{"meta":{"query_hash":"a2addb5837d6","filters":{"topic":"Advanced Bandit Algorithms Research"},"cohort_total":436,"direct_labels_cover":1,"predictions_cover":436,"exported":436,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/a2addb5837d6","api":"https://metacan.xera.ac/api/v1/cohort?topic=Advanced+Bandit+Algorithms+Research"},"results":[{"id":"W100039866","doi":"","title":"The Online Loop-free Stochastic Shortest-Path Problem.","year":2010,"lang":"en","type":"article","venue":"SZTAKI Publication Repository (Hungarian Academy of Sciences)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Shortest path problem; Regret; Mathematics; Asymptotically optimal algorithm; Path (computing); Graph; Action (physics); State (computer science); Combinatorics; Mathematical optimization; Hindsight bias; Discrete mathematics; Computer science; Algorithm","score_opus":0.07004419195070641,"score_gpt":0.3992770809796929,"score_spread":0.3292328890289865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W100039866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35507107,0.0019400098,0.20173447,0.34436214,0.0076883505,0.009985682,0.0005103617,0.0014615093,0.077246405],"genre_scores_gemma":[0.96753585,0.000015383775,0.017618924,0.0004968641,0.0007926121,0.0001458504,0.0000073677743,0.00003381212,0.013353335],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99047214,0.00037673794,0.0017445592,0.0013329521,0.005212147,0.0008614577],"domain_scores_gemma":[0.9922229,0.0032366791,0.0013283548,0.0013230899,0.0014129756,0.00047599955],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["sts"],"category_scores_codex":[0.010650638,0.0002960356,0.00039492056,0.0007145578,0.0022209529,0.0013474767,0.008261663,0.0003216101,0.00013657907],"category_scores_gemma":[0.015214064,0.00018672898,0.00018355614,0.003998686,0.0038079428,0.001941271,0.000872332,0.0014671888,0.0001275966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022774139,0.0015004625,0.015976787,0.000032145585,0.00014514763,0.000009495171,0.001365424,0.008154655,0.17845502,0.31627044,0.1402333,0.3376294],"study_design_scores_gemma":[0.0021921275,0.0006666035,0.18940164,0.00008901297,0.00006698066,0.0005405506,0.002674771,0.21044594,0.01875861,0.36333212,0.21028087,0.0015507692],"about_ca_topic_score_codex":0.00003106736,"about_ca_topic_score_gemma":0.00003538653,"teacher_disagreement_score":0.6124648,"about_ca_system_score_codex":0.00007493615,"about_ca_system_score_gemma":0.00071295607,"threshold_uncertainty_score":0.9996892},"labels":[],"label_agreement":null},{"id":"W1506389236","doi":"10.1109/ccece.2015.7129466","title":"An estimation based allocation rule with super-linear regret and finite lock-on time for time-dependent multi-armed bandit processes","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Mathematical optimization; Index (typography); Markov decision process; Multi-armed bandit; Computer science; Upper and lower bounds; Process (computing); Moving average; Markov chain; Markov process; Mathematics; Statistics; Machine learning","score_opus":0.12708405197254166,"score_gpt":0.4245114426048841,"score_spread":0.29742739063234247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506389236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035989,0.000037887618,0.9618302,0.00069747266,0.00003995917,0.0010375228,0.000069736576,0.00012879883,0.00016941194],"genre_scores_gemma":[0.7270252,0.00000512364,0.25934547,0.00026343472,0.00013806894,0.00025415423,0.00031376758,0.00006477688,0.012590023],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966443,0.00014923092,0.00040979232,0.0007238566,0.0017261576,0.00034667228],"domain_scores_gemma":[0.9953917,0.0018619904,0.00014910469,0.0005575663,0.0017072463,0.0003323865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002160389,0.00021825901,0.00028591297,0.000345301,0.0001917389,0.000301524,0.00043172427,0.00010214889,0.00028855714],"category_scores_gemma":[0.0060874484,0.0001402157,0.000026704369,0.0006177689,0.00015582038,0.0010175459,0.000044602504,0.00012124481,0.00061599986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029835573,0.0011422286,0.0018940984,0.0000988696,0.000045493867,0.00002142906,0.001284376,0.89035076,0.0019260149,0.000036916943,0.004298699,0.095917575],"study_design_scores_gemma":[0.0026868782,0.0011398139,0.00027230717,0.00002714421,0.00001007425,0.0000051333914,0.00021904858,0.97992986,0.01340671,0.0013636143,0.0007157273,0.00022368523],"about_ca_topic_score_codex":0.000022993909,"about_ca_topic_score_gemma":0.000055596953,"teacher_disagreement_score":0.7024847,"about_ca_system_score_codex":0.000087016284,"about_ca_system_score_gemma":0.00044484867,"threshold_uncertainty_score":0.7917638},"labels":[],"label_agreement":null},{"id":"W1540112079","doi":"10.5555/1402821.1402866","title":"Using adaptive consultation of experts to improve convergence rates in multiagent learning","year":2008,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Regret; Computer science; Outcome (game theory); Convergence (economics); Advice (programming); Multi-agent system; Set (abstract data type); Class (philosophy); Nash equilibrium; Process (computing); Frame (networking); Order (exchange); Artificial intelligence; Machine learning; Mathematical optimization; Mathematics","score_opus":0.367641049994208,"score_gpt":0.4650858587974098,"score_spread":0.09744480880320183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1540112079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8197591,0.0007808242,0.17714377,0.000013888059,0.0006300095,0.0015319034,0.000049875583,0.000022101585,0.000068566835],"genre_scores_gemma":[0.99175745,0.00023576836,0.0063284477,0.00003332399,0.000052217703,0.00009751283,0.000004917284,0.00003124081,0.0014591061],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950941,0.0006916448,0.0011726994,0.0009642953,0.0014996672,0.00057757384],"domain_scores_gemma":[0.99681085,0.0009305387,0.0005401592,0.000376847,0.0010159275,0.00032567422],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013806135,0.00032500655,0.00067517196,0.0006197505,0.00033084746,0.00008605754,0.0004379018,0.00012789338,0.00007067435],"category_scores_gemma":[0.0023008855,0.00026559297,0.000089831294,0.0009860127,0.0002778324,0.0006866425,0.00031724395,0.00022771313,0.00006998549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019909611,0.0016119785,0.2587844,0.00012429756,0.00047720684,0.00096953666,0.0912426,0.5048854,0.09240387,0.00022129092,0.0010347406,0.04625373],"study_design_scores_gemma":[0.0030031467,0.0003891104,0.055269748,0.00022472885,0.000010675572,0.000024249097,0.027378341,0.9081517,0.004278557,0.000026724281,0.00083297753,0.00041004346],"about_ca_topic_score_codex":0.0023187057,"about_ca_topic_score_gemma":0.000086690176,"teacher_disagreement_score":0.40326634,"about_ca_system_score_codex":0.00019361575,"about_ca_system_score_gemma":0.0001270729,"threshold_uncertainty_score":0.9999796},"labels":[],"label_agreement":null},{"id":"W1545471058","doi":"10.1007/11776420_39","title":"Online Learning with Constraints","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hindsight bias; Convex hull; Computer science; Path (computing); Decision maker; Mathematical optimization; Constraint (computer-aided design); Term (time); Function (biology); Online learning; Regular polygon; Artificial intelligence; Operations research; Mathematics","score_opus":0.05701351581155001,"score_gpt":0.3661818562238235,"score_spread":0.3091683404122735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1545471058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027639818,0.00018789255,0.99119914,0.0003664058,0.00045107183,0.00031834858,0.000023089695,0.00007794298,0.0070996857],"genre_scores_gemma":[0.40408197,0.000041925286,0.5669542,0.0008544135,0.0019214523,0.000011631535,0.000054289234,0.00014968555,0.02593042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9918662,0.00007412437,0.000746382,0.0018856929,0.0045966343,0.0008309849],"domain_scores_gemma":[0.9946437,0.0027264713,0.00041960477,0.0010846072,0.0009143707,0.00021123308],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0023353302,0.0004933359,0.000687374,0.0015461646,0.00036291135,0.0006863947,0.0027878992,0.00028129306,0.00038138928],"category_scores_gemma":[0.0012199088,0.00033681007,0.00010932012,0.0012354896,0.004078715,0.0004441993,0.00083428924,0.0018246085,0.00018286901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010328649,0.00002271007,0.00023220282,0.000003697719,0.0000040325945,0.00020038137,0.00008334239,0.3114365,0.000014172635,0.00014763798,0.00004374131,0.68780124],"study_design_scores_gemma":[0.0012363121,0.0009661843,0.0021754606,0.00068643724,0.0000139667345,0.0004633297,0.0000039255387,0.6471535,0.0006926398,0.31576863,0.029092567,0.001747069],"about_ca_topic_score_codex":0.000020598305,"about_ca_topic_score_gemma":0.00023006939,"teacher_disagreement_score":0.68605417,"about_ca_system_score_codex":0.00028946274,"about_ca_system_score_gemma":0.0007348454,"threshold_uncertainty_score":0.9999084},"labels":[],"label_agreement":null},{"id":"W1564634725","doi":"10.1007/11776420_31","title":"Online Learning with Variable Stage Duration","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Stochastic game; Hindsight bias; Regret; Repeated game; Computer science; Minimax; Mathematical economics; Variable (mathematics); Duration (music); Term (time); Game theory; Mathematics; Machine learning; Psychology","score_opus":0.048767061172971984,"score_gpt":0.3533309066974802,"score_spread":0.3045638455245082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564634725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023228847,0.00013869422,0.99373,0.00025189584,0.00043193615,0.00034632182,0.000024900171,0.000077830526,0.0047661215],"genre_scores_gemma":[0.06337418,0.000031327374,0.8595313,0.00050078245,0.0015479737,0.000013443524,0.00009011082,0.00011519445,0.07479571],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925017,0.00008192599,0.0007909642,0.0016941045,0.0042306697,0.00070068694],"domain_scores_gemma":[0.99525493,0.0020658416,0.0005039021,0.0010518478,0.0009692887,0.00015416926],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002787314,0.00042935586,0.00055450614,0.0013471144,0.00043445153,0.00088665663,0.0021291978,0.00026442893,0.00032817086],"category_scores_gemma":[0.0012583268,0.00029938927,0.00006941556,0.0015404489,0.0010234175,0.0007660939,0.00068237906,0.0014715238,0.00010259109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001610694,0.000025646625,0.00016404806,0.0000064455244,0.0000036038311,0.000078193094,0.000094408635,0.77032554,0.000057045538,0.0004178814,0.000040537365,0.22877055],"study_design_scores_gemma":[0.00045166377,0.00042920056,0.00052223215,0.00021101901,0.0000056443455,0.00005116641,0.0000015157888,0.8527621,0.0004841783,0.110204995,0.034215465,0.00066079595],"about_ca_topic_score_codex":0.000060364975,"about_ca_topic_score_gemma":0.0003094176,"teacher_disagreement_score":0.22810976,"about_ca_system_score_codex":0.00035253773,"about_ca_system_score_gemma":0.00071345194,"threshold_uncertainty_score":0.9999458},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07238701070652422,"score_gpt":0.3767942946054017,"score_spread":0.3044072838988775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569559301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024767423,0.00082255574,0.99286944,0.0017002877,0.0016786141,0.0009210924,0.00001713958,0.00009058397,0.001875531],"genre_scores_gemma":[0.16245525,0.0005305138,0.80488414,0.00214974,0.0027635125,0.00013135718,0.000021084126,0.0002635735,0.02680084],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9899113,0.000110557936,0.0011359701,0.0021613052,0.0054343464,0.0012465114],"domain_scores_gemma":[0.99072075,0.005093814,0.0005202977,0.0022157454,0.0011365092,0.00031286507],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00531014,0.0006036992,0.0006738952,0.0011418747,0.0011148293,0.0016592323,0.006657433,0.0003938449,0.000218164],"category_scores_gemma":[0.0027961477,0.00035371972,0.00022876445,0.001628708,0.0036504525,0.0005413105,0.0018096602,0.0016938632,0.00053894677],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021908318,0.000028538874,0.000038268867,0.0000076959,0.000011162589,0.000111875466,0.00043761593,0.116331495,0.000052780168,0.0014837706,0.000091682785,0.8813832],"study_design_scores_gemma":[0.0008092171,0.0001953489,0.00031475688,0.00021824375,0.0000058320516,0.00005670367,0.000001306056,0.15470679,0.000925641,0.8213385,0.020734169,0.00069352175],"about_ca_topic_score_codex":0.00002961102,"about_ca_topic_score_gemma":0.00038455243,"teacher_disagreement_score":0.8806897,"about_ca_system_score_codex":0.00075494754,"about_ca_system_score_gemma":0.0015294518,"threshold_uncertainty_score":0.99989146},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.07038242003984675,"score_gpt":0.3665795994389151,"score_spread":0.29619717939906837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577851669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021899166,0.00024118074,0.995196,0.00022616102,0.0013757041,0.00031818383,0.000007009869,0.000053528995,0.0023632392],"genre_scores_gemma":[0.66568816,0.00007059826,0.3291735,0.00037581872,0.003453924,0.00002883541,0.000009481661,0.000059023794,0.0011406497],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99339527,0.000038629816,0.0006879632,0.00075184676,0.0043547675,0.00077155355],"domain_scores_gemma":[0.9961013,0.0014188783,0.0003869868,0.0010953251,0.0007427329,0.00025474056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025660144,0.0003610972,0.00043629933,0.001258658,0.0002954704,0.0008798486,0.0021294905,0.00022570316,0.00010858164],"category_scores_gemma":[0.0008787677,0.0002445064,0.00007478316,0.00089960743,0.0009081747,0.0027598115,0.00077511,0.0008828966,0.0005192742],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018305838,0.0000061682176,0.00043700272,0.000004878087,0.0000035876592,0.000014778633,0.0004874066,0.0680882,0.00001473089,0.00020406679,0.000007859953,0.930713],"study_design_scores_gemma":[0.0020101974,0.0011186854,0.007324367,0.001184528,0.00003588248,0.00038107246,0.000011890296,0.43886012,0.02440495,0.41129795,0.109953925,0.0034164211],"about_ca_topic_score_codex":0.000013854209,"about_ca_topic_score_gemma":0.000019867826,"teacher_disagreement_score":0.9272966,"about_ca_system_score_codex":0.00031203724,"about_ca_system_score_gemma":0.00046849638,"threshold_uncertainty_score":0.99706817},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.22064056196574067,"score_gpt":0.3089465051702611,"score_spread":0.08830594320452045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1675620121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037680503,0.000036093865,0.9928875,0.00008048776,0.0006725388,0.00046527095,0.00006276081,0.00016504465,0.0018622298],"genre_scores_gemma":[0.9229508,0.000107309745,0.059445944,0.00005495305,0.00019090396,0.0000024085973,0.00005815583,0.000051539777,0.017137976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995625,0.00055185525,0.0005468131,0.002014232,0.00065304124,0.0006090535],"domain_scores_gemma":[0.99502045,0.0009575991,0.00051762286,0.0021424594,0.0009310559,0.00043083812],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015504531,0.00042921145,0.0006465802,0.0008053701,0.00032706012,0.00034604903,0.0027234186,0.00050202035,0.0011954171],"category_scores_gemma":[0.0017128999,0.0004260814,0.0003332335,0.001239546,0.0003859529,0.00038693933,0.002119892,0.00095331995,0.00076934265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045691802,0.000084167106,0.0008325715,0.000016954094,0.00002703534,0.00010417793,0.00006543469,0.9970271,0.000005299088,0.00021562734,0.0005517053,0.001024231],"study_design_scores_gemma":[0.00066043326,0.00004153661,0.00037513595,0.000041152445,0.00003970184,0.0000038056658,0.00016407654,0.98507845,0.000043696746,0.012315165,0.0007835017,0.000453363],"about_ca_topic_score_codex":0.00006753765,"about_ca_topic_score_gemma":0.000059706697,"teacher_disagreement_score":0.9334416,"about_ca_system_score_codex":0.0003484308,"about_ca_system_score_gemma":0.00026496084,"threshold_uncertainty_score":0.9998191},"labels":[],"label_agreement":null},{"id":"W169239147","doi":"10.5220/0002712500360044","title":"A GENERIC SOLUTION TO MULTI-ARMED BERNOULLI BANDIT PROBLEMS BASED ON RANDOM SAMPLING FROM SIBLING CONJUGATE PRIORS","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Conjugate prior; Bernoulli's principle; Conjugate; Prior probability; Computer science; Thompson sampling; Sampling (signal processing); Mathematics; Mathematical optimization; Algorithm; Bayesian probability; Artificial intelligence; Engineering; Telecommunications","score_opus":0.20640621805017811,"score_gpt":0.43735276582573485,"score_spread":0.23094654777555673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W169239147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21491787,0.000022379869,0.7816421,0.0009915557,0.0008280747,0.0010143083,0.00005210146,0.00014295994,0.00038863925],"genre_scores_gemma":[0.81824905,0.0000070228916,0.17867547,0.00067363074,0.000369542,0.00014704182,0.000033820874,0.000048317695,0.0017960916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99423265,0.00023388777,0.00090308033,0.0012233254,0.002578946,0.00082811964],"domain_scores_gemma":[0.9935817,0.0039436007,0.00023077583,0.0010971978,0.00061410386,0.00053262414],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003500623,0.00032438905,0.00052609603,0.00091496255,0.0004902216,0.0005940899,0.0011023593,0.00019877871,0.0020540832],"category_scores_gemma":[0.0072572753,0.00023137071,0.00018825328,0.0016563071,0.00015851129,0.0004267085,0.00024603633,0.0006832969,0.001643434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014843326,0.0006438203,0.0068863365,0.000014026992,0.000060361708,0.000036156467,0.0014422289,0.5655408,0.30564427,0.000069971975,0.0028985178,0.11527915],"study_design_scores_gemma":[0.006353167,0.00020361724,0.0066036037,0.000041875268,0.000011335563,0.0000022103081,0.00020560749,0.94899774,0.01778578,0.0023873139,0.016912,0.00049572624],"about_ca_topic_score_codex":0.00048589832,"about_ca_topic_score_gemma":0.0019241908,"teacher_disagreement_score":0.6033312,"about_ca_system_score_codex":0.0001064228,"about_ca_system_score_gemma":0.0002176258,"threshold_uncertainty_score":0.9991339},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3788463044400635,"score_gpt":0.44604060495732645,"score_spread":0.06719430051726294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1838526237","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02138115,0.00015839304,0.7890342,0.0031359238,0.0021211295,0.0016452398,0.000008173848,0.00028774037,0.18222806],"genre_scores_gemma":[0.92374957,0.000016869477,0.035858482,0.00025822083,0.000120582255,0.000084484556,0.0000017226199,0.000016662174,0.039893407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912472,0.000091267095,0.00045322275,0.0010627022,0.006355248,0.00079035514],"domain_scores_gemma":[0.99739707,0.00020129363,0.00014129867,0.001165965,0.00058998977,0.00050436496],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010532931,0.00015673751,0.00019305073,0.000962803,0.0004094267,0.00081825803,0.0033220518,0.000029286932,0.00028368065],"category_scores_gemma":[0.0024515633,0.00011136611,0.000050732404,0.0049555893,0.0009855174,0.0015361189,0.0014177805,0.00015074096,0.0029907392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083200815,0.0005008272,0.014426088,0.00003265156,0.000034593504,0.0003077593,0.0026544505,0.44685158,0.0005004461,0.0123812575,0.10335333,0.41887382],"study_design_scores_gemma":[0.0027856526,0.0002898595,0.03959691,0.00004416171,0.000014024789,0.000020561241,0.0059402892,0.36175963,0.0012885213,0.09879869,0.48863885,0.0008228597],"about_ca_topic_score_codex":0.00001755271,"about_ca_topic_score_gemma":0.000016695432,"teacher_disagreement_score":0.9023684,"about_ca_system_score_codex":0.00023405011,"about_ca_system_score_gemma":0.000114335366,"threshold_uncertainty_score":0.99778557},"labels":[],"label_agreement":null},{"id":"W1844882231","doi":"10.1007/978-3-540-72606-7_71","title":"Reinforcement