochastic Click Models","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Learning to rank; Rank (graph theory); Regret; Machine learning; Online learning; Convergence (economics); Artificial intelligence; Range (aeronautics); Class (philosophy); Theoretical computer science; Ranking (information retrieval); Mathematics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.3577127700268318,"gpt":0.3531140666372869,"spread":0.004598703389544934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001959622,0.0003926125,0.0007681781,0.00153982,0.0003533145,0.0003406016,0.004061396,0.0003866181,0.0001854523],"category_scores_gemma":[0.0041886,0.0003993936,0.0002581699,0.001038745,0.000245821,0.0006473802,0.004457309,0.00197972,0.0007139656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004514724,"about_ca_system_score_gemma":0.0003439254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004150115,"about_ca_topic_score_gemma":0.0008108923,"domain_scores_codex":[0.9955888,0.0004325325,0.0005229362,0.002006571,0.0007186888,0.0007304902],"domain_scores_gemma":[0.9952799,0.001017472,0.0004598325,0.002190933,0.000625235,0.0004266052],"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":[0.0001391259,0.0001028622,0.000703137,0.000007225087,0.00001869376,0.000365014,0.0003493969,0.9918748,0.000005112718,0.0007330445,0.0002076545,0.005493996],"study_design_scores_gemma":[0.0006595529,0.00006169849,0.002044474,0.0001162287,0.00001303047,0.000002211864,0.0005580829,0.8280902,0.000004991114,0.1673565,0.000708146,0.0003848462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3627128,0.00005004293,0.634823,0.0001766819,0.0005664622,0.0005204321,0.0000569374,0.00007094208,0.001022694],"genre_scores_gemma":[0.9677402,0.00007363586,0.0007088899,0.00003691301,0.0001440005,0.000002181234,0.00002236212,0.00003653679,0.03123524],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6341141,"threshold_uncertainty_score":0.9998458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146807381","doi":"","title":"PAC-Bayesian Analysis of Contextual Bandits","year":2011,"lang":"la","type":"article","venue":"MPG.PuRe (Max Planck Society)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Regret; Logarithm; Upper and lower bounds; Scaling; Bayesian probability; Computer science; Task (project management); Combinatorics; Mathematics; Algorithm; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1328243330302454,"gpt":0.3771460626394505,"spread":0.2443217296092051,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003324958,0.0008113331,0.002324453,0.001062705,0.0005797992,0.0002751302,0.002668455,0.0009129,0.01404912],"category_scores_gemma":[0.001475158,0.0006783378,0.002388561,0.009074482,0.001433234,0.0008480049,0.0006548336,0.001223682,0.0007410471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002475991,"about_ca_system_score_gemma":0.0005755675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003493142,"about_ca_topic_score_gemma":0.0005564822,"domain_scores_codex":[0.9895065,0.0006123513,0.002102149,0.001836334,0.004257293,0.00168535],"domain_scores_gemma":[0.9921967,0.00240957,0.001190624,0.002121509,0.001320883,0.0007607531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.002346171,0.004867786,0.2433715,0.0005786284,0.03880424,0.001063153,0.1579727,0.004257509,0.003402789,0.007171271,0.3677955,0.1683687],"study_design_scores_gemma":[0.01514826,0.004632344,0.3654774,0.0007835436,0.01308016,0.000105246,0.1002825,0.2416027,0.01485556,0.03179546,0.2043531,0.00788369],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3133975,0.01532956,0.5645192,0.002086153,0.008075756,0.004816557,0.01110442,0.0007230752,0.07994782],"genre_scores_gemma":[0.9787253,0.0005707167,0.006141969,0.0003293398,0.0005233282,0.0000278094,0.0001665953,0.00009034664,0.01342464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6653277,"threshold_uncertainty_score":0.9995668,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135829225","doi":"10.1109/gamenets.2009.5137416","title":"Online learning in Markov decision processes with arbitrarily changing rewards and