Learning-Based Load Shared Sequential Routing","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Learning automata; Reinforcement learning; Static routing; Distributed computing; Destination-Sequenced Distance Vector routing; Routing (electronic design automation); Link-state routing protocol; Dynamic Source Routing; Blocking (statistics); Artificial intelligence; Automaton; Computer network; Routing protocol","score_opus":0.10729862514666907,"score_gpt":0.39573778242917695,"score_spread":0.2884391572825079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1844882231","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030363937,0.00017589328,0.99059284,0.00029463688,0.0014068088,0.0005205919,0.0000059966446,0.00011167966,0.0068612196],"genre_scores_gemma":[0.7177403,0.000028744846,0.2565452,0.002384845,0.0028972772,0.000025198815,0.000051435774,0.00018456184,0.020142449],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9864222,0.000095405834,0.001332682,0.0022264149,0.008619256,0.0013040553],"domain_scores_gemma":[0.99280536,0.0030699703,0.0006962092,0.0014854375,0.0015954296,0.00034760492],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008893516,0.0006129182,0.0007510446,0.0019227169,0.00061899325,0.0012062483,0.0038769569,0.00045010578,0.00109439],"category_scores_gemma":[0.0043698004,0.0005005265,0.00026340084,0.0015301034,0.0014370228,0.0006003957,0.0015259035,0.0020518566,0.0005287231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027007794,0.000008202525,0.00004656745,0.0000058820365,0.0000045886527,0.00012582663,0.00020303355,0.67945164,0.00003641733,0.00013471452,0.000025178886,0.31993094],"study_design_scores_gemma":[0.00054379494,0.00026742992,0.000065113745,0.00024550426,0.000005514471,0.000022585687,9.0554494e-7,0.9532664,0.0016814752,0.031395502,0.011866118,0.0006396563],"about_ca_topic_score_codex":0.000050953633,"about_ca_topic_score_gemma":0.00018095,"teacher_disagreement_score":0.73404765,"about_ca_system_score_codex":0.0014640396,"about_ca_system_score_gemma":0.0020486934,"threshold_uncertainty_score":0.9998306},"labels":[],"label_agreement":null},{"id":"W1868011046","doi":"","title":"On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oracle; Set (abstract data type); Exploit; Computer science; Quality (philosophy); Mathematical optimization; Identification (biology); Mathematics; Theoretical computer science","score_opus":0.2028115132751566,"score_gpt":0.4445514399849025,"score_spread":0.2417399267097459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1868011046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50949216,0.00016323851,0.39912227,0.009497384,0.008801813,0.0011662252,0.0002092891,0.00022951039,0.07131813],"genre_scores_gemma":[0.9897661,0.000025478492,0.000817506,0.00013926766,0.0001284566,0.000018721268,0.000065547174,0.000023146542,0.009015755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99493396,0.00048428826,0.00057738303,0.0006533775,0.0030107673,0.0003402196],"domain_scores_gemma":[0.997745,0.0011603558,0.00027490445,0.0003532257,0.0002714167,0.00019511371],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016355048,0.00022705608,0.00027176848,0.00073072565,0.00014941688,0.0005032125,0.0011643206,0.000107949294,0.0016811783],"category_scores_gemma":[0.0049131964,0.00019496451,0.000077282835,0.00040373305,0.00010573858,0.00045952376,0.0003149684,0.0010775878,0.0015184749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048788093,0.00035023468,0.014524391,0.0000021834078,0.000061284074,0.00008246332,0.00076442247,0.80529636,0.0014042042,0.14921935,0.00019615423,0.027611068],"study_design_scores_gemma":[0.0034075317,0.00046799303,0.024563571,0.000094313924,0.0000042222923,0.000008363375,0.0009916004,0.4997863,0.00037042773,0.4645422,0.0053773746,0.00038610245],"about_ca_topic_score_codex":0.00012002351,"about_ca_topic_score_gemma":0.00017232313,"teacher_disagreement_score":0.480274,"about_ca_system_score_codex":0.00038164438,"about_ca_system_score_gemma":0.00012872416,"threshold_uncertainty_score":0.99925894},"labels":[],"label_agreement":null},{"id":"W189728362","doi":"10.1007/978-3-642-40988-2_16","title":"Greedy Confidence Pursuit: A Pragmatic Approach to Multi-bandit Optimization","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Greedy algorithm; Selection (genetic algorithm); Set (abstract data type); Thompson sampling; Mathematical optimization; Baseline (sea); Artificial intelligence; Machine learning; Algorithm; Bayesian probability; Mathematics","score_opus":0.08883393490227826,"score_gpt":0.3708055884183275,"score_spread":0.28197165351604925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W189728362","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010807673,0.00022726531,0.9917895,0.00061225396,0.0010704915,0.0018259109,0.000021773552,0.000093990464,0.0043480084],"genre_scores_gemma":[0.011687762,0.000025485584,0.97930306,0.0009543839,0.0004928992,0.00009709096,0.000014944327,0.00007169077,0.007352695],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9889425,0.00013900273,0.0012338253,0.002695267,0.005914768,0.0010746596],"domain_scores_gemma":[0.99264765,0.0024658826,0.0005551588,0.0021989779,0.0015960073,0.000536328],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0044970047,0.00067823485,0.000942084,0.0024088386,0.0004242995,0.0020203446,0.0061793504,0.00042704627,0.00060966634],"category_scores_gemma":[0.0045446903,0.00051918306,0.00016497383,0.0021137642,0.0013692887,0.0011540923,0.0018561471,0.0011244746,0.0012154847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007267389,0.000041195886,0.000009456893,0.000015247055,0.0000056694544,0.000017524577,0.0006268963,0.79373527,0.000023856881,0.0006542605,0.00015005605,0.20471333],"study_design_scores_gemma":[0.0003440282,0.00015601564,0.000078435914,0.00019222684,0.0000057258344,0.000058429807,0.0000024672079,0.9379899,0.00014252907,0.05918803,0.001226376,0.00061584415],"about_ca_topic_score_codex":0.00004616289,"about_ca_topic_score_gemma":0.000048405014,"teacher_disagreement_score":0.20409748,"about_ca_system_score_codex":0.00049061613,"about_ca_system_score_gemma":0.0007180935,"threshold_uncertainty_score":0.999726},"labels":[],"label_agreement":null},{"id":"W1915057100","doi":"10.1007/978-3-319-11662-4_13","title":"Bayesian Reinforcement Learning with Exploration","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Reinforcement learning; Computer science; Minimax; Sample complexity; Bayesian probability; Class (philosophy); Artificial intelligence; Sample (material); Machine learning; Mathematical optimization; Mathematics","score_opus":0.06435445389814211,"score_gpt":0.3528636545911634,"score_spread":0.28850920069302133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1915057100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012269177,0.000053891352,0.9932496,0.0005718725,0.0004718661,0.00040152264,8.2856883e-7,0.00006517885,0.005172972],"genre_scores_gemma":[0.6627947,0.00006120461,0.31254172,0.00091644784,0.0014950901,0.00003962478,0.000021639951,0.000113666334,0.02201591],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99225897,0.00008657784,0.0007205807,0.0015695652,0.0047005326,0.000663777],"domain_scores_gemma":[0.9956976,0.0016295312,0.0004653451,0.0011997967,0.0007927124,0.00021501064],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003527156,0.00042443935,0.0005493574,0.0014340951,0.0004400422,0.00085039175,0.0021769954,0.00021683142,0.0002632183],"category_scores_gemma":[0.0011987496,0.0002913814,0.00008569844,0.0009793263,0.0010099929,0.00077640975,0.00071084726,0.0011332699,0.00026691507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012920384,0.0000024716273,0.000025734398,0.0000034130294,0.0000024670373,0.00002013568,0.00024522407,0.5817076,0.000009550692,0.00047237225,0.000013081928,0.41748506],"study_design_scores_gemma":[0.00027759158,0.0005022202,0.000024111598,0.00017758945,0.000003459296,0.000023445993,0.0000014282897,0.85762954,0.0004938569,0.12905262,0.011382062,0.0004320537],"about_ca_topic_score_codex":0.000010431379,"about_ca_topic_score_gemma":0.00010801865,"teacher_disagreement_score":0.6807079,"about_ca_system_score_codex":0.0003236222,"about_ca_system_score_gemma":0.00045902046,"threshold_uncertainty_score":0.9999538},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3651976247050544,"score_gpt":0.5253249721812989,"score_spread":0.16012734747624452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W191658262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068386407,0.00018353808,0.86885697,0.010932399,0.0004132479,0.00030059266,0.000014908204,0.00016980366,0.11228992],"genre_scores_gemma":[0.71328706,0.000016915295,0.19515553,0.0009562553,0.0006839443,0.000039256884,0.000008522326,0.000034622535,0.0898179],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955585,0.00017377743,0.00048667355,0.00045629573,0.0029188239,0.00040591977],"domain_scores_gemma":[0.9969017,0.0010495888,0.00009990436,0.00070902106,0.0007922433,0.00044756543],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026678601,0.00013071917,0.00023286628,0.0005472691,0.00009107888,0.00029437937,0.001006016,0.000070456656,0.0007330045],"category_scores_gemma":[0.020420603,0.000087627785,0.00007521295,0.0016595628,0.0001799056,0.0007037286,0.00031805792,0.00014954484,0.008909793],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005704639,0.000108550674,0.00059129257,0.0000031615843,0.00001558,0.000044166096,0.001443675,0.03552714,0.000049003076,0.024061995,0.18692337,0.75117505],"study_design_scores_gemma":[0.00080947945,0.0001387395,0.0013795332,0.000004355366,0.000002600212,0.000037328875,0.0013645596,0.38521734,0.0013139052,0.43267444,0.17683366,0.00022406163],"about_ca_topic_score_codex":0.00012217407,"about_ca_topic_score_gemma":0.000011117376,"teacher_disagreement_score":0.750951,"about_ca_system_score_codex":0.00017958159,"about_ca_system_score_gemma":0.0006437635,"threshold_uncertainty_score":0.9918619},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2128862204345478,"score_gpt":0.5039623446227086,"score_spread":0.2910761241881608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1917528016","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24668558,0.000048555903,0.7191325,0.0020347203,0.0027830251,0.0005814793,0.00003381109,0.00026204402,0.0284383],"genre_scores_gemma":[0.91911054,0.000002616151,0.019587616,0.00021797334,0.00021699058,0.000015803966,0.0000021790263,0.000013017857,0.060833283],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99692154,0.00008151539,0.0003994549,0.00050779025,0.0016781212,0.00041160698],"domain_scores_gemma":[0.9966654,0.0017175395,0.00007503064,0.00075379485,0.00052595336,0.00026225267],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019678776,0.00012026335,0.00020788955,0.0002449387,0.00017293086,0.0002368206,0.0010200348,0.00010003847,0.011705482],"category_scores_gemma":[0.009221193,0.000075163065,0.00006679836,0.00059348537,0.00027136438,0.00042664888,0.00022311896,0.00045625318,0.006826063],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011141122,0.00045392304,0.011907488,0.0000034962172,0.000033272838,0.00012449712,0.0007926279,0.00016633396,0.07950337,0.0062608225,0.10539987,0.7952429],"study_design_scores_gemma":[0.004980662,0.00027138877,0.11178867,0.0000054976285,0.000008048734,0.0000874309,0.0018403972,0.06486276,0.052151073,0.029416678,0.73376226,0.00082516304],"about_ca_topic_score_codex":0.000030400854,"about_ca_topic_score_gemma":0.00061223283,"teacher_disagreement_score":0.79441774,"about_ca_system_score_codex":0.000014054223,"about_ca_system_score_gemma":0.00008828868,"threshold_uncertainty_score":0.9991246},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.13562717372587746,"score_gpt":0.3110003567384468,"score_spread":0.17537318301256932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1931877416","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8585063,0.000025663026,0.1400253,0.00005738841,0.00068068097,0.00036962025,0.000056544064,0.00008003973,0.00019844917],"genre_scores_gemma":[0.9903265,0.00012555117,0.0035727054,0.000003730981,0.00022597189,0.0000010591764,0.00008803107,0.00002383633,0.005632589],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971559,0.000413093,0.0004441627,0.0011692869,0.00052692817,0.000290612],"domain_scores_gemma":[0.99688935,0.00045514264,0.00057445513,0.000505413,0.0013581075,0.00021752504],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011469119,0.0002510058,0.00042215144,0.000979949,0.00025896693,0.000111326946,0.00056886236,0.00041904664,0.00016154729],"category_scores_gemma":[0.004130423,0.0002521154,0.00012407794,0.0010571283,0.00023105991,0.00040010572,0.0009298501,0.0018965924,0.000046603585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031466366,0.00004727169,0.010928057,0.000039544906,0.00004765552,0.000019029414,0.0007753959,0.9585677,0.007031327,0.00025328557,0.00010476666,0.021871332],"study_design_scores_gemma":[0.0011120257,0.00060259976,0.043466818,0.00017234318,0.000092217575,0.000020640482,0.004289613,0.9085107,0.0016629607,0.034919918,0.004577286,0.00057287817],"about_ca_topic_score_codex":0.00009616858,"about_ca_topic_score_gemma":0.00008528208,"teacher_disagreement_score":0.1364526,"about_ca_system_score_codex":0.0001422417,"about_ca_system_score_gemma":0.00013336408,"threshold_uncertainty_score":0.9999931},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04680964409173786,"score_gpt":0.418173190851378,"score_spread":0.3713635467596401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969276875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046652883,0.000007926085,0.9491842,0.0015220989,0.0006470817,0.00029101424,0.000010755567,0.0000805261,0.001603544],"genre_scores_gemma":[0.8297389,6.9427887e-7,0.16941223,0.0003263806,0.00033047242,0.000018666844,0.0000014333084,0.000012861399,0.0001583384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940432,0.00021557519,0.00051189656,0.0011200448,0.0031095252,0.0009997865],"domain_scores_gemma":[0.99340814,0.0039376426,0.00010505873,0.0011627853,0.0009205782,0.00046577532],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010265895,0.00020104888,0.00034049148,0.00025771288,0.0011284942,0.0018953658,0.0032673571,0.00006454327,0.00029511933],"category_scores_gemma":[0.0056388164,0.00013179636,0.00012774473,0.001898443,0.010014843,0.000813044,0.0009645198,0.0002417086,0.00041579295],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072042625,0.00005991242,0.000094118324,0.0000030854665,0.0000031061581,0.000002604752,0.0002976786,0.0038541218,0.00025268478,0.86099905,0.00076847157,0.13359313],"study_design_scores_gemma":[0.00027540931,0.00031733487,0.00060714444,0.0000063213247,0.0000019482572,0.000009042983,0.000017840961,0.6586541,0.0009045144,0.33227184,0.0067890165,0.00014551691],"about_ca_topic_score_codex":0.0000019633912,"about_ca_topic_score_gemma":8.480578e-7,"teacher_disagreement_score":0.78308606,"about_ca_system_score_codex":0.00007674432,"about_ca_system_score_gemma":0.0002144769,"threshold_uncertainty_score":0.99914074},"labels":[],"label_agreement":null},{"id":"W1978605753","doi":"10.1023/b:josh.0000031422.02125.97","title":"Predictive, Stochastic and Dynamic Extensions to Aversion Dynamics Scheduling","year":2004,"lang":"en","type":"article","venue":"Journal of Scheduling","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Risk aversion (psychology); Computer science; Heuristic; Loss aversion; Schedule; Scheduling (production processes); Operations research; Economics; Microeconomics; Expected utility hypothesis; Operations management; Mathematical economics; Mathematics; Artificial intelligence","score_opus":0.04847535851588778,"score_gpt":0.3939548206699781,"score_spread":0.3454794621540903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978605753","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43899187,0.0002605686,0.5590237,0.0012737749,0.00031248995,0.00010422425,0.0000059236754,0.000010192234,0.000017292088],"genre_scores_gemma":[0.81899875,0.000045504676,0.18064559,0.00008440859,0.00013666612,0.0000013944622,7.068166e-7,0.000019439074,0.000067540226],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602765,0.00008812826,0.0009498396,0.00039048918,0.0021208143,0.00042305927],"domain_scores_gemma":[0.996279,0.0009494086,0.0004912441,0.00032514348,0.0014025009,0.0005527203],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027914771,0.00018847862,0.00044885933,0.0010376535,0.00035628333,0.00024572795,0.00064784486,0.000109067616,0.000032231932],"category_scores_gemma":[0.008617078,0.00014328246,0.00014393064,0.0010823276,0.00014538514,0.0008915043,0.00033412743,0.0007381641,0.00006885053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016166225,0.000054622116,0.00017972515,0.000004150355,0.000023531285,0.000088200635,0.00039181192,0.9802787,0.0021801891,0.00015451534,0.00000723712,0.016475707],"study_design_scores_gemma":[0.0022546677,0.00089574605,0.006215474,0.0005594275,0.00004677987,0.0008400897,0.0074833035,0.9226611,0.0003730979,0.058264874,0.00007133804,0.000334055],"about_ca_topic_score_codex":0.000005593128,"about_ca_topic_score_gemma":0.0000184009,"teacher_disagreement_score":0.38000688,"about_ca_system_score_codex":0.00046329448,"about_ca_system_score_gemma":0.0003127812,"threshold_uncertainty_score":0.99973375},"labels":[],"label_agreement":null},{"id":"W1982615629","doi":"10.1109/icassp.2013.6638679","title":"Learning-stage based decentralized adaptive access policy for dynamic spectrum access","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Stage (stratigraphy); Access control; Computer network; Distributed computing","score_opus":0.16316195378576367,"score_gpt":0.5125284662488282,"score_spread":0.3493665124630645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982615629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021389242,0.000035050758,0.96579295,0.007722417,0.00020753135,0.0019162953,0.00005285064,0.00019299146,0.0026906705],"genre_scores_gemma":[0.9453264,0.000026482187,0.00721628,0.0006243631,0.00010983876,0.00038720365,0.000022344397,0.000054646163,0.046232425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99494636,0.00030931318,0.0007054089,0.0009837361,0.0018991776,0.0011560159],"domain_scores_gemma":[0.9941406,0.0035039792,0.00030563923,0.00080681144,0.00081277674,0.00043014195],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013754859,0.00030441314,0.00048973726,0.0009861484,0.00042732974,0.0023012904,0.0034034583,0.00013131318,0.012713204],"category_scores_gemma":[0.0066869627,0.0002142074,0.0002473946,0.0022182867,0.0002452537,0.002925765,0.00069823576,0.00036558774,0.0010973865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027447804,0.0012994813,0.028045379,0.000114142116,0.00033183972,0.00008350977,0.0012851388,0.50420296,0.0015058622,0.0099399015,0.063485146,0.38696188],"study_design_scores_gemma":[0.0022262488,0.0002773963,0.02041073,0.000010666475,0.0000057608413,0.0000020560249,0.00079463236,0.8986355,0.0033095614,0.057067394,0.016834103,0.00042597257],"about_ca_topic_score_codex":0.0019966208,"about_ca_topic_score_gemma":0.0005837803,"teacher_disagreement_score":0.9585767,"about_ca_system_score_codex":0.0003136046,"about_ca_system_score_gemma":0.0005486899,"threshold_uncertainty_score":0.9996804},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.43992274550270394,"score_gpt":0.5509132329952277,"score_spread":0.11099048749252372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987292194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33174247,0.00033038502,0.65362364,0.0040222653,0.00032248872,0.0012480847,0.000048045677,0.00007511886,0.008587533],"genre_scores_gemma":[0.8922712,0.000091614354,0.10276009,0.000006189352,0.00026462745,0.00012515669,0.0000057606376,0.00002628303,0.0044490406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99376196,0.0006443029,0.0009071517,0.00053190626,0.0036781053,0.00047655002],"domain_scores_gemma":[0.99202764,0.003616151,0.00008345014,0.0012330939,0.0028154764,0.0002241752],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013318639,0.00013983471,0.00036192316,0.00072660577,0.0007185513,0.0007027714,0.0009872518,0.00010524598,0.00025109452],"category_scores_gemma":[0.018495983,0.00010554159,0.000057395002,0.0014543171,0.00081394217,0.0005053089,0.00039402736,0.00041966836,0.00029355206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010175245,0.00243794,0.008668742,0.00039023784,0.00018709709,0.000017801232,0.018593442,0.010663006,0.061382987,0.4737054,0.016761944,0.40708962],"study_design_scores_gemma":[0.00061050936,0.00030493704,0.003805149,0.000073945565,0.00000702436,0.000019089599,0.0044506076,0.83760476,0.022505343,0.1170473,0.013321934,0.0002493899],"about_ca_topic_score_codex":0.00003706817,"about_ca_topic_score_gemma":0.0000227815,"teacher_disagreement_score":0.8269418,"about_ca_system_score_codex":0.000060505397,"about_ca_system_score_gemma":0.00018611524,"threshold_uncertainty_score":0.98977166},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.043294788994366507,"score_gpt":0.3667983632348631,"score_spread":0.3235035742404966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000850397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02148839,0.00005010255,0.97479254,0.0015308989,0.0007774307,0.00063194276,0.00011319068,0.0002832024,0.00033230215],"genre_scores_gemma":[0.9846848,0.000021412012,0.011439138,0.0006468864,0.00013724477,0.00010110118,0.0000028574664,0.000045297358,0.0029212409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944181,0.00038720047,0.001049556,0.0007937693,0.0027464218,0.0006049403],"domain_scores_gemma":[0.98688656,0.010712488,0.0002498053,0.0011159359,0.000718261,0.00031693216],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019556086,0.00034161314,0.00064593117,0.00072548643,0.00046062493,0.00036273096,0.0010243782,0.00016661988,0.003551582],"category_scores_gemma":[0.0017040115,0.00024686704,0.00023332983,0.0015857691,0.00020503988,0.0005424485,0.000004497582,0.00036903308,0.0020096246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015253815,0.0006083559,0.000013799323,0.000024077908,0.000056363875,0.0000059172467,0.00009847568,0.06946191,0.00020015302,0.000012074716,0.0011345611,0.9282318],"study_design_scores_gemma":[0.0050145835,0.0004719015,0.002837587,0.00013565455,0.00006299834,0.00003723185,0.0003188898,0.96538806,0.0015542491,0.01853693,0.005186111,0.00045581665],"about_ca_topic_score_codex":0.000014691217,"about_ca_topic_score_gemma":0.00028799273,"teacher_disagreement_score":0.9633534,"about_ca_system_score_codex":0.00014458719,"about_ca_system_score_gemma":0.00024109277,"threshold_uncertainty_score":0.99999833},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08329802728424093,"score_gpt":0.39703393465733616,"score_spread":0.3137359073730952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009482316","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23569581,0.00018138414,0.76236856,0.00037774793,0.00021441148,0.00078708155,0.00017186331,0.00008427311,0.00011884124],"genre_scores_gemma":[0.96151567,0.00004732666,0.032395653,0.000036087877,0.0010292737,0.0002999853,0.00057533523,0.000037481277,0.0040632165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947983,0.000497861,0.0010742593,0.0012994958,0.0016008698,0.0007291982],"domain_scores_gemma":[0.9973224,0.0003573932,0.0004590711,0.0004929973,0.0011457464,0.00022240754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014006605,0.00040622335,0.0007762409,0.0013066877,0.0007075773,0.0006773046,0.00038869088,0.00020385283,0.00066400674],"category_scores_gemma":[0.00023214209,0.00033037618,0.0007279811,0.002865991,0.00023695575,0.00079425646,0.00012034129,0.00014549767,0.000061472194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024217423,0.0009836793,0.0040414263,0.000018970666,0.006498287,0.000050933177,0.0010041554,0.76416236,0.106551886,0.005650093,0.0029713,0.105645195],"study_design_scores_gemma":[0.0035516613,0.00085094705,0.00211558,0.000005547841,0.0025021117,0.000021235302,0.00036555817,0.90837896,0.05761039,0.019032048,0.004896256,0.0006696888],"about_ca_topic_score_codex":0.0032998032,"about_ca_topic_score_gemma":0.0058856835,"teacher_disagreement_score":0.7299729,"about_ca_system_score_codex":0.0005708117,"about_ca_system_score_gemma":0.00030283484,"threshold_uncertainty_score":0.9999148},"labels":[],"label_agreement":null},{"id":"W2015102477","doi":"10.1109/spawc.2013.6612026","title":"Decentralized spectrum learning and access adaptive to channel availability distribution in primary network","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Channel (broadcasting); Computer science; Closeness; Distribution (mathematics); Range (aeronautics); Computer network; Distributed computing; Artificial intelligence; Mathematics; Engineering","score_opus":0.07890080798694213,"score_gpt":0.3996474952581169,"score_spread":0.3207466872711747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015102477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46465722,0.00020713035,0.52802014,0.0031075217,0.00020066473,0.0014371257,0.000012741145,0.000082868464,0.0022745938],"genre_scores_gemma":[0.99590087,0.0000530759,0.0018617781,0.000120230405,0.00007988306,0.00007907267,0.0000133315925,0.000009676932,0.0018820529],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968109,0.00036400944,0.00050146214,0.0006759978,0.0009824281,0.0006652066],"domain_scores_gemma":[0.99785274,0.0012480376,0.0000926314,0.00029024444,0.00023645035,0.00027991735],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022543597,0.00014737426,0.00032534287,0.00013112988,0.0001734613,0.0004612926,0.00052013533,0.00007190282,0.0017919206],"category_scores_gemma":[0.002465566,0.000107873326,0.000039821723,0.0015067083,0.00012336594,0.001054969,0.0006885786,0.00031430428,0.0005157238],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008869703,0.0003310164,0.5826541,0.000018763876,0.00003285576,0.00003285202,0.00083982025,0.06746143,0.00021181646,0.000940272,0.0381723,0.30841777],"study_design_scores_gemma":[0.0006464871,0.00015365933,0.8894083,0.000016732536,0.0000015751067,0.0000033586489,0.00035484746,0.043039683,0.00027972754,0.06011925,0.005742128,0.00023423381],"about_ca_topic_score_codex":0.0003836038,"about_ca_topic_score_gemma":0.00038287678,"teacher_disagreement_score":0.5312437,"about_ca_system_score_codex":0.00024692077,"about_ca_system_score_gemma":0.00006398596,"threshold_uncertainty_score":0.9991206},"labels":[],"label_agreement":null},{"id":"W2020216268","doi":"10.1109/spawc.2014.6941869","title":"Distributed stochastic learning for dynamic spectrum access adaptive to primary network conditions","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Cognitive radio; Learning automata; Channel (broadcasting); Set (abstract data type); Collision; Distributed computing; Computer network; Adaptive learning; Selection (genetic algorithm); Automaton; Machine learning; Artificial intelligence; Computer security; Telecommunications; Wireless","score_opus":0.08252314095925892,"score_gpt":0.44043246196883157,"score_spread":0.3579093210095726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020216268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024212813,0.000014373353,0.99374557,0.0016528982,0.00029637816,0.0008288505,0.00010720434,0.0001221628,0.00081130676],"genre_scores_gemma":[0.9864773,8.968144e-7,0.007330769,0.0002654803,0.00027039158,0.00019972636,0.00015482277,0.000027605727,0.005273002],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967772,0.00020516799,0.00047266975,0.0006882884,0.0011210798,0.00073562586],"domain_scores_gemma":[0.99295765,0.0056817275,0.0001475732,0.000478047,0.00042982848,0.00030517823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018075194,0.00018291679,0.00036638282,0.00026272263,0.0006030464,0.0004250303,0.0011294094,0.00007054238,0.00060538825],"category_scores_gemma":[0.0052554505,0.0001417144,0.000118531614,0.0014544296,0.00012680324,0.00052842486,0.0004873834,0.00028170476,0.0004979769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010368076,0.000027149068,0.00013051074,0.0000020331229,0.000015290761,0.0000013034382,0.000029462873,0.9801812,0.00002226025,0.0014513088,0.009714493,0.008321262],"study_design_scores_gemma":[0.00058086566,0.00044433904,0.025651408,0.000018276312,0.000009520103,0.0000048105976,0.00016840015,0.80157906,0.000035794263,0.161715,0.00951699,0.0002755075],"about_ca_topic_score_codex":0.000013562416,"about_ca_topic_score_gemma":0.00018604436,"teacher_disagreement_score":0.9864148,"about_ca_system_score_codex":0.0002006701,"about_ca_system_score_gemma":0.00010530292,"threshold_uncertainty_score":0.6628577},"labels":[],"label_agreement":null},{"id":"W2022938204","doi":"10.1142/s0218488508005364","title":"PORTFOLIO SELECTION AND ONLINE LEARNING","year":2008,"lang":"en","type":"article","venue":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Portfolio; Universalization; Computer science; Selection (genetic algorithm); Markov chain; Investment strategy; Econometrics; Stock market; Mathematical optimization; Work (physics); Cover (algebra); Economics; Financial economics; Artificial intelligence; Mathematics; Machine learning; Microeconomics; Engineering","score_opus":0.09085081597946684,"score_gpt":0.40544625715843874,"score_spread":0.31459544117897187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022938204","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92850876,0.0032661816,0.064701,0.00058324216,0.002252506,0.00016615375,0.000023963637,0.000025396681,0.00047280407],"genre_scores_gemma":[0.9965652,0.0002999648,0.00031153427,0.000022728602,0.0010788753,0.0000043269665,0.0000071144564,0.000014954204,0.0016952812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964881,0.0003330834,0.0010104532,0.0002990616,0.0016473974,0.00022191046],"domain_scores_gemma":[0.9932732,0.0011797065,0.00069957535,0.00011378218,0.0045119766,0.00022175467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021372833,0.00017472266,0.0004363277,0.0009336333,0.00023618017,0.0002488228,0.0005055403,0.00008971203,0.000059895843],"category_scores_gemma":[0.0022732692,0.00012267761,0.0001140096,0.0005138817,0.00018411216,0.00044521134,0.00009623725,0.00042636768,0.000012182384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022235436,0.0011726543,0.25506383,0.000101262405,0.0005911882,0.0011358619,0.0022407873,0.46808383,0.0036080675,0.0010376022,0.006620647,0.25812075],"study_design_scores_gemma":[0.0068557216,0.0011265136,0.06276683,0.000582596,0.000042564247,0.005990327,0.0035377152,0.7550963,0.00045221127,0.0017808236,0.16113348,0.00063492055],"about_ca_topic_score_codex":0.00008969235,"about_ca_topic_score_gemma":0.000057347173,"teacher_disagreement_score":0.28701246,"about_ca_system_score_codex":0.00015178746,"about_ca_system_score_gemma":0.00039628794,"threshold_uncertainty_score":0.50026476},"labels":[],"label_agreement":null},{"id":"W2024490033","doi":"10.1007/s001860300295","title":"One-armed bandit models with continuous and delayed responses","year":2003,"lang":"en","type":"article","venue":"Mathematical Methods of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Manitoba","funders":"","keywords":"Multi-armed bandit; Monotonic function; Markov decision process; Sequence (biology); Optimal stopping; Markov process; Mathematical optimization; Limit (mathematics); Index (typography); Bayesian probability; Markov chain; Mathematics; Time horizon; Computer science; Statistics","score_opus":0.5018446804662678,"score_gpt":0.6032521031918505,"score_spread":0.10140742272558267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024490033","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055256747,0.00024632568,0.9353731,0.0006675868,0.000019765937,0.0008693182,0.000022338982,0.000023704764,0.0075210594],"genre_scores_gemma":[0.22190814,0.000035775924,0.7734496,0.000017009443,0.000016397624,0.00016233958,0.0000012115138,0.000025577168,0.004383924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9874809,0.0065718335,0.00097413757,0.00070565584,0.0035805367,0.00068695983],"domain_scores_gemma":[0.96992165,0.025749264,0.0000644883,0.0011458349,0.0027489185,0.0003698447],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031206377,0.0001797086,0.00066124357,0.0009237052,0.0005326594,0.00047843452,0.0007306165,0.00013084855,0.0010979556],"category_scores_gemma":[0.06461966,0.000120499084,0.00006847142,0.001976847,0.0014519482,0.0006188687,0.00026000856,0.00061220175,0.00008915829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001325283,0.0015959312,0.00012414872,0.00013421285,0.00025434053,0.000056804318,0.0051836893,0.015184848,0.025045501,0.8224453,0.0006926708,0.12795727],"study_design_scores_gemma":[0.0010228003,0.0009246806,0.00012653615,0.00006913255,0.000015822021,0.00006603368,0.0036671448,0.16374265,0.033454772,0.7958686,0.0007964245,0.00024544806],"about_ca_topic_score_codex":0.000022195545,"about_ca_topic_score_gemma":0.00003056109,"teacher_disagreement_score":0.16665138,"about_ca_system_score_codex":0.00005777715,"about_ca_system_score_gemma":0.0004034227,"threshold_uncertainty_score":0.99981517},"labels":[],"label_agreement":null},{"id":"W2030136720","doi":"10.1016/j.jspi.2004.01.022","title":"Evaluation of asymptotic approximations for a two-stage Bernoulli bandit","year":2004,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Bernoulli's principle; Bayes' theorem; Applied mathematics; Bernoulli trial; Bayesian probability; Optimal stopping; Mathematical optimization; Approximations of π; Stage (stratigraphy); Mathematical economics; Statistics","score_opus":0.27833213208247826,"score_gpt":0.5350748650473813,"score_spread":0.2567427329649031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030136720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064315535,0.00020295582,0.9346938,0.00013986869,0.0000943281,0.00015733195,0.00013672939,0.000002985337,0.00025642035],"genre_scores_gemma":[0.92161804,0.0000067035207,0.07823942,0.000012645242,0.000059720755,0.0000055194946,0.0000040203363,0.000004781554,0.000049135284],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996505,0.00014816177,0.0007781902,0.00015975564,0.0022295834,0.00017930388],"domain_scores_gemma":[0.9927648,0.0041193073,0.00048833544,0.00012923691,0.0023551362,0.00014321966],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062097027,0.00008620665,0.00029884785,0.000267901,0.00011315729,0.00010682675,0.00023260908,0.000040561077,0.00012454088],"category_scores_gemma":[0.026693264,0.000060146933,0.000044965193,0.0002504172,0.00019151012,0.00038009696,0.000037079513,0.00020202396,0.000004697951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043053558,0.00041637517,0.0060058823,0.00010357922,0.00015665226,0.000041762007,0.003028015,0.64103734,0.0013690442,0.076352626,0.0008874461,0.27017072],"study_design_scores_gemma":[0.0036675567,0.0010508223,0.025528027,0.00020897556,0.00009859826,0.000051631137,0.00096658827,0.2522681,0.00071706815,0.71487004,0.0004203214,0.00015223866],"about_ca_topic_score_codex":0.000008551576,"about_ca_topic_score_gemma":0.0000029927642,"teacher_disagreement_score":0.8573025,"about_ca_system_score_codex":0.000072908915,"about_ca_system_score_gemma":0.00045116412,"threshold_uncertainty_score":0.98150533},"labels":[],"label_agreement":null},{"id":"W2037905382","doi":"10.1007/s10994-006-0219-y","title":"Online calibrated forecasts: Memory efficiency versus universality for learning in games","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Army Research Office; Air Force Office of Scientific Research; Fonds Québécois de la Recherche sur la Nature et les Technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Fictitious play; Regret; Repeated game; Computer science; Nash equilibrium; Best response; Universality (dynamical systems); Artificial intelligence; Mathematics; Mathematical optimization; Game theory; Mathematical economics; Machine