transitions","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Regret; Computer science; Markov chain; Transition (genetics); Decision maker; Markov process; Range (aeronautics); Trajectory; Control (management); Online learning; Mathematical optimization; Artificial intelligence; Machine learning; Mathematics; Operations research; Statistics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04799188361605175,"gpt":0.3932287474444243,"spread":0.3452368638283726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001231568,0.0001379446,0.0002429138,0.0009241845,0.0002135271,0.000204029,0.0002736771,0.00005863066,0.0001495617],"category_scores_gemma":[0.002478128,0.00008834984,0.00002373729,0.002890507,0.00008782669,0.0006696425,0.0000419618,0.0003379284,0.00001402213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003345326,"about_ca_system_score_gemma":0.0001566934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009752012,"about_ca_topic_score_gemma":0.0006395647,"domain_scores_codex":[0.9974195,0.00007680108,0.0003570584,0.00050843,0.001226607,0.0004116319],"domain_scores_gemma":[0.9980451,0.001218115,0.00006060295,0.0002217706,0.0003282385,0.0001261349],"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":[0.0003456699,0.000283091,0.003382374,0.00001367533,0.000005737496,0.0001394706,0.002288145,0.008832759,0.0002736459,0.0001406286,0.0001391608,0.9841557],"study_design_scores_gemma":[0.01078174,0.005118829,0.5122403,0.001560623,0.00003650938,0.0007101194,0.04888381,0.2200656,0.004341031,0.1756793,0.01825636,0.002325839],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5296431,0.0003424833,0.4646851,0.002681282,0.00002410777,0.0002618881,0.00000769984,0.00009047304,0.002263834],"genre_scores_gemma":[0.9477227,0.0001252111,0.04992584,0.0002199005,0.00004762978,0.000006486533,0.000005846547,0.00001010323,0.001936234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9818298,"threshold_uncertainty_score":0.3602802,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810504435","doi":"10.1109/access.2018.2850879","title":"A Multi-Domain Anti-Jamming Defense Scheme in Heterogeneous Wireless Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Jamming; Computer science; Power domains; Stackelberg competition; Channel (broadcasting); Wireless; Frequency domain; Computer network; Logarithm; Domain (mathematical analysis); Power (physics); Mathematical optimization; Telecommunications; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1625277235217346,"gpt":0.4640437230106479,"spread":0.3015159994889133,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002357392,0.0002611593,0.0004717179,0.0005982381,0.0002927054,0.0007157733,0.002319501,0.0001832195,0.000264349],"category_scores_gemma":[0.0008723973,0.0002130446,0.0001177803,0.002232624,0.000504234,0.001070961,0.0005755471,0.0004245375,0.0004807397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001222501,"about_ca_system_score_gemma":0.00009394437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001356346,"about_ca_topic_score_gemma":0.001087583,"domain_scores_codex":[0.9954634,0.0003390515,0.0007849504,0.0009723946,0.001496283,0.0009438819],"domain_scores_gemma":[0.9971382,0.000976267,0.0002258242,0.0008968362,0.0005235402,0.0002393012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008240364,0.001220811,0.3496886,0.00004006835,0.0001408093,0.003461173,0.003130062,0.09214539,0.01919551,0.00007186781,0.0061385,0.5239432],"study_design_scores_gemma":[0.002874254,0.0002149836,0.02385244,0.0001046982,0.000005538033,0.000123754,0.0004023675,0.940993,0.02067146,0.004225096,0.00566751,0.0008649067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6783255,0.0001127019,0.3203451,0.0000822525,0.0007046404,0.0002655656,0.000005839885,0.00004941436,0.0001089746],"genre_scores_gemma":[0.9917893,0.00003098185,0.006997591,0.0002156027,0.0005829115,0.00004117454,0.000001978712,0.00003998768,0.0003004681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8488476,"threshold_uncertainty_score":0.8687705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W659523800","doi":"","title":"Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Algorithm; Logarithm; Stochastic