learning","score_opus":0.08089650883186325,"score_gpt":0.4011498157716262,"score_spread":0.32025330693976295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037905382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78996855,0.0005772659,0.20370324,0.0010154739,0.0004276768,0.0006337576,0.000046911915,0.00032871554,0.0032983818],"genre_scores_gemma":[0.98213756,0.000010683641,0.0043632654,0.00002465705,0.00021124752,0.000017108996,0.00014233589,0.000044879016,0.013048248],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959083,0.00066041946,0.00070927927,0.0007876571,0.0012043327,0.0007299988],"domain_scores_gemma":[0.9951629,0.0037872333,0.0002885261,0.00034423295,0.00030342993,0.000113660746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030030229,0.0002493677,0.0004391629,0.00069686456,0.00041187156,0.00020204825,0.00071068516,0.00012550276,0.00035923268],"category_scores_gemma":[0.008214424,0.0002109508,0.00014970184,0.0018979859,0.00017320727,0.00048234596,0.00026184795,0.00090102677,0.00005347026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059980416,0.00021459725,0.030579207,0.000012750575,0.000010726725,0.00005188862,0.0003369952,0.85403824,0.00036411482,0.000191316,0.00033247494,0.113267906],"study_design_scores_gemma":[0.0036869752,0.0004011752,0.013848882,0.000021148797,0.000006797649,0.0000044405865,0.0015913886,0.9368796,0.00034504713,0.0020766265,0.040835053,0.0003028924],"about_ca_topic_score_codex":0.0012942208,"about_ca_topic_score_gemma":0.0019389308,"teacher_disagreement_score":0.19933997,"about_ca_system_score_codex":0.00021876284,"about_ca_system_score_gemma":0.00013853931,"threshold_uncertainty_score":0.98340267},"labels":[],"label_agreement":null},{"id":"W2038683608","doi":"10.1287/opre.1110.0922","title":"A Unified Framework for Dynamic Prediction Market Design","year":2011,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Computer science; Mathematical optimization; Bidding; Function (biology); Mechanism design; Bounded function; Convex optimization; Bellman equation; Regular polygon; Mathematical economics; Economics; Mathematics; Microeconomics","score_opus":0.558322727140912,"score_gpt":0.5555112619072152,"score_spread":0.002811465233696797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038683608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015557734,0.00007970923,0.9910284,0.00075594644,0.00023648089,0.0017373456,0.0001089945,0.000058728023,0.0044385693],"genre_scores_gemma":[0.35191262,0.00009376568,0.60370076,0.000036106474,0.00017409648,0.0014141935,0.000023203442,0.000044786535,0.042600468],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99400246,0.00132236,0.00055482396,0.0007436695,0.0026312268,0.00074548303],"domain_scores_gemma":[0.990381,0.005268819,0.000030412155,0.0011407434,0.0029292349,0.000249771],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013755752,0.000136262,0.00020820968,0.0010285963,0.0012951121,0.00055156543,0.0012738005,0.00018841767,0.0051606596],"category_scores_gemma":[0.02397882,0.00010592952,0.00008759584,0.0025050973,0.00038031128,0.00073684606,0.00024932332,0.00066246797,0.0007824728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042710393,0.0024435725,0.0014554954,0.000063867905,0.0002873847,0.00010344492,0.0146872,0.06309831,0.0069377366,0.16621427,0.22262631,0.51781136],"study_design_scores_gemma":[0.0004518907,0.00057614234,0.003576808,0.000022070255,0.0000037807138,0.0000079404235,0.0017119524,0.70327944,0.0017625528,0.28001928,0.008431868,0.00015628435],"about_ca_topic_score_codex":0.000058161462,"about_ca_topic_score_gemma":0.00013373395,"teacher_disagreement_score":0.6401811,"about_ca_system_score_codex":0.00020192866,"about_ca_system_score_gemma":0.0005149154,"threshold_uncertainty_score":0.9999955},"labels":[],"label_agreement":null},{"id":"W2038708756","doi":"10.1016/j.orl.2010.09.006","title":"Weak aggregating algorithm for the distribution-free perishable inventory problem","year":2010,"lang":"en","type":"article","venue":"Operations Research Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematical optimization; Class (philosophy); Parametric statistics; Computer science; Distribution (mathematics); Mathematics; Algorithm; Artificial intelligence; Statistics","score_opus":0.1251349721004983,"score_gpt":0.4507296444040477,"score_spread":0.32559467230354944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038708756","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019507362,0.00018698638,0.886681,0.08839652,0.0007580216,0.003040204,0.00061986654,0.00008345918,0.0007265331],"genre_scores_gemma":[0.25252867,0.00021539131,0.63963884,0.0029191112,0.008696177,0.015276403,0.0010192314,0.00033570363,0.07937045],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931927,0.0005494282,0.00064102677,0.00078372983,0.0037536677,0.0010794526],"domain_scores_gemma":[0.9902147,0.0050682,0.00006300419,0.001965994,0.0024076118,0.0002804548],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.012925675,0.00018839873,0.00022431303,0.00035962174,0.0040253378,0.002399697,0.003196973,0.000111067,0.0007965566],"category_scores_gemma":[0.020871375,0.00012047454,0.00016148492,0.0020197225,0.0011420494,0.0011605341,0.0007830408,0.0015447652,0.00038856594],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002558434,0.00014763496,0.00032289154,0.000009957242,0.000058057216,0.000011071519,0.0007188559,0.023228474,0.019636676,0.0040050554,0.55429035,0.39754537],"study_design_scores_gemma":[0.0006310006,0.000077931385,0.00029368242,0.000012500807,0.000004217321,0.000013517833,0.0012551787,0.6393008,0.0019420818,0.0038224305,0.352458,0.000188611],"about_ca_topic_score_codex":0.0003954232,"about_ca_topic_score_gemma":0.001255929,"teacher_disagreement_score":0.61607236,"about_ca_system_score_codex":0.00017710643,"about_ca_system_score_gemma":0.00045548525,"threshold_uncertainty_score":0.9986359},"labels":[],"label_agreement":null},{"id":"W204541363","doi":"","title":"Online Learning with Global Cost Functions","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Mathematical optimization; Job shop scheduling; Computer science; Scheduling (production processes); Function (biology); Decision maker; Norm (philosophy); Operations research; Mathematics; Machine learning; Schedule","score_opus":0.11747433322981686,"score_gpt":0.4665678340823299,"score_spread":0.349093500852513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W204541363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022726474,0.000043044445,0.94038534,0.003877221,0.00009023303,0.0001878781,0.000019067804,0.00015117225,0.03251958],"genre_scores_gemma":[0.9100984,0.0000069669245,0.026523504,0.00041505802,0.00016894146,0.000004713416,0.00001573081,0.000006203067,0.06276051],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997602,0.00007546529,0.00022689761,0.00036361284,0.0014240982,0.00030796538],"domain_scores_gemma":[0.9987526,0.0003108577,0.000056560195,0.00032830992,0.0003945949,0.0001571028],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00053167314,0.00009367464,0.00014405194,0.00010056793,0.00020814271,0.00017683944,0.00037888697,0.000036595702,0.0015620679],"category_scores_gemma":[0.0012103252,0.000054291737,0.00003999888,0.0014390905,0.00008258788,0.00034513004,0.00005130687,0.00021940337,0.0011477834],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000624137,0.00015473954,0.008409385,2.056201e-7,0.000005991584,0.00002628619,0.000036651458,0.019719511,0.000023819624,0.00030793098,0.006898456,0.96435463],"study_design_scores_gemma":[0.001869462,0.0018053325,0.4137747,0.000014838232,0.000010599801,0.0001567404,0.006171576,0.09711814,0.00014554948,0.025391353,0.45305192,0.000489787],"about_ca_topic_score_codex":0.000015701096,"about_ca_topic_score_gemma":0.0001634699,"teacher_disagreement_score":0.9638648,"about_ca_system_score_codex":0.000075315555,"about_ca_system_score_gemma":0.00006988673,"threshold_uncertainty_score":0.9996299},"labels":[],"label_agreement":null},{"id":"W2059995471","doi":"10.3182/20140824-6-za-1003.01866","title":"Fast Distributed Strategic Learning for Global Optima in Queueing Access Games","year":2014,"lang":"en","type":"article","venue":"IFAC Proceedings Volumes","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Stochastic game; Computer science; Queueing theory; Queue; Convergence (economics); Mathematical optimization; Stochastic approximation; Graph; Q-learning; Reinforcement learning; Theoretical computer science; Artificial intelligence; Mathematics; Asynchronous communication; Mathematical economics","score_opus":0.10372407585180725,"score_gpt":0.4312016915104807,"score_spread":0.32747761565867345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059995471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6997745,0.00030959025,0.28204843,0.0009317574,0.00035374,0.0010536677,0.00006136665,0.0003199139,0.015147015],"genre_scores_gemma":[0.9938457,0.0000195929,0.0048786057,0.000039604416,0.00021776899,0.0001214379,0.000016784506,0.000026160063,0.0008343151],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959272,0.000043345495,0.00072981365,0.00096424104,0.0014343751,0.00090101914],"domain_scores_gemma":[0.99769104,0.00066119793,0.00033559694,0.00020049098,0.0008942345,0.00021742849],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0025628165,0.0002829979,0.00051330065,0.00030565666,0.00032268462,0.0017296534,0.0015786267,0.00015987293,0.000086530454],"category_scores_gemma":[0.006493816,0.00023840461,0.00012553003,0.0018783212,0.00020393686,0.0018701259,0.0004458044,0.00039322313,0.00007283475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041906047,0.00020919066,0.41292784,0.00016896294,0.000042702206,0.000009550582,0.0008915828,0.04071653,0.000837899,0.018003851,0.002911538,0.5228613],"study_design_scores_gemma":[0.0022523135,0.00041333662,0.07400889,0.00012145044,0.000013528021,0.000020295141,0.00624491,0.62326723,0.0015381838,0.26653418,0.02477389,0.0008117997],"about_ca_topic_score_codex":0.000047572263,"about_ca_topic_score_gemma":0.000057311834,"teacher_disagreement_score":0.5825507,"about_ca_system_score_codex":0.00023816316,"about_ca_system_score_gemma":0.00011240946,"threshold_uncertainty_score":0.9993066},"labels":[],"label_agreement":null},{"id":"W2066996533","doi":"10.1007/s10463-013-0401-5","title":"One-armed bandit process with a covariate","year":2013,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Manitoba","funders":"","keywords":"Covariate; Mathematics; Conjugate prior; Bayesian probability; Statistics; Sequence (biology); Econometrics; Variance (accounting); Stochastic game; Monotonic function; Prior probability; Regression; Mathematical economics","score_opus":0.26697745204278833,"score_gpt":0.46407051248974257,"score_spread":0.19709306044695424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066996533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10834079,0.000029989202,0.88440996,0.0025350896,0.00016020697,0.00094276,0.00021363774,0.000021910406,0.0033456224],"genre_scores_gemma":[0.87112486,0.000011178717,0.12820466,0.00010497494,0.000028772778,0.000039726532,0.000002679201,0.000017058652,0.000466082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99592716,0.0000758432,0.00093424984,0.00027452942,0.002458032,0.0003301725],"domain_scores_gemma":[0.99506855,0.0017519797,0.0005624188,0.0008156496,0.0016522015,0.00014922774],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011020553,0.00015958774,0.0005517335,0.00013393539,0.000108100525,0.00008661169,0.0012877783,0.00006283937,0.00050798117],"category_scores_gemma":[0.008446026,0.00008525093,0.000078372155,0.00078171864,0.0012651517,0.00047900894,0.00021665308,0.00019108459,0.00014619909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057604804,0.0050323014,0.001218325,0.0025941578,0.0009053524,0.00005119371,0.006679902,0.022704553,0.0028759826,0.8262485,0.023969887,0.10714375],"study_design_scores_gemma":[0.00039679924,0.00021596666,0.0032752578,0.00023314182,0.000022738783,0.000009723478,0.00030681514,0.0110563245,0.008660091,0.97527647,0.0003925911,0.0001541087],"about_ca_topic_score_codex":0.000056240086,"about_ca_topic_score_gemma":0.000017609693,"teacher_disagreement_score":0.76278406,"about_ca_system_score_codex":0.000009980469,"about_ca_system_score_gemma":0.00020843737,"threshold_uncertainty_score":0.99990624},"labels":[],"label_agreement":null},{"id":"W2068420430","doi":"10.1002/asmb.823","title":"Optimal investment and consumption with stochastic dividends","year":2009,"lang":"en","type":"article","venue":"Applied Stochastic Models in Business and Industry","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Dividend; Consumption (sociology); Economics; Poisson distribution; Investment (military); Econometrics; Investment strategy; Rate of return; Financial market; Mathematical economics; Microeconomics; Actuarial science; Mathematics; Finance; Statistics","score_opus":0.10484829443400571,"score_gpt":0.35823646907277057,"score_spread":0.25338817463876484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068420430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3577264,0.00018432333,0.64095753,0.00040099665,0.000033934764,0.0003486209,0.000008395449,0.000023611461,0.00031619432],"genre_scores_gemma":[0.9958385,0.000014708617,0.0035782347,0.00024873833,0.00006995828,0.00007551005,0.0000055318733,0.000016330647,0.00015244854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971386,0.000036368172,0.00047962437,0.0007755527,0.0010950528,0.00047475705],"domain_scores_gemma":[0.9985694,0.00045053803,0.00014600107,0.00039413097,0.00020512816,0.00023476405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075115834,0.00028032146,0.00042156372,0.00043936103,0.00019202985,0.00024950795,0.00029048795,0.00029588921,0.00004710568],"category_scores_gemma":[0.00022208015,0.00020550934,0.000014349906,0.00083289255,0.00042472134,0.0005124267,0.00017150867,0.00065577513,0.000008956961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002324934,0.00009051917,0.000088274704,0.000008214282,0.00000865056,0.000016251715,0.00032217338,0.95070124,0.000080097816,0.015316613,0.00007051651,0.03306497],"study_design_scores_gemma":[0.0041740523,0.00025867668,0.04146768,0.00020180037,0.000030388668,0.00013408865,0.000884498,0.79340714,0.000031609245,0.1586664,0.000036199348,0.00070749555],"about_ca_topic_score_codex":0.000022752562,"about_ca_topic_score_gemma":0.000011772615,"teacher_disagreement_score":0.6381121,"about_ca_system_score_codex":0.00006105077,"about_ca_system_score_gemma":0.00010808215,"threshold_uncertainty_score":0.8380428},"labels":[],"label_agreement":null},{"id":"W2069281427","doi":"10.1109/iccchina.2012.6356916","title":"Distributed opportunistic spectrum access with unknown population","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Cognitive radio; Regret; Population; Channel (broadcasting); Online learning; Computer network; Bernoulli's principle; Throughput; Distributed computing; Machine learning; Telecommunications; Wireless; Engineering","score_opus":0.2369926352547683,"score_gpt":0.4832749232261946,"score_spread":0.2462822879714263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069281427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04129572,0.000031481108,0.9511196,0.0012391687,0.00028514184,0.0002852479,0.000054192256,0.00011213933,0.0055772825],"genre_scores_gemma":[0.9926386,0.0000036160322,0.0014148845,0.00005953218,0.00019635807,0.00001210073,0.00009533564,0.000013332471,0.00556624],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968782,0.00010598565,0.00036178395,0.00033039352,0.0017633383,0.00056028395],"domain_scores_gemma":[0.9981493,0.0005988574,0.0001335327,0.00057759485,0.00019020216,0.00035051524],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012859604,0.00013344952,0.0002090415,0.00021674355,0.00018592962,0.00035685112,0.00073879363,0.000049975682,0.0030637318],"category_scores_gemma":[0.0011722847,0.00007715842,0.000040319235,0.0012275844,0.00009258565,0.0017319433,0.0002259232,0.00014643942,0.00048121045],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026836197,0.000485208,0.85387796,0.000011062506,0.000054052034,0.000058979138,0.0001509493,0.0041993805,0.00005659597,0.03221935,0.019177983,0.0894401],"study_design_scores_gemma":[0.00066744257,0.00013739927,0.8908357,0.000010587215,0.000013385575,0.00005454584,0.0002189517,0.01418214,0.00065899076,0.03548695,0.057313625,0.00042026717],"about_ca_topic_score_codex":0.00013347475,"about_ca_topic_score_gemma":0.00015061209,"teacher_disagreement_score":0.9513429,"about_ca_system_score_codex":0.000094813,"about_ca_system_score_gemma":0.000051888317,"threshold_uncertainty_score":0.9978476},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16040752224704838,"score_gpt":0.4127314576545998,"score_spread":0.2523239354075514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073384958","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000056800247,0.0008677423,0.93645436,0.0013639875,0.0010746168,0.0016084808,0.000050461655,0.00028059562,0.058242936],"genre_scores_gemma":[0.06788354,0.0009999631,0.006355473,0.00051086926,0.0030230165,0.000502524,0.00018839813,0.00037128708,0.92016494],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931322,0.0004202843,0.0014421986,0.0016754905,0.0023528596,0.0009770135],"domain_scores_gemma":[0.9839671,0.013485292,0.00083958806,0.00073745294,0.00062792207,0.0003426232],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0045559565,0.0007870023,0.0011268811,0.0012185299,0.0014575138,0.0008893858,0.0012129018,0.0008103002,0.0027286694],"category_scores_gemma":[0.030274484,0.0006092855,0.00047400343,0.00038852825,0.00048700068,0.0002215203,0.00036760655,0.0041519436,0.00089339574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026351947,0.0000316598,0.0000056936296,0.000033649896,0.00006838303,0.000016127433,0.00036730725,0.11568932,0.00021844053,0.0034853483,0.0012453414,0.8785752],"study_design_scores_gemma":[0.000052060368,0.0007606797,0.000004463859,0.00016256518,0.00006149846,0.000014384536,0.00021042276,0.19510624,0.016138155,0.16027792,0.6264191,0.0007924819],"about_ca_topic_score_codex":0.00005377089,"about_ca_topic_score_gemma":0.00020532247,"teacher_disagreement_score":0.9300989,"about_ca_system_score_codex":0.000172805,"about_ca_system_score_gemma":0.00034467276,"threshold_uncertainty_score":0.99988455},"labels":[],"label_agreement":null},{"id":"W2079808644","doi":"10.1109/icassp.2014.6855022","title":"Channel-aware distributed dynamic spectrum access via learning-based heterogeneous multi-channel auction","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Channel (broadcasting); Throughput; Overhead (engineering); Diversity gain; Auction algorithm; Computer network; Spectrum auction; Auction theory; Wireless; Common value auction; Telecommunications; Revenue equivalence; Fading; Mathematics","score_opus":0.07850233049752461,"score_gpt":0.41138927468019487,"score_spread":0.3328869441826703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079808644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013767019,0.00003041084,0.99576133,0.0013241495,0.00066913874,0.00042524276,0.000052800096,0.00035376477,0.000006471488],"genre_scores_gemma":[0.9967363,0.00000803488,0.00009675386,0.00012142494,0.00016078012,0.00005432001,0.00014153196,0.00005036448,0.0026305194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946609,0.00053271436,0.00071865245,0.0011502907,0.00203731,0.0009001284],"domain_scores_gemma":[0.99686635,0.000989679,0.000314241,0.00090229814,0.00055458123,0.00037284626],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001808243,0.00036121596,0.00048562832,0.00062219123,0.0005783292,0.0006027175,0.0015726768,0.00019800192,0.0009735747],"category_scores_gemma":[0.0021400338,0.00027833282,0.00022984324,0.0014864729,0.00024380171,0.0006874581,0.00043851984,0.0005459018,0.0010666943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058381633,0.00011432601,0.000028617842,0.000005824117,0.0000128210195,0.000017477269,0.000027484608,0.9982706,0.00000868436,1.409728e-7,0.00019482247,0.0012608664],"study_design_scores_gemma":[0.0010352938,0.00026040562,0.002002264,0.000010493548,0.0000064124333,0.000027006381,0.00008125337,0.9862039,0.004785349,0.0031608373,0.0020714435,0.00035534592],"about_ca_topic_score_codex":0.00014387384,"about_ca_topic_score_gemma":0.00068118284,"teacher_disagreement_score":0.99566454,"about_ca_system_score_codex":0.0002648014,"about_ca_system_score_gemma":0.000080209975,"threshold_uncertainty_score":0.99996686},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2081804334","doi":"10.1109/glocom.2012.6503147","title":"Rank-optimal channel selection strategy in cognitive networks","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Quality of service; Channel (broadcasting); Computer science; Selection (genetic algorithm); Cognitive radio; Throughput; Rank (graph theory); Convergence (economics); Quality (philosophy); Provisioning; Computer network; Mathematical optimization; Artificial intelligence; Mathematics; Wireless; Telecommunications; Combinatorics","score_opus":0.16538516075825044,"score_gpt":0.4570105232673575,"score_spread":0.2916253625091071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081804334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07771713,0.00025491216,0.9095588,0.000106245694,0.00025468768,0.00031897906,0.0000034234158,0.000052213018,0.011733651],"genre_scores_gemma":[0.99322456,0.000016649923,0.0004901221,0.00006503512,0.00036106908,0.000030564275,0.0000037346117,0.000010834878,0.0057974122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973881,0.0002183466,0.00037346085,0.0003375352,0.0009849626,0.00069758104],"domain_scores_gemma":[0.9980441,0.001232447,0.00007317798,0.00014367011,0.00032110017,0.0001855413],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025797682,0.0001238755,0.00020266928,0.00036629353,0.00010631474,0.00012261728,0.0002679164,0.00010783005,0.002083173],"category_scores_gemma":[0.001098935,0.00009009422,0.000052232586,0.0015938412,0.00008875641,0.0010801855,0.00009749197,0.00034071697,0.00052531366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004956782,0.00054103846,0.04671182,0.0000026992557,0.00003319161,0.000019573383,0.00090897037,0.6223544,0.000075768534,0.0006025417,0.007443023,0.32081133],"study_design_scores_gemma":[0.001237958,0.00018514412,0.08895136,0.000012109786,0.0000040796385,0.000027142978,0.0035081138,0.90092456,0.001016321,0.0030716667,0.000774388,0.00028718542],"about_ca_topic_score_codex":0.00006484527,"about_ca_topic_score_gemma":0.00013500366,"teacher_disagreement_score":0.91550744,"about_ca_system_score_codex":0.00006325818,"about_ca_system_score_gemma":0.000048081587,"threshold_uncertainty_score":0.99882907},"labels":[],"label_agreement":null},{"id":"W2084056659","doi":"10.1109/pimrc.2013.6666540","title":"Channel selection in Cognitive Radio Networks: A Switchable Bayesian Learning Automata approach","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Learning automata; Cognitive radio; Computer science; Channel (broadcasting); Probabilistic logic; Automaton; Bayesian probability; Bayesian network; Action selection; Selection (genetic algorithm); Theoretical computer science; Artificial intelligence; Computer network; Wireless; Telecommunications","score_opus":0.07435939515523153,"score_gpt":0.377254372149669,"score_spread":0.30289497699443746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084056659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007853938,0.00007769789,0.97875357,0.00023268482,0.00008469222,0.0007244923,7.695736e-7,0.00016843411,0.012103714],"genre_scores_gemma":[0.97469836,0.000025226454,0.0056815427,0.00006576228,0.00016117819,0.00022819857,0.00000766993,0.000025574835,0.019106494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962761,0.00038937954,0.0005325455,0.0007723554,0.0012895978,0.00074001536],"domain_scores_gemma":[0.9977188,0.001258194,0.00013844771,0.00021159594,0.00047659164,0.00019635634],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024289628,0.00019317273,0.00034103697,0.0006540146,0.00025778674,0.00046436407,0.0005215717,0.00014131669,0.0019604636],"category_scores_gemma":[0.002490845,0.00014491392,0.00006983145,0.00275838,0.00009958976,0.0012983115,0.00020403633,0.00064762885,0.0006845334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010824289,0.00044635145,0.017009405,0.000010752072,0.000046204645,0.000019232308,0.0015249472,0.73364913,0.00011333521,0.00015938847,0.012543071,0.23436995],"study_design_scores_gemma":[0.0006831298,0.00010635793,0.0143662775,0.000015396665,0.0000019482516,0.000021725224,0.0030538773,0.9767283,0.000093525356,0.004390779,0.00034997132,0.00018867855],"about_ca_topic_score_codex":0.0005165808,"about_ca_topic_score_gemma":0.00008959865,"teacher_disagreement_score":0.97307205,"about_ca_system_score_codex":0.00012125418,"about_ca_system_score_gemma":0.00008009139,"threshold_uncertainty_score":0.99895185},"labels":[],"label_agreement":null},{"id":"W2086587356","doi":"10.1007/s10994-013-5364-5","title":"BoostingTree: parallel selection of weak learners in boosting, with application to ranking","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Magyarország Kormánya; Alberta Innovates; Nemzeti Kutatási és Technológiai Hivatal; Hungarian Scientific Research Fund","keywords":"Boosting (machine learning); Gradient boosting; Machine learning; Artificial intelligence; Ranking (information retrieval); Decision tree; Computer science; Mathematics; Feature selection; Pattern recognition (psychology); Random forest","score_opus":0.03175220600398684,"score_gpt":0.3621694942332327,"score_spread":0.3304172882292459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086587356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47570717,0.000056824905,0.51987964,0.0007598484,0.000026478085,0.00066846836,7.452016e-7,0.00008141148,0.0028194264],"genre_scores_gemma":[0.97724617,0.0000035791425,0.020248536,0.00003784252,0.000046954774,0.000096959884,0.0000052230184,0.000026243964,0.0022884782],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970195,0.0002859545,0.0005395414,0.0005356711,0.0012143161,0.0004049909],"domain_scores_gemma":[0.99810374,0.0008769504,0.00029629344,0.00027095753,0.00033872252,0.00011335123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001953911,0.0001556107,0.0002964136,0.0006322474,0.00017951122,0.00012587172,0.00043479993,0.000060629278,0.0003649809],"category_scores_gemma":[0.0037771796,0.00011806615,0.000040559924,0.002018929,0.00006117595,0.00038898012,0.0001485913,0.0005214591,0.00027175696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006188652,0.00002504332,0.36882448,0.000005854422,0.000005196535,0.0000011725945,0.00052877946,0.43513834,0.004137064,0.00004044869,0.000075520154,0.19115618],"study_design_scores_gemma":[0.0010498277,0.00034444244,0.17779292,0.000068378926,0.0000044042304,0.00001571268,0.0012440255,0.8088503,0.001067305,0.0015997038,0.007670211,0.00029277027],"about_ca_topic_score_codex":0.0017180096,"about_ca_topic_score_gemma":0.0008075886,"teacher_disagreement_score":0.501539,"about_ca_system_score_codex":0.00008541432,"about_ca_system_score_gemma":0.000047986236,"threshold_uncertainty_score":0.4814598},"labels":[],"label_agreement":null},{"id":"W2094589420","doi":"10.1016/j.jet.2006.09.003","title":"Good news and bad news in two-armed bandits","year":2006,"lang":"en","type":"article","venue":"Journal of Economic Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"News media; Economics; Advertising; Computer science; Business","score_opus":0.04525898535024124,"score_gpt":0.4004500211495165,"score_spread":0.35519103579927525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094589420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97847795,0.0011938045,0.0087168375,0.0009623211,0.00073947915,0.00013742759,0.000009785018,0.000006226488,0.009756176],"genre_scores_gemma":[0.99436086,0.000120870405,0.0015655505,0.00010612437,0.00074305665,0.0000017547312,4.664171e-7,0.00001561971,0.0030857085],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99755114,0.00037293523,0.0011498688,0.00026179117,0.00035651002,0.00030774597],"domain_scores_gemma":[0.99648476,0.0023812994,0.00061142346,0.0002832308,0.00009260216,0.00014666749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004779814,0.00013260101,0.00045214093,0.00065093447,0.000062632294,0.00019147964,0.0005913883,0.00005200487,0.0007229489],"category_scores_gemma":[0.0008546744,0.00009691449,0.00011939831,0.00017484081,0.0001584353,0.00078550604,0.00011606342,0.00033956443,0.00017969942],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014761991,0.00036282025,0.19285646,0.000010283372,0.00010355293,0.00069674023,0.0008990447,0.047206018,0.0012639712,0.054847226,0.028096698,0.672181],"study_design_scores_gemma":[0.0030950692,0.00013091271,0.04195777,0.000024510218,0.000007401064,0.00030043838,0.0011409619,0.0012637986,0.0004965661,0.9276304,0.023760565,0.00019159095],"about_ca_topic_score_codex":0.00009393628,"about_ca_topic_score_gemma":0.0008968414,"teacher_disagreement_score":0.8727832,"about_ca_system_score_codex":0.00019396245,"about_ca_system_score_gemma":0.00019193735,"threshold_uncertainty_score":0.79157835},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.048601252740934964,"score_gpt":0.3624277436117635,"score_spread":0.31382649087082853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095762034","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55653214,0.0007494973,0.41186002,0.023569373,0.00057436415,0.0011581659,0.00051071803,0.0012839801,0.0037617225],"genre_scores_gemma":[0.8692268,0.00006925179,0.12947808,0.00012251965,0.00007015603,0.00001403965,0.000033422366,0.00002680184,0.0009589074],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99499124,0.000091514186,0.0008831189,0.0010463515,0.0021009324,0.00088681036],"domain_scores_gemma":[0.99645925,0.00042836173,0.0006027195,0.0014194805,0.0008753366,0.00021486905],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001053997,0.00041767283,0.00083711935,0.0018081749,0.00036899705,0.000111309746,0.0019553571,0.00045981945,0.00025475727],"category_scores_gemma":[0.008851621,0.00030886554,0.00015352425,0.0037358028,0.002451274,0.00077894103,0.00030617573,0.0012702837,0.000105309344],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016881425,0.0007390518,0.029698659,0.000014855917,0.00013305877,0.00037905126,0.00027609017,0.0061262106,0.003391887,0.0077704783,0.0021528974,0.94914895],"study_design_scores_gemma":[0.00589367,0.004243222,0.033053506,0.00043317387,0.000091329835,0.0004140711,0.0036381541,0.0067915865,0.017086208,0.090436384,0.8361249,0.0017937901],"about_ca_topic_score_codex":0.00002257209,"about_ca_topic_score_gemma":0.0000980966,"teacher_disagreement_score":0.94735515,"about_ca_system_score_codex":0.00013774828,"about_ca_system_score_gemma":0.00031014168,"threshold_uncertainty_score":0.99993634},"labels":[],"label_agreement":null},{"id":"W2096871811","doi":"10.2139/ssrn.1133118","title":"Strategic Manipulation of Empirical Tests","year":2008,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Business; Political science; Psychology","score_opus":0.2411058581692617,"score_gpt":0.47160472181368035,"score_spread":0.23049886364441866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096871811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89389724,0.001003365,0.10274218,0.0005237283,0.00014193972,0.00010530001,0.0000017474089,0.000017499202,0.0015669982],"genre_scores_gemma":[0.9959116,0.00067652954,0.0004688901,0.000018241826,0.0002010184,0.0000015057739,0.0000010579312,0.0000121008725,0.002709046],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953407,0.00021642025,0.0006464602,0.0002603919,0.0019924478,0.0015435916],"domain_scores_gemma":[0.9982585,0.0004910446,0.00030145366,0.00030219596,0.000529944,0.00011687655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039930195,0.000114702096,0.00024673337,0.00036724054,0.00026151002,0.000046608697,0.0006772463,0.00007530246,0.00018464285],"category_scores_gemma":[0.00093568844,0.000081271915,0.00013406164,0.00088716263,0.00015772124,0.00040122753,0.000060390073,0.0013808571,0.0001638961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012111983,0.0016821001,0.4018282,0.000017605023,0.0005516585,0.0006516022,0.0029447174,0.03679164,0.00803456,0.19566514,0.0041646194,0.34645694],"study_design_scores_gemma":[0.0005487435,0.0004543105,0.028021468,0.0000046389705,0.000004420401,0.0022954685,0.0011835446,0.0031035547,0.00027421885,0.96350545,0.00048697033,0.00011723018],"about_ca_topic_score_codex":0.000013394013,"about_ca_topic_score_gemma":0.00015622331,"teacher_disagreement_score":0.76784027,"about_ca_system_score_codex":0.00044760428,"about_ca_system_score_gemma":0.002665401,"threshold_uncertainty_score":0.5999214},"labels":[],"label_agreement":null},{"id":"W2102933744","doi":"10.5555/2025816.2025869","title":"The Bayesian pursuit algorithm: a new family of estimator learning automata","year":2011,"lang":"en","type":"article","venue":"Duo Research Archive (University of Oslo)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Learning automata; Prior probability; Bayesian probability; Conjugate prior; Estimator; Computer science; Algorithm; Artificial intelligence; Machine learning; Mathematics; Automaton; Statistics","score_opus":0.14377433902124603,"score_gpt":0.3747589294397711,"score_spread":0.2309845904185251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102933744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007678233,0.00024706373,0.9725991,0.0009946367,0.00011276807,0.0006341933,0.00009728711,0.000067960966,0.01756879],"genre_scores_gemma":[0.45049834,0.0012341549,0.5068202,0.000022718163,0.00020137393,0.0000053837416,0.000034104436,0.000096261996,0.04108749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912328,0.0015901492,0.00044535956,0.00071315863,0.0050185975,0.0009999371],"domain_scores_gemma":[0.9905013,0.0060459827,0.0003273424,0.001279415,0.0012476742,0.0005982752],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.008213995,0.00018786678,0.00046395286,0.0011382235,0.0014417891,0.00011060832,0.0047747083,0.00009415789,0.0007265812],"category_scores_gemma":[0.0057855654,0.00015259143,0.00024878286,0.0022050038,0.0026989821,0.0006550842,0.002270435,0.0011122549,0.0004309092],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007093703,0.0002298796,0.0021265156,0.000020770429,0.00013504202,0.00024690726,0.009463268,0.00023303875,0.003101224,0.004216976,0.027462004,0.952055],"study_design_scores_gemma":[0.003126501,0.0021819805,0.1498488,0.00015218403,0.000026872896,0.000031169388,0.063874185,0.34655324,0.0012555103,0.30996105,0.12243475,0.00055376784],"about_ca_topic_score_codex":0.002611362,"about_ca_topic_score_gemma":0.00039128892,"teacher_disagreement_score":0.95150125,"about_ca_system_score_codex":0.000087431705,"about_ca_system_score_gemma":0.00092504977,"threshold_uncertainty_score":0.9998582},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1316744920066128,"score_gpt":0.431294036276807,"score_spread":0.2996195442701942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103581319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9583387,0.00016498863,0.0017962626,0.0012830497,0.00040485576,0.0011256309,0.00006972689,0.000060097307,0.036756694],"genre_scores_gemma":[0.97420436,0.0065872846,0.009366245,0.00009866214,0.0002477817,0.00009937343,0.000044908407,0.000055163666,0.009296234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951015,0.00058726396,0.0010017379,0.0009495241,0.0013510225,0.001008954],"domain_scores_gemma":[0.9952697,0.0030514135,0.00012849875,0.00093784224,0.0003533354,0.0002592004],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004798828,0.000182681,0.00043829202,0.0018008957,0.00024628415,0.00011230566,0.0011945881,0.00018263841,0.00068567327],"category_scores_gemma":[0.008922496,0.00016653411,0.000087900655,0.0015608756,0.0005595332,0.00059408136,0.0004296184,0.000925077,0.000101472506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014642585,0.00040976802,0.027262384,0.0000045808256,0.000008042372,0.0002410571,0.00046780863,0.73681104,0.000051191702,0.000034199456,0.00022217417,0.23434132],"study_design_scores_gemma":[0.0028746482,0.00024336608,0.12444683,0.00004689948,9.050705e-7,0.000080375554,0.0018328513,0.8386262,0.00031302663,0.0031576846,0.02790012,0.00047706935],"about_ca_topic_score_codex":0.000048205748,"about_ca_topic_score_gemma":0.00067574286,"teacher_disagreement_score":0.23386425,"about_ca_system_score_codex":0.0007672518,"about_ca_system_score_gemma":0.00053851877,"threshold_uncertainty_score":0.99942577},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.18336283013052163,"score_gpt":0.44411397646752687,"score_spread":0.26075114633700525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105336508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05597288,0.00016373236,0.86732334,0.00418224,0.0002623348,0.0005702148,0.000027974382,0.00008142239,0.071415834],"genre_scores_gemma":[0.9647919,0.000035223256,0.0057766186,0.00011257468,0.00008588855,0.000011395794,0.0000014436271,0.000006235561,0.0291787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979058,0.000044281987,0.00041149108,0.0002189794,0.0012101415,0.00020930065],"domain_scores_gemma":[0.9988318,0.00027542087,0.00010094582,0.00038082522,0.00032730616,0.00008367298],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00066137826,0.00006626507,0.00014938237,0.00035935946,0.000057816218,0.000068294794,0.00035632667,0.00003340969,0.00666677],"category_scores_gemma":[0.0014159927,0.000043076005,0.0000612132,0.0009041767,0.000077701014,0.00040073495,0.000098984434,0.000057995323,0.00075219024],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059025908,0.00046782833,0.002958045,0.000025560981,0.00003549022,0.000014447129,0.005577375,0.0010564208,0.0058002276,0.049022023,0.05517959,0.87980396],"study_design_scores_gemma":[0.0009440474,0.00021063793,0.0017977707,0.000008126662,0.0000024722601,0.000014769575,0.00057719805,0.7455637,0.037800472,0.16939752,0.043473464,0.00020983616],"about_ca_topic_score_codex":0.000029829658,"about_ca_topic_score_gemma":0.000010898924,"teacher_disagreement_score":0.908819,"about_ca_system_score_codex":0.00003970194,"about_ca_system_score_gemma":0.000022225397,"threshold_uncertainty_score":0.9942413},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.14089624632931172,"score_gpt":0.28580462013331953,"score_spread":0.1449083738040078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106233414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9568207,0.000095057825,0.033539295,0.000058451333,0.0001687598,0.00023146042,0.0000033367066,0.00008455871,0.008998344],"genre_scores_gemma":[0.97655874,0.000069425754,0.00045540254,0.000048975053,0.00009640031,8.4703214e-7,0.0000024817703,0.000020403199,0.022747317],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99755,0.0003004426,0.00024385909,0.00066789245,0.00044986044,0.00078791403],"domain_scores_gemma":[0.99730057,0.0011360494,0.00015755664,0.0005988627,0.00049967045,0.00030726645],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016581296,0.00021028252,0.0003291389,0.0005782013,0.00019428342,0.000078968515,0.0007355195,0.000111074354,0.000559491],"category_scores_gemma":[0.0017372717,0.00016261618,0.000094524316,0.0021280444,0.00026439707,0.0015301256,0.00028751182,0.00055789476,0.0016777851],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087138487,0.0002559694,0.8779716,0.000013222794,0.000053103577,0.00075459544,0.0010976668,0.089749,0.0003938799,0.0038687324,0.0012996466,0.02367122],"study_design_scores_gemma":[0.007282253,0.0017689981,0.5236578,0.00020222671,0.00006831569,0.00015462145,0.009135948,0.3154011,0.0018650591,0.017649285,0.12062445,0.0021899608],"about_ca_topic_score_codex":0.00009535285,"about_ca_topic_score_gemma":0.00013004833,"teacher_disagreement_score":0.3543138,"about_ca_system_score_codex":0.00021287278,"about_ca_system_score_gemma":0.00009908293,"threshold_uncertainty_score":0.99909955},"labels":[],"label_agreement":null},{"id":"W2107105626","doi":"","title":"Optimal