process; Adversarial system; Artificial intelligence; Mathematical optimization; Mathematics; Machine learning; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.07402534430139121,"gpt":0.3945074600203065,"spread":0.3204821157189153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002647249,0.0000608858,0.0001796711,0.0002470589,0.00005867449,0.00002048089,0.0005407099,0.00002928917,0.0008780953],"category_scores_gemma":[0.001032745,0.00002669012,0.00006599887,0.001735046,0.0002567851,0.0002437413,0.0002738545,0.00008642006,0.00001509483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004566226,"about_ca_system_score_gemma":0.00003903714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008975736,"about_ca_topic_score_gemma":0.00004746301,"domain_scores_codex":[0.9964492,0.0002770592,0.0003899196,0.0002023005,0.002555357,0.0001261573],"domain_scores_gemma":[0.9985639,0.0005111185,0.0001800472,0.0005512491,0.0001683426,0.00002533499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005488374,0.00008487834,0.09414473,0.000001756388,0.0001080869,4.346863e-8,0.0007668289,0.2249738,0.002294933,0.00001166311,0.0000564677,0.6775513],"study_design_scores_gemma":[0.0001090703,0.00001150384,0.4605617,0.000002756125,0.00002777864,1.280447e-7,0.0001931024,0.5371946,0.00129535,0.0005806789,0.000004949381,0.00001840015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665046,0.00005818763,0.03271622,0.0001215425,0.00004254161,0.0004299119,0.000005378242,0.000001024864,0.0001205844],"genre_scores_gemma":[0.9984183,0.000008307662,0.0007220399,0.00001294388,0.000004405953,0.00002769964,4.272683e-7,0.000002502,0.000803338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6775329,"threshold_uncertainty_score":0.9614528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2187589363","doi":"10.1609/aaai.v28i1.8891","title":"Online (Budgeted) Social Choice","year":2014,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Cardinality (data modeling); Regret; Set (abstract data type); Decision maker; Combinatorics; Social choice theory; Matching (statistics); Contrast (vision); Selection (genetic algorithm); Order (exchange); Mathematics; Computer science; Binary logarithm; Mathematical optimization; Mathematical economics; Discrete mathematics; Artificial intelligence; Data mining; Operations research; Machine learning; Statistics; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.2875956122926702,"gpt":0.4538000765792046,"spread":0.1662044642865344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002414726,0.0002718146,0.0004649403,0.0003088675,0.0004759954,0.0003892644,0.003409306,0.0001490546,0.0006361448],"category_scores_gemma":[0.01464825,0.0001759528,0.0002283501,0.001674155,0.0008326069,0.0004484412,0.0005901471,0.0006102932,0.0005894009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006259482,"about_ca_system_score_gemma":0.0001049986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004329549,"about_ca_topic_score_gemma":0.00005230113,"domain_scores_codex":[0.994979,0.00007568267,0.001055644,0.0007613453,0.002564765,0.0005635642],"domain_scores_gemma":[0.9950876,0.001150546,0.000679301,0.0004250294,0.002504699,0.0001528858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001613487,0.0004877385,0.0008076768,0.00002117835,0.00002060048,3.699438e-7,0.001088233,0.0001828153,0.02474101,0.3331139,0.002610164,0.6367649],"study_design_scores_gemma":[0.00007173569,0.0003111671,0.004103135,0.00007921059,0.00001338207,0.00000324201,0.001774964,0.06441732,0.2213124,0.7000245,0.007523799,0.0003651225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8475081,0.00004127652,0.05864337,0.03363112,0.002013809,0.001464793,0.0001078896,0.0002681633,0.05632154],"genre_scores_gemma":[0.996085,0.000009334422,0.00102571,0.0003075963,0.0004802538,0.00001719164,0.000001090703,0.00002185704,0.002051914],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6363998,"threshold_uncertainty_score":0.9936518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}