unbiased estimators for evaluating agent performance","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Estimator; Variance (accounting); Outcome (game theory); Computer science; Minimum-variance unbiased estimator; Set (abstract data type); Bias of an estimator; Mathematical optimization; Mathematics; Statistics; Mathematical economics; Economics","score_opus":0.25992983276054066,"score_gpt":0.5149763499626402,"score_spread":0.25504651720209953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107105626","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45213994,0.000031829764,0.54512346,0.00019020315,0.0001575814,0.00037873842,0.000008460389,0.000057124213,0.0019126233],"genre_scores_gemma":[0.66738003,0.0000014381192,0.3151765,0.000050926126,0.00015063451,0.000093527495,0.000009008365,0.000017295353,0.01712063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644816,0.000068419155,0.00056190236,0.0004956345,0.0019423966,0.00048348587],"domain_scores_gemma":[0.9969292,0.0017913296,0.00013051432,0.0004558685,0.0005961957,0.00009686549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032981804,0.00013506036,0.00021089659,0.0002290903,0.00031777978,0.00022576953,0.00060459593,0.000050046605,0.00081796554],"category_scores_gemma":[0.0025749337,0.00009364553,0.000104263774,0.0006362209,0.00010358202,0.00042632356,0.00012050393,0.0001032794,0.00049810135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014629721,0.0001210349,0.006381548,0.000013717148,0.000010653614,0.000006603217,0.00007886455,0.7084318,0.001431262,0.00063621684,0.025012413,0.25772962],"study_design_scores_gemma":[0.0006882613,0.00021959873,0.007976484,0.000006259345,0.000003630245,0.0000052425894,0.00011603058,0.9706879,0.008468191,0.0042273384,0.00744776,0.0001532842],"about_ca_topic_score_codex":0.000025298456,"about_ca_topic_score_gemma":0.000010069107,"teacher_disagreement_score":0.26225615,"about_ca_system_score_codex":0.00008257548,"about_ca_system_score_gemma":0.00012061451,"threshold_uncertainty_score":0.89561486},"labels":[],"label_agreement":null},{"id":"W2110454495","doi":"10.48550/arxiv.1405.3318","title":"Adaptive Monte Carlo via Bandit Allocation","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Monte Carlo method; Estimator; Mathematical optimization; Computer science; Set (abstract data type); Mean squared error; Mathematics; Statistics","score_opus":0.1881229664939298,"score_gpt":0.2733599798044529,"score_spread":0.08523701331052314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110454495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15493666,0.000019216805,0.8403268,0.000113117465,0.0002010206,0.00017450833,0.000006599221,0.00007285817,0.0041492246],"genre_scores_gemma":[0.98714995,0.000015087691,0.00048092098,0.00006418651,0.000109999644,7.3225124e-7,0.0000018393835,0.0000139125195,0.012163382],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780476,0.0003189614,0.00023596834,0.0007992065,0.00045549884,0.0003855804],"domain_scores_gemma":[0.9973326,0.0009007515,0.00016085849,0.00082719483,0.00054833875,0.00023028755],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012009601,0.00016360603,0.00023818036,0.00037030107,0.0002587713,0.00008162931,0.0010167555,0.000100358644,0.0003439765],"category_scores_gemma":[0.0008368108,0.00014991223,0.00012210515,0.0014201932,0.00022107094,0.00078627083,0.0002394607,0.00022594392,0.0015655347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037489657,0.00017252755,0.008491734,0.0000053648178,0.00007474021,0.00016776596,0.0004987225,0.90456563,0.00034514425,0.026955083,0.0041676485,0.054180723],"study_design_scores_gemma":[0.0006795078,0.00017224268,0.005838565,0.000006826396,0.000013784294,0.000004240594,0.0004538886,0.92224,0.00038058782,0.061527815,0.008445402,0.00023709668],"about_ca_topic_score_codex":0.00014506634,"about_ca_topic_score_gemma":0.00018949303,"teacher_disagreement_score":0.8398459,"about_ca_system_score_codex":0.00016142704,"about_ca_system_score_gemma":0.000059636604,"threshold_uncertainty_score":0.99921185},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4019517217496925,"score_gpt":0.3403438641409024,"score_spread":0.06160785760879012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110582581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25402513,0.00004959971,0.7424408,0.00014270394,0.0007253479,0.001198065,0.00032977888,0.00011797185,0.0009705576],"genre_scores_gemma":[0.9874266,0.000021421607,0.00209412,0.000032330452,0.00039488624,0.000025947209,0.00012523727,0.000054791253,0.009824689],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961184,0.00019774896,0.0004982642,0.0016246111,0.0007295111,0.00083141465],"domain_scores_gemma":[0.99497205,0.0011374424,0.0006281201,0.0016025614,0.0012180059,0.00044179562],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011548917,0.00045445756,0.00062144967,0.000614698,0.00061094546,0.00041007303,0.00227595,0.00038149094,0.00024830987],"category_scores_gemma":[0.0011198631,0.0003861517,0.0002598037,0.0012712348,0.0004985525,0.0008941838,0.00078658375,0.0006844122,0.00012844625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052657607,0.0018291638,0.08460134,0.0010913394,0.0010993105,0.0014949334,0.0049527166,0.82658976,0.00017604626,0.05210849,0.008619096,0.012172038],"study_design_scores_gemma":[0.0048780935,0.0006984707,0.031823013,0.00044917376,0.0006069489,0.0000529332,0.0025870588,0.5084091,0.0005371974,0.43233532,0.014985799,0.0026369356],"about_ca_topic_score_codex":0.000028807013,"about_ca_topic_score_gemma":0.00016681092,"teacher_disagreement_score":0.7403467,"about_ca_system_score_codex":0.00026273096,"about_ca_system_score_gemma":0.0007392,"threshold_uncertainty_score":0.99985904},"labels":[],"label_agreement":null},{"id":"W2110722897","doi":"10.1109/icassp.2006.1660926","title":"Transmission Scheduling for Sensor Network Lifetime Maximization: A Shortest Path Bandit Formulation","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Wireless sensor network; Scheduling (production processes); Maximization; Mathematical optimization; Shortest path problem; Computer science; Independent and identically distributed random variables; Job shop scheduling; Dynamic priority scheduling; Fading; Fair-share scheduling; Channel (broadcasting); Computer network; Mathematics; Random variable; Theoretical computer science; Quality of service; Routing (electronic design automation)","score_opus":0.06525706696555161,"score_gpt":0.37955171465594856,"score_spread":0.31429464769039694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110722897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034485066,0.00014004951,0.99280584,0.00094119646,0.00017525656,0.0007298958,0.000014680929,0.00011836759,0.0016262316],"genre_scores_gemma":[0.59721965,0.000013526265,0.3906275,0.00011366705,0.0012734738,0.00006439259,0.000105290936,0.000038310594,0.010544197],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99660945,0.00008773804,0.0007577508,0.00059120567,0.001413804,0.0005400642],"domain_scores_gemma":[0.9971123,0.0015485284,0.00015693977,0.00040610414,0.0006307053,0.00014546253],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017581608,0.00018389957,0.00028396293,0.00020223384,0.00047825792,0.00030578498,0.00037386463,0.00013485893,0.00096493284],"category_scores_gemma":[0.0006322856,0.00013211758,0.0001573606,0.001032725,0.000044895292,0.00062135304,0.000048866703,0.00012997542,0.00012711521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114835115,0.000058127684,0.002742485,0.000004302233,0.0000064212504,0.0000046034515,0.00003106504,0.9360881,0.00031189815,0.0016617106,0.006371931,0.052604537],"study_design_scores_gemma":[0.0007203967,0.000092783535,0.0031209476,0.000018499888,0.000007494395,0.0000067886126,0.000053510386,0.8778985,0.0007524803,0.07597727,0.041153338,0.00019798595],"about_ca_topic_score_codex":0.000016834852,"about_ca_topic_score_gemma":0.000016083439,"teacher_disagreement_score":0.60217834,"about_ca_system_score_codex":0.000061290084,"about_ca_system_score_gemma":0.00008382042,"threshold_uncertainty_score":0.9999483},"labels":[],"label_agreement":null},{"id":"W2111440138","doi":"","title":"Online learning with expert advice and finite-horizon constraints","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Computer science; Sublinear function; Novelty; Mathematical optimization; Time horizon; Adversary; Artificial intelligence; Online learning; Quality (philosophy); Machine learning; Mathematics","score_opus":0.10906569035608918,"score_gpt":0.4113532463015598,"score_spread":0.30228755594547063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111440138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6045177,0.0004980027,0.36676764,0.0013957309,0.00013818106,0.00035831422,0.000017270777,0.00032068303,0.02598647],"genre_scores_gemma":[0.93644017,0.00020240995,0.039194565,0.0001671007,0.000110544635,0.0000072897724,0.0000057588645,0.000016719998,0.023855416],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974373,0.000119722645,0.0002907797,0.00048766032,0.0013394511,0.00032510303],"domain_scores_gemma":[0.9970401,0.0020491676,0.0000774987,0.00028701779,0.00035185475,0.0001943474],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00057013665,0.0001324669,0.0002231247,0.00021050734,0.00031378644,0.00007786803,0.00031198224,0.00005442907,0.0015165512],"category_scores_gemma":[0.002471285,0.000079915444,0.000026998247,0.0006226601,0.0007157921,0.00037878298,0.00014091276,0.0002994505,0.00019333576],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024208275,0.00029814508,0.030458795,0.000004425767,0.0000365095,0.0006796564,0.0026109782,0.0043893903,0.00055885874,0.00023698047,0.0065345154,0.9539497],"study_design_scores_gemma":[0.009963236,0.0068089953,0.08495119,0.00013593766,0.000015009727,0.0026718064,0.053507213,0.24054615,0.005364205,0.0059188567,0.5877993,0.002318066],"about_ca_topic_score_codex":0.000043921165,"about_ca_topic_score_gemma":0.00005695697,"teacher_disagreement_score":0.9516316,"about_ca_system_score_codex":0.000020143783,"about_ca_system_score_gemma":0.000084020154,"threshold_uncertainty_score":0.9993962},"labels":[],"label_agreement":null},{"id":"W2116497114","doi":"10.1007/978-3-540-72927-3_19","title":"Strategies for Prediction Under Imperfect Monitoring","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Imperfect; Computer science; Constructive; Logarithm; Consistency (knowledge bases); Convergence (economics); Simple (philosophy); Asymptotically optimal algorithm; Mathematical optimization; Algorithm; Artificial intelligence; Mathematics","score_opus":0.14308238564303533,"score_gpt":0.4279685929098571,"score_spread":0.2848862072668218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116497114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014339606,0.00044288012,0.9928592,0.00015694315,0.003341451,0.0006660541,0.000041802625,0.00008732568,0.0022609502],"genre_scores_gemma":[0.39464512,0.00014763871,0.59137523,0.00043927037,0.008314978,0.00007823203,0.000023211978,0.00018227992,0.004794011],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99313074,0.000036342928,0.00081793225,0.0016958668,0.0034435631,0.0008755301],"domain_scores_gemma":[0.9931648,0.004237153,0.00030098064,0.0010988353,0.0009994314,0.00019879825],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004861481,0.00043897456,0.00053827814,0.0017834706,0.00044462248,0.0011581592,0.002335814,0.00040670534,0.0000633829],"category_scores_gemma":[0.00080199115,0.00034152847,0.00019100375,0.00093956356,0.0010276957,0.0010247359,0.000589614,0.0008793776,0.000057035588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030951855,0.000012674536,0.00011218887,0.0000129517875,0.000008674696,0.000018963085,0.00024890417,0.25374734,0.00020560433,0.0021125088,0.00003544068,0.7434538],"study_design_scores_gemma":[0.00036487955,0.00033638882,0.0006276586,0.00017168272,0.0000065249324,0.000031249925,0.000008196867,0.19129139,0.0022099558,0.8012924,0.003218982,0.00044067885],"about_ca_topic_score_codex":0.000010512664,"about_ca_topic_score_gemma":0.000057024405,"teacher_disagreement_score":0.7991799,"about_ca_system_score_codex":0.0005393423,"about_ca_system_score_gemma":0.0008725174,"threshold_uncertainty_score":0.9999037},"labels":[],"label_agreement":null},{"id":"W2116541203","doi":"10.1109/itw.2008.4578656","title":"Streaming algorithms for estimating entropy","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; National Defense Science and Engineering Graduate; National Science Foundation","keywords":"Rényi entropy; Shannon's source coding theorem; Entropy (arrow of time); Computation; Computer science; Maximum entropy probability distribution; Algorithm; Entropy power inequality; Information theory; Entropy rate; Rate of convergence; Mathematics; Joint entropy; Principle of maximum entropy; Applied mathematics; Mathematical optimization; Maximum entropy thermodynamics; Joint quantum entropy; Statistics; Artificial intelligence","score_opus":0.23567286712257887,"score_gpt":0.4722105377626748,"score_spread":0.23653767064009593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116541203","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009091716,0.00003953636,0.9882757,0.00032175827,0.00035977009,0.0003218112,0.000015165506,0.00008868473,0.0014858401],"genre_scores_gemma":[0.077305906,0.0000052513174,0.90645564,0.00007934297,0.00043230172,0.000054661872,0.0000051634074,0.000018957297,0.015642766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694735,0.000055221644,0.00049522053,0.00051373965,0.0015042815,0.00048417627],"domain_scores_gemma":[0.9958363,0.0029079458,0.00011734119,0.0004716885,0.00050640135,0.00016031478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012199908,0.00012950023,0.00024564212,0.0002345352,0.00050641934,0.00011582185,0.0006575615,0.000052183925,0.0006503964],"category_scores_gemma":[0.00648473,0.000089780275,0.000120544835,0.0005748123,0.0001495406,0.0004610827,0.00014896317,0.00012092331,0.00038461183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043729462,0.00010847185,0.002043621,0.0000060942552,0.00002324936,0.000066186665,0.0006434561,0.0117826,0.0008818109,0.001209143,0.02463474,0.9585569],"study_design_scores_gemma":[0.0006728319,0.00011476272,0.0009592272,0.0000051835113,0.0000021496248,0.00005781128,0.00042611873,0.9530221,0.0035718586,0.025425019,0.015565423,0.00017751605],"about_ca_topic_score_codex":0.000020778052,"about_ca_topic_score_gemma":0.000005200295,"teacher_disagreement_score":0.9583794,"about_ca_system_score_codex":0.00005556627,"about_ca_system_score_gemma":0.000094986346,"threshold_uncertainty_score":0.77632964},"labels":[],"label_agreement":null},{"id":"W2118191986","doi":"10.1613/jair.1336","title":"Can We Learn to Beat the Best Stock","year":2004,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Algorithmic trading; Technical analysis; Computer science; Smoothing; Heuristics; Stock market; Trading strategy; Stock (firearms); Pairs trade; Econometrics; Financial economics; Empirical evidence; Artificial intelligence; Machine learning; Context (archaeology); Alternative trading system; Economics; Engineering","score_opus":0.5013709025139251,"score_gpt":0.568274054729651,"score_spread":0.06690315221572585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118191986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2256978,0.001332546,0.56125647,0.20731694,0.0015936197,0.0013301832,0.000023453456,0.000023880799,0.001425104],"genre_scores_gemma":[0.99245304,0.0003717598,0.003152168,0.00013411755,0.0012819063,0.000015835958,2.644654e-7,0.000030695664,0.0025602127],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98703885,0.00094015035,0.0016017351,0.000484795,0.008697879,0.0012365903],"domain_scores_gemma":[0.9877302,0.0046388907,0.0003149854,0.00093189755,0.0056037116,0.0007803313],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022845417,0.00019123113,0.00043293167,0.0016793563,0.0009313023,0.0010194455,0.0038770356,0.000119167154,0.00064518733],"category_scores_gemma":[0.025727868,0.00010809508,0.00026195083,0.0050280783,0.0008713827,0.0005192182,0.00064293324,0.0021781733,0.0030085999],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003442689,0.00027990944,0.000104056526,0.0000039761135,0.000028227825,0.00024239713,0.0037687013,0.06719098,0.0043716,0.0039255526,0.0017367855,0.91800356],"study_design_scores_gemma":[0.00010550207,0.0022657774,0.00013625062,0.00015058009,0.000007933061,0.0001945965,0.041566625,0.002492883,0.090108044,0.8273155,0.035401475,0.00025479996],"about_ca_topic_score_codex":0.00027729786,"about_ca_topic_score_gemma":0.0010247068,"teacher_disagreement_score":0.91774875,"about_ca_system_score_codex":0.00061399414,"about_ca_system_score_gemma":0.0014006689,"threshold_uncertainty_score":0.9977677},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3179026584292263,"score_gpt":0.46215023141597483,"score_spread":0.1442475729867485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119738618","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089494896,0.000037050115,0.9950824,0.00012525303,0.00055628474,0.0006984963,0.000044839846,0.000098614815,0.0024621456],"genre_scores_gemma":[0.41564652,0.000006764012,0.5122555,0.0003400656,0.0009702462,0.00040790753,0.000016236832,0.00008791894,0.07026884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970291,0.000060593575,0.0005644316,0.00068244996,0.0010678,0.00059557083],"domain_scores_gemma":[0.99669707,0.0013398692,0.00013158102,0.0007262835,0.0008402856,0.00026492024],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001932964,0.00018094247,0.00030702763,0.00031816194,0.00020984988,0.000089322035,0.0010401865,0.000102517195,0.0025512855],"category_scores_gemma":[0.004526408,0.00011983846,0.00016148394,0.0006372106,0.00016005388,0.00044570793,0.00020481208,0.00016658432,0.000764601],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095306203,0.0007006625,0.00022838704,0.000021607333,0.00013601748,0.00003247132,0.0026400103,0.0015367146,0.002509969,0.0038069647,0.026981575,0.96045256],"study_design_scores_gemma":[0.0021851936,0.00088677066,0.0011635849,0.000008604841,0.000014474169,0.000018683488,0.00074380037,0.86391705,0.012315394,0.10438122,0.013848549,0.00051669806],"about_ca_topic_score_codex":0.00004168634,"about_ca_topic_score_gemma":0.000024568064,"teacher_disagreement_score":0.95993584,"about_ca_system_score_codex":0.000039658342,"about_ca_system_score_gemma":0.000109088985,"threshold_uncertainty_score":0.9983605},"labels":[],"label_agreement":null},{"id":"W2133081350","doi":"10.1109/cdc.2010.5717262","title":"Online Convex Programming and regularization in adaptive control","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Convex optimization; Generalization; Sequence (biology); Mathematical optimization; Computer science; Regular polygon; Dynamic programming; Regularization (linguistics); Adaptive control; Convex function; Convex analysis; Control theory (sociology); Control (management); Algorithm; Mathematics; Artificial intelligence","score_opus":0.07039671897197886,"score_gpt":0.41335475547406814,"score_spread":0.3429580365020893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133081350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17948124,0.000056976223,0.8160864,0.0019421118,0.00023472481,0.00079703773,0.00001637934,0.00006243191,0.0013226565],"genre_scores_gemma":[0.95261055,0.0000027919768,0.043162137,0.000084840045,0.00006416439,0.000014705804,0.0000033544113,0.0000069094663,0.004050564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983285,0.00008200714,0.00030037283,0.00033722204,0.0007303382,0.00022155674],"domain_scores_gemma":[0.9984716,0.0008100032,0.00006652535,0.00024937445,0.00030845893,0.00009404019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013793992,0.00007539083,0.00017094717,0.00024733492,0.00005976359,0.00012831103,0.00023243994,0.000073588744,0.00023383324],"category_scores_gemma":[0.0023347524,0.000051889958,0.000019090932,0.0005815232,0.00018601156,0.00035426253,0.00007250267,0.000280054,0.00003250721],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008723677,0.00017295731,0.020132035,0.0000015827899,0.0000064423234,0.000022197824,0.000295475,0.00016962357,0.0024642025,0.0069691776,0.0001251717,0.9695539],"study_design_scores_gemma":[0.0042085317,0.0003155621,0.14134982,0.000012848213,0.000004836481,0.00002953752,0.0026993207,0.67289484,0.0019311152,0.15363759,0.022556104,0.0003598952],"about_ca_topic_score_codex":0.000026454332,"about_ca_topic_score_gemma":0.00068382634,"teacher_disagreement_score":0.969194,"about_ca_system_score_codex":0.0000123227555,"about_ca_system_score_gemma":0.00004721666,"threshold_uncertainty_score":0.27950853},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04799188361605175,"score_gpt":0.3932287474444243,"score_spread":0.3452368638283726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135829225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5296431,0.00034248334,0.46468508,0.0026812819,0.000024107765,0.0002618881,0.00000769984,0.00009047304,0.0022638338],"genre_scores_gemma":[0.94772273,0.00012521111,0.049925838,0.0002199005,0.000047629776,0.0000064865326,0.0000058465466,0.000010103232,0.001936234],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974195,0.00007680108,0.00035705842,0.00050843,0.0012266075,0.00041163186],"domain_scores_gemma":[0.99804515,0.0012181149,0.000060602946,0.00022177056,0.0003282385,0.00012613487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012315676,0.0001379446,0.00024291378,0.0009241845,0.00021352714,0.000204029,0.00027367705,0.00005863066,0.00014956169],"category_scores_gemma":[0.0024781278,0.00008834984,0.000023737291,0.002890507,0.00008782669,0.0006696425,0.000041961797,0.00033792836,0.00001402213],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003456699,0.000283091,0.0033823743,0.000013675328,0.000005737496,0.00013947062,0.0022881455,0.008832759,0.00027364594,0.0001406286,0.00013916078,0.98415565],"study_design_scores_gemma":[0.010781737,0.0051188287,0.5122403,0.0015606233,0.000036509384,0.0007101194,0.048883807,0.22006556,0.004341031,0.17567927,0.018256364,0.0023258387],"about_ca_topic_score_codex":0.000009752012,"about_ca_topic_score_gemma":0.0006395647,"teacher_disagreement_score":0.9818298,"about_ca_system_score_codex":0.000033453256,"about_ca_system_score_gemma":0.00015669338,"threshold_uncertainty_score":0.3602802},"labels":[],"label_agreement":null},{"id":"W2136723863","doi":"","title":"An Empirical Analysis of Off-policy Learning in Discrete MDPs","year":2012,"lang":"en","type":"article","venue":"European Workshop on Reinforcement Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Dynamic programming; Variance (accounting); Sampling (signal processing); Population; Mathematical optimization; Monte Carlo method; Policy analysis; Artificial intelligence; Algorithm; Statistics; Mathematics; Economics","score_opus":0.10710063990214132,"score_gpt":0.45902569817125777,"score_spread":0.35192505826911646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136723863","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6798519,0.00028540034,0.2291816,0.00064551714,0.00022418448,0.00048741855,0.0000029888301,0.00022831111,0.08909265],"genre_scores_gemma":[0.98375547,0.00009230338,0.00042329318,0.00017666505,0.0002768363,0.0000064871215,0.000047207763,0.00005123543,0.015170499],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9918799,0.0025580886,0.0013334474,0.0006662299,0.002532211,0.0010301189],"domain_scores_gemma":[0.9960097,0.0018641377,0.0005970396,0.0008874975,0.0002101729,0.00043142255],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009275687,0.0003096567,0.00067250157,0.00330378,0.0002980579,0.0002212232,0.0010782907,0.00007730678,0.0013214846],"category_scores_gemma":[0.008941299,0.0002473272,0.00030103239,0.0070686084,0.00017907869,0.00089239783,0.00045161045,0.0013085512,0.00061089115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009129043,0.00005564754,0.09694895,0.0000021393107,0.00008571392,0.000012793517,0.0025843945,0.78953665,0.000082662715,0.00013403148,0.000085053936,0.11038065],"study_design_scores_gemma":[0.0008099185,0.00044313754,0.25981784,0.00007190767,0.000076443655,0.0000017503515,0.0051645916,0.6482854,0.00012330314,0.000024494351,0.084709324,0.00047189186],"about_ca_topic_score_codex":0.000021565154,"about_ca_topic_score_gemma":0.000009795866,"teacher_disagreement_score":0.30390355,"about_ca_system_score_codex":0.00019218444,"about_ca_system_score_gemma":0.00006764719,"threshold_uncertainty_score":0.9999979},"labels":[],"label_agreement":null},{"id":"W2142115504","doi":"10.48550/arxiv.1503.05087","title":"Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Weighting; Computer science; Algorithm; Mathematical optimization; Mathematics","score_opus":0.1796660741256431,"score_gpt":0.3228558868453828,"score_spread":0.1431898127197397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142115504","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43235317,0.00032775235,0.5590436,0.00006555736,0.0041704187,0.0019842193,0.0006494316,0.00031878724,0.001087069],"genre_scores_gemma":[0.9814834,0.00010436444,0.011688766,0.00006020979,0.0017408212,0.000028453587,0.00028603213,0.00014926701,0.004458663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912309,0.0005589945,0.0013080364,0.0038297963,0.0016544128,0.0014178681],"domain_scores_gemma":[0.9894818,0.0013104884,0.0016549347,0.003249833,0.0032136056,0.0010893098],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0053598573,0.0009151635,0.0014577168,0.0007566898,0.0007113717,0.00054242986,0.0043518995,0.0007558392,0.00017639706],"category_scores_gemma":[0.0019346195,0.0008542003,0.0005862219,0.0018147015,0.0005996449,0.00084414275,0.0019834437,0.0015082831,0.00018299326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016374348,0.0020654614,0.056936312,0.0001999833,0.00064479373,0.0021201842,0.0016002255,0.86828405,0.00006227069,0.02953901,0.014165066,0.022745183],"study_design_scores_gemma":[0.0024995767,0.00024712997,0.0005046083,0.00007664548,0.000081865524,0.000011382556,0.0004932025,0.7474284,0.00018428652,0.24243364,0.005101633,0.00093764055],"about_ca_topic_score_codex":0.00006412086,"about_ca_topic_score_gemma":0.00010537982,"teacher_disagreement_score":0.54913026,"about_ca_system_score_codex":0.0012259317,"about_ca_system_score_gemma":0.0013434562,"threshold_uncertainty_score":0.9993909},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.20250909729079805,"score_gpt":0.46313926625110025,"score_spread":0.2606301689603022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142971854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057959575,0.00002653591,0.9399899,0.0012278417,0.00031827544,0.00026855196,0.0000023640894,0.00006324568,0.00014369431],"genre_scores_gemma":[0.71828413,0.0000028676225,0.28145596,0.00016751779,0.000067546884,0.0000046986765,7.909129e-7,0.0000056600397,0.00001083677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99509025,0.00023160016,0.0006439523,0.0009440239,0.002380779,0.00070939574],"domain_scores_gemma":[0.9970365,0.0014558246,0.0001241576,0.00062470295,0.0004865764,0.0002722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049612257,0.00019143357,0.0003035006,0.00069955667,0.00042100297,0.0007090758,0.0017069179,0.000064127256,0.00011155612],"category_scores_gemma":[0.003552325,0.00014600715,0.00005309462,0.0037928005,0.0020844399,0.0026059854,0.00021642786,0.00027803818,0.00012560532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012665815,0.0005823241,0.00066303083,0.000005642567,0.000003935347,0.00011236061,0.0046440056,0.26235524,0.010759509,0.45753068,0.000070881215,0.26314571],"study_design_scores_gemma":[0.00032038434,0.00010686532,0.006729311,0.000019717843,0.0000011058486,0.000010221467,0.000052830725,0.6571352,0.0029338745,0.33254933,0.00001185038,0.00012933752],"about_ca_topic_score_codex":0.0000032527341,"about_ca_topic_score_gemma":0.0000024058413,"teacher_disagreement_score":0.6603246,"about_ca_system_score_codex":0.00015891918,"about_ca_system_score_gemma":0.0001891846,"threshold_uncertainty_score":0.7680205},"labels":[],"label_agreement":null},{"id":"W2142975476","doi":"10.1287/ijoc.2013.0553","title":"Online Sequential Optimization with Biased Gradients: Theory and Applications to Censored Demand","year":2013,"lang":"en","type":"article","venue":"INFORMS journal on computing","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convexity; Mathematical optimization; Convex optimization; Generalization; Convex function; Computer science; Regular polygon; Gradient descent; Mathematics; Artificial intelligence","score_opus":0.05892505650074767,"score_gpt":0.39245925833899264,"score_spread":0.333534201838245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142975476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17514025,0.00002126093,0.8238321,0.0003089624,0.000077679404,0.00039060274,0.0000055635483,0.00002422125,0.00019935015],"genre_scores_gemma":[0.8666235,0.00001945184,0.13157715,0.00087124715,0.0005289587,0.0000146236325,0.000009156331,0.000024182438,0.00033171073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759406,0.00011264839,0.0005974696,0.00024996488,0.0011022983,0.00034357788],"domain_scores_gemma":[0.9971859,0.001057763,0.00031786395,0.000255717,0.00083507085,0.00034769299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019347301,0.00014111663,0.0002037752,0.0005253954,0.0005376314,0.0008018073,0.00043309986,0.000045083056,0.00014607223],"category_scores_gemma":[0.0010921923,0.00008278431,0.000041242096,0.00079934485,0.00009577018,0.0007432903,0.00013686846,0.0003407106,0.000109861336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000843619,0.000056900146,0.0007925859,0.0000021333808,0.000019010457,0.0000066786383,0.00031177045,0.77696097,0.000024462066,0.00047346242,0.00024729437,0.22102039],"study_design_scores_gemma":[0.003133921,0.001166328,0.023855165,0.00020584544,0.00001823433,0.00069691095,0.0029645602,0.9349091,0.00043547704,0.023226395,0.008778932,0.0006091564],"about_ca_topic_score_codex":0.0000053917206,"about_ca_topic_score_gemma":0.0000028279057,"teacher_disagreement_score":0.69225496,"about_ca_system_score_codex":0.00007728678,"about_ca_system_score_gemma":0.000066904046,"threshold_uncertainty_score":0.77318466},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.059531194792093976,"score_gpt":0.4010226266591596,"score_spread":0.34149143186706565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146412174","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6994618,0.00008454847,0.29157153,0.0030295525,0.0021845698,0.0009544429,0.000066755674,0.00031728152,0.0023295188],"genre_scores_gemma":[0.9910201,0.000004388096,0.008039988,0.00024242455,0.00020644511,0.00005797422,0.00007586862,0.000015506148,0.00033733775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99649936,0.00015109166,0.0011895534,0.00035784667,0.0013656103,0.00043655073],"domain_scores_gemma":[0.9972197,0.0005730354,0.00063892687,0.000348937,0.00096224697,0.00025716287],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019399659,0.00022763664,0.0003118643,0.00047413327,0.00055610645,0.0025114452,0.000515435,0.00019982024,0.00011873261],"category_scores_gemma":[0.0024909305,0.00017640094,0.0000500529,0.00071147416,0.0001544467,0.0087402435,0.00017022055,0.00062605954,0.00015542633],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076326294,0.000036168003,0.0029242486,0.000171176,0.000011085968,0.0000035474566,0.0020199823,0.018814303,0.00068890635,0.00011040183,0.0041509564,0.9709929],"study_design_scores_gemma":[0.00055703084,0.00010188911,0.0063994457,0.000037461396,0.000004586907,0.0001528346,0.0010292083,0.94024765,0.00018292853,0.0001071204,0.0509233,0.00025651505],"about_ca_topic_score_codex":0.000048065067,"about_ca_topic_score_gemma":0.000016532984,"teacher_disagreement_score":0.9707364,"about_ca_system_score_codex":0.00005295148,"about_ca_system_score_gemma":0.0001485167,"threshold_uncertainty_score":0.99852407},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.13282433303024543,"score_gpt":0.3771460626394505,"score_spread":0.24432172960920506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146807381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31339753,0.015329558,0.56451917,0.0020861528,0.008075756,0.004816557,0.011104418,0.00072307524,0.07994782],"genre_scores_gemma":[0.97872525,0.00057071674,0.0061419685,0.0003293398,0.0005233282,0.000027809405,0.0001665953,0.000090346635,0.01342464],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.98950654,0.00061235134,0.0021021494,0.0018363335,0.0042572934,0.0016853499],"domain_scores_gemma":[0.9921967,0.0024095702,0.0011906241,0.0021215088,0.0013208828,0.0007607531],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003324958,0.00081133307,0.0023244529,0.0010627046,0.00057979923,0.00027513024,0.0026684552,0.00091289997,0.014049124],"category_scores_gemma":[0.0014751578,0.0006783378,0.0023885611,0.009074482,0.0014332343,0.0008480049,0.00065483357,0.0012236823,0.00074104714],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002346171,0.0048677856,0.24337147,0.00057862845,0.03880424,0.001063153,0.15797274,0.0042575095,0.0034027894,0.007171271,0.3677955,0.16836873],"study_design_scores_gemma":[0.01514826,0.0046323445,0.36547738,0.0007835436,0.0130801555,0.00010524596,0.10028251,0.24160273,0.014855559,0.031795464,0.2043531,0.00788369],"about_ca_topic_score_codex":0.0003493142,"about_ca_topic_score_gemma":0.00055648223,"teacher_disagreement_score":0.6653277,"about_ca_system_score_codex":0.00024759912,"about_ca_system_score_gemma":0.0005755675,"threshold_uncertainty_score":0.9995668},"labels":[],"label_agreement":null},{"id":"W2151101070","doi":"10.2139/ssrn.789464","title":"Evaluating Search and Matching Models Using Experimental Data","year":2005,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Matching (statistics); Computer science; Data mining; Econometrics; Mathematics; Statistics","score_opus":0.46222288934752004,"score_gpt":0.568678542894699,"score_spread":0.10645565354717895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151101070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5981959,0.005807769,0.39538237,0.00034295314,0.00006132484,0.000110147506,0.000004855858,0.000013475732,0.00008119431],"genre_scores_gemma":[0.97233254,0.0004642173,0.02591193,0.000039699953,0.00055537024,0.0000014227347,0.0000020359937,0.000026455968,0.0006663375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933005,0.0004252487,0.00057420455,0.000613686,0.0026961956,0.0023901907],"domain_scores_gemma":[0.9983032,0.00044236056,0.00013799832,0.00069184863,0.0002380688,0.00018652665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019775553,0.00016307476,0.00024159928,0.00032605152,0.00074027956,0.0005673616,0.0015957305,0.00005883931,0.000111622285],"category_scores_gemma":[0.0005339304,0.00012655271,0.00005047947,0.0004112826,0.00011612902,0.0027951954,0.0009705554,0.0019757708,0.000038183658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010719117,0.00009705544,0.00012615867,0.0000017115187,0.00007273788,0.000009872461,0.0014455644,0.37853214,0.0120083755,0.005768253,0.000034736375,0.6017962],"study_design_scores_gemma":[0.0005444018,0.00012805514,0.000012913771,0.000010096296,0.0000055709256,0.00087768247,0.007603406,0.7982106,0.0005902865,0.19180942,0.00007721471,0.00013033979],"about_ca_topic_score_codex":0.000079924226,"about_ca_topic_score_gemma":0.00018780593,"teacher_disagreement_score":0.60166585,"about_ca_system_score_codex":0.0010238659,"about_ca_system_score_gemma":0.0020494815,"threshold_uncertainty_score":0.8583851},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09547229580583252,"score_gpt":0.270794819568804,"score_spread":0.1753225237629715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154806059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6124066,0.000009288739,0.38672334,0.000182465,0.000027839264,0.0003930951,0.000024051174,0.00005392599,0.00017937522],"genre_scores_gemma":[0.9958372,0.000042007137,0.0030857837,0.000016635182,0.00003346277,0.0000037023306,0.00004005854,0.00001197623,0.00092918007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9975822,0.00027163632,0.00034640182,0.00088700093,0.000477142,0.0004356508],"domain_scores_gemma":[0.996471,0.0016620521,0.00015012117,0.0004968787,0.0010241026,0.00019583853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083620654,0.00018809774,0.00027746407,0.0003812722,0.00027107587,0.00013843531,0.0006841978,0.00011033967,0.00052558567],"category_scores_gemma":[0.0032065522,0.00015163266,0.000068266985,0.0035130018,0.00027675217,0.0016173493,0.00013861628,0.00042136686,0.0002107991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009215675,0.0011625497,0.08742838,0.0000498238,0.00003467846,0.00024004553,0.00068423105,0.86926025,0.00015392023,0.0009159154,0.0002712579,0.03887735],"study_design_scores_gemma":[0.004910219,0.0007634845,0.42269486,0.00022643179,0.000038669317,0.000021883687,0.0043591075,0.37059778,0.0003259136,0.19335216,0.0018582136,0.00085126027],"about_ca_topic_score_codex":0.00024831225,"about_ca_topic_score_gemma":0.0020244874,"teacher_disagreement_score":0.49866247,"about_ca_system_score_codex":0.00027893938,"about_ca_system_score_gemma":0.00034784817,"threshold_uncertainty_score":0.61834},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.20504333039520903,"score_gpt":0.5069362652545172,"score_spread":0.3018929348593081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156211713","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39983994,0.0013592005,0.56882113,0.0042500445,0.000069617294,0.0028871833,0.000091409005,0.00014660883,0.022534907],"genre_scores_gemma":[0.6772392,0.000274021,0.31753558,0.000035982248,0.00008609535,0.00011422591,0.000010296217,0.00003215648,0.0046724402],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99100554,0.00022575687,0.0010193563,0.0006615821,0.006440941,0.000646831],"domain_scores_gemma":[0.9822537,0.0069871503,0.00010329334,0.0012831091,0.009140673,0.00023212559],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0059818355,0.00021597452,0.00048393296,0.0012780024,0.00064926594,0.0007381237,0.0018506332,0.000109067754,0.00055127096],"category_scores_gemma":[0.0491695,0.00013460571,0.00005413499,0.006631904,0.0005196418,0.0011686882,0.00023314565,0.00053180766,0.0002831775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034922343,0.022072518,0.0031882317,0.0066884025,0.0004561912,0.00075075706,0.050968993,0.15153147,0.018739646,0.043355048,0.07353304,0.62522346],"study_design_scores_gemma":[0.003538978,0.005989485,0.003038308,0.0026778544,0.00003969661,0.0003287962,0.018441506,0.066169694,0.114331685,0.77573085,0.008209879,0.0015032559],"about_ca_topic_score_codex":0.000012570188,"about_ca_topic_score_gemma":0.00030748616,"teacher_disagreement_score":0.7323758,"about_ca_system_score_codex":0.00007448259,"about_ca_system_score_gemma":0.0022123354,"threshold_uncertainty_score":0.9588398},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08846169459235069,"score_gpt":0.44501094081824716,"score_spread":0.35654924622589645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157016390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44668514,0.0001413653,0.5336622,0.0033570162,0.0015771198,0.00048460285,0.00006962427,0.00021718409,0.013805722],"genre_scores_gemma":[0.8373506,0.00006453094,0.11108688,0.00060003944,0.00067937805,0.000019127088,0.000019672512,0.000044432498,0.0501353],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949963,0.00006221714,0.0006355422,0.0007894279,0.0029888474,0.00052763784],"domain_scores_gemma":[0.99258053,0.0045540915,0.00013355092,0.0010664838,0.0013474808,0.00031784986],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017682005,0.00020692614,0.00030319844,0.00042950778,0.000248245,0.00045321582,0.0015475446,0.00016249983,0.015497131],"category_scores_gemma":[0.013003751,0.00012697144,0.00008957407,0.0019608827,0.00026327572,0.0008039876,0.00042420268,0.00057723816,0.0030178484],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002176756,0.00074387004,0.0043475903,0.00001412027,0.000022681252,0.000045565987,0.00013295488,0.00089898973,0.0034585088,0.0007470953,0.082586795,0.9067842],"study_design_scores_gemma":[0.0025355318,0.00030362542,0.09904185,0.00004023132,0.000012283214,0.00013891784,0.0019605833,0.0124857295,0.01350072,0.45385987,0.41515058,0.0009700626],"about_ca_topic_score_codex":0.0000224762,"about_ca_topic_score_gemma":0.001808446,"teacher_disagreement_score":0.9058141,"about_ca_system_score_codex":0.000030555242,"about_ca_system_score_gemma":0.00031812253,"threshold_uncertainty_score":0.9977584},"labels":[],"label_agreement":null},{"id":"W2157140780","doi":"10.1007/978-3-642-16108-7_20","title":"Toward a Classification of Finite Partial-Monitoring Games","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.1545661084896942,"score_gpt":0.40540969760175927,"score_spread":0.25084358911206506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157140780","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005421245,0.00024898857,0.99480367,0.00041034308,0.0022716394,0.0003114641,0.00001373386,0.000038445596,0.0013596204],"genre_scores_gemma":[0.80931336,0.0000661634,0.18838365,0.00006363268,0.0011715894,0.0000145869835,0.0000033423025,0.00003900038,0.0009446908],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9931211,0.00006224167,0.0009969694,0.0014512436,0.0037980163,0.0005704429],"domain_scores_gemma":[0.9924676,0.0040491754,0.00062980293,0.0016000025,0.0010665277,0.00018689124],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033167645,0.00035662696,0.00063329906,0.0014689156,0.00018525252,0.00039707733,0.0032297454,0.000412925,0.00015523465],"category_scores_gemma":[0.0039631557,0.00027688956,0.00016209099,0.0010726949,0.0018577623,0.00050689495,0.00087351387,0.0013118222,0.00012412414],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016252397,0.000021105012,0.00048889604,0.00001422825,0.0000053690505,0.000024218663,0.00068531936,0.017102905,0.0030754253,0.00065977883,0.000005377852,0.9779011],"study_design_scores_gemma":[0.00048290406,0.00030990303,0.0042009614,0.00047912504,0.000012355923,0.000032264412,0.000004362826,0.31935608,0.076916136,0.582903,0.014384787,0.0009181224],"about_ca_topic_score_codex":0.000012852336,"about_ca_topic_score_gemma":0.000027064096,"teacher_disagreement_score":0.976983,"about_ca_system_score_codex":0.00015635249,"about_ca_system_score_gemma":0.00061131205,"threshold_uncertainty_score":0.99996835},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1076079387823779,"score_gpt":0.4263062865630172,"score_spread":0.3186983477806393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160163723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8072849,0.00059091515,0.17741,0.0023835842,0.005350001,0.0018799794,0.00007737861,0.00045915664,0.00456406],"genre_scores_gemma":[0.9973146,0.000003452257,0.00081327837,0.00025414937,0.00043708752,0.000080941296,0.0000120316545,0.000010799661,0.0010736751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960746,0.0001934967,0.0011396946,0.00023150694,0.0019723459,0.00038834594],"domain_scores_gemma":[0.99640954,0.0008644827,0.00063248264,0.00064805825,0.0012917251,0.0001537166],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032462366,0.00017799386,0.0002566251,0.0005631961,0.00087331055,0.002153674,0.0008540953,0.00013043333,0.00009173872],"category_scores_gemma":[0.0050692973,0.00009459903,0.000079629055,0.0024722668,0.00018258365,0.004402479,0.00012262371,0.0006314017,0.00064460706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010568977,0.00006157581,0.0013115251,0.00016405374,0.000024784556,0.00020972577,0.0036867196,0.1124968,0.00047328157,0.0013132701,0.020449605,0.85970294],"study_design_scores_gemma":[0.00042297255,0.00003182846,0.00018487567,0.000009490534,0.0000045536276,0.002480609,0.0017245892,0.86868393,0.00024407335,0.00028958853,0.12576775,0.00015571575],"about_ca_topic_score_codex":0.000113412374,"about_ca_topic_score_gemma":0.000020642827,"teacher_disagreement_score":0.85954726,"about_ca_system_score_codex":0.000035614124,"about_ca_system_score_gemma":0.00013552631,"threshold_uncertainty_score":0.9988822},"labels":[],"label_agreement":null},{"id":"W2160262323","doi":"10.48550/arxiv.1306.0686","title":"Online Learning under Delayed Feedback","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Online learning; Computer science; Multiplicative function; Feedback loop; Adversarial system; Black box; Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Multimedia; World Wide Web","score_opus":0.2569419831242067,"score_gpt":0.3170267194651759,"score_spread":0.060084736340969225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160262323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61013913,0.00010295326,0.38624611,0.00022397099,0.00054949103,0.00040471076,0.000060522867,0.00018349354,0.002089592],"genre_scores_gemma":[0.9263175,0.0002506448,0.0011834564,0.00008164066,0.00022377136,0.0000012884996,0.000076357865,0.000049251335,0.071816094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99524677,0.0006225114,0.0005621913,0.0019983759,0.00080704974,0.00076307467],"domain_scores_gemma":[0.99468076,0.0014159088,0.00055465644,0.0017349207,0.0011747585,0.00043900203],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011610367,0.00046831666,0.0006747337,0.00085151824,0.00036290693,0.00040250772,0.0030258296,0.0005488508,0.002779069],"category_scores_gemma":[0.0013185887,0.00043959825,0.0003945129,0.0015890818,0.0004126684,0.00059990736,0.0038122847,0.0023145883,0.004572197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077204895,0.00014320167,0.0014231015,0.00001013381,0.00009833108,0.00018622164,0.00009993387,0.9889729,0.000021581563,0.0024170605,0.002110294,0.004440012],"study_design_scores_gemma":[0.000825723,0.00011805769,0.008844144,0.000052160183,0.00005066118,0.0000074618483,0.0020667647,0.70346534,0.000050163242,0.2756966,0.008094645,0.0007282364],"about_ca_topic_score_codex":0.00035761463,"about_ca_topic_score_gemma":0.00016976535,"teacher_disagreement_score":0.38506266,"about_ca_system_score_codex":0.00042977693,"about_ca_system_score_gemma":0.0003152406,"threshold_uncertainty_score":0.9999871},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12027882754212588,"score_gpt":0.45583294118547746,"score_spread":0.3355541136433516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160367301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019690652,0.000024519573,0.9907419,0.0022252572,0.00016224173,0.0007330949,0.0000125499255,0.00009061967,0.0058129127],"genre_scores_gemma":[0.24467424,0.000022792156,0.7464706,0.0011372741,0.000059055477,0.00006035661,0.000011806472,0.000009143057,0.007554787],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99730587,0.0001315146,0.000571568,0.0002769757,0.0012951348,0.00041894097],"domain_scores_gemma":[0.9948184,0.0037445612,0.00015833903,0.0005905642,0.00054996053,0.00013819287],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030917116,0.00013594516,0.00021613271,0.00038022338,0.00020595366,0.00043055406,0.0007705916,0.00014161115,0.0010239341],"category_scores_gemma":[0.008901502,0.00009541857,0.00009196555,0.0009170771,0.000056462028,0.0014907151,0.00005687082,0.00019503846,0.0005228415],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047546127,0.000061332175,0.000031708983,0.00000459771,0.000011429334,0.0000026309997,0.00031418225,0.0044592195,0.000039119008,0.0265171,0.05252013,0.9155631],"study_design_scores_gemma":[0.00036864533,0.00020406044,0.0030565055,0.000007062315,0.0000023399275,0.0000029175494,0.0003418816,0.2995306,0.00018945923,0.6731281,0.023036765,0.00013162591],"about_ca_topic_score_codex":0.0000024033736,"about_ca_topic_score_gemma":0.0000034863517,"teacher_disagreement_score":0.91543144,"about_ca_system_score_codex":0.00008518975,"about_ca_system_score_gemma":0.00010677921,"threshold_uncertainty_score":0.99988925},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.2241001579878948,"score_gpt":0.4240967083286237,"score_spread":0.19999655034072888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161571887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031024497,0.00013618224,0.90885067,0.01689352,0.00011859172,0.000804631,0.000029945428,0.0002514943,0.041890454],"genre_scores_gemma":[0.8358264,0.00002081209,0.097340815,0.0014173898,0.00015817341,0.00005241043,0.000037074937,0.000019469699,0.065127455],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965981,0.00007527931,0.00042713757,0.00047980543,0.0020667007,0.0003529737],"domain_scores_gemma":[0.99750566,0.00093989406,0.00010905305,0.00056547945,0.00071591657,0.00016398722],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00084029726,0.0001335948,0.00018667306,0.00027630397,0.00026113854,0.00023197729,0.0006008209,0.00004592991,0.0010317056],"category_scores_gemma":[0.0010107287,0.00008077458,0.00004711118,0.001565949,0.00010614984,0.0010198752,0.000046703477,0.00016684776,0.00062436017],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000275236,0.00095400284,0.023741739,0.000010700146,0.00007208037,0.00019509783,0.0019966776,0.22936933,0.0040327306,0.03078133,0.12949513,0.57907593],"study_design_scores_gemma":[0.0013933984,0.0008832873,0.42015943,0.000026529537,0.000008782567,0.000047853013,0.0010227216,0.042174913,0.0011571471,0.41954008,0.11308463,0.0005012463],"about_ca_topic_score_codex":0.000015306077,"about_ca_topic_score_gemma":0.00008520506,"teacher_disagreement_score":0.81150985,"about_ca_system_score_codex":0.00005142995,"about_ca_system_score_gemma":0.00015733599,"threshold_uncertainty_score":0.9998815},"labels":[],"label_agreement":null},{"id":"W2161790782","doi":"10.1145/1553374.1553500","title":"A simpler unified analysis of budget perceptrons","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perceptron; Computer science; Regret; Mathematical proof; Regularization (linguistics); Algorithm; Set (abstract data type); Mathematical optimization; Artificial intelligence; Machine learning; Artificial neural network; Mathematics","score_opus":0.13430457853375094,"score_gpt":0.4873831615531908,"score_spread":0.35307858301943984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161790782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3309022,0.00005833373,0.6146734,0.0029265664,0.00007422112,0.00024789845,0.000054505574,0.00008108461,0.050981853],"genre_scores_gemma":[0.9819496,0.0000068725067,0.005604958,0.00019107548,0.000020587386,0.0000015587337,0.0000062524146,0.0000033459805,0.0122157475],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9970044,0.00011819364,0.0005126979,0.00037742895,0.0017000274,0.00028728877],"domain_scores_gemma":[0.9975969,0.0008955306,0.000105210645,0.0007841488,0.00049024663,0.00012794207],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001285614,0.00009376489,0.00040655083,0.0012165717,0.00007051712,0.00006842587,0.00073602534,0.000050597402,0.009032915],"category_scores_gemma":[0.0015647967,0.000060470924,0.00025277742,0.0053880652,0.000105139356,0.00022952021,0.00007700755,0.000107089945,0.00023215359],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024008325,0.0008078318,0.025222782,0.000002774574,0.0011058333,0.000044456734,0.0029050733,0.08370818,0.013354582,0.014722715,0.056397997,0.8014877],"study_design_scores_gemma":[0.000595355,0.00033500517,0.77320266,0.0000021000699,0.00020429767,0.000002305641,0.0027574408,0.1472187,0.0023663167,0.052107025,0.020905236,0.00030355778],"about_ca_topic_score_codex":0.00004025306,"about_ca_topic_score_gemma":0.00013005195,"teacher_disagreement_score":0.8011841,"about_ca_system_score_codex":0.000028757231,"about_ca_system_score_gemma":0.00005294759,"threshold_uncertainty_score":0.99187297},"labels":[],"label_agreement":null},{"id":"W2168337246","doi":"10.1109/cdc.2007.4434388","title":"Decentralized adaptation in sensor networks: Analysis and application of regret-based algorithms","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Wireless sensor network; Computer science; Overhead (engineering); Class (philosophy); Correlated equilibrium; Matching (statistics); Set (abstract data type); Distributed computing; Scheme (mathematics); Adaptation (eye); Game theory; Algorithm; Real-time computing; Computer network; Repeated game; Artificial intelligence; Mathematics; Machine learning; Equilibrium selection","score_opus":0.06504570463724091,"score_gpt":0.4214379622264054,"score_spread":0.3563922575891645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168337246","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033602502,0.00012698382,0.9656966,0.00012867151,0.000022934664,0.0002694956,0.0000040308228,0.000019133673,0.00012965048],"genre_scores_gemma":[0.85505176,0.000028585999,0.14468387,0.000035373447,0.000018366365,0.000009164261,0.000014271003,0.000006258274,0.00015238888],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726015,0.00013711174,0.0007455631,0.00044119867,0.0011122599,0.00030373645],"domain_scores_gemma":[0.99683934,0.0020034863,0.00022938129,0.0004144519,0.00039818822,0.000115158524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040933024,0.000102558835,0.00032783078,0.0011438295,0.000048755537,0.000046032736,0.0002471423,0.00008557393,0.000101071244],"category_scores_gemma":[0.0009395344,0.00007735581,0.000080919366,0.005121491,0.00013834839,0.00018783919,0.000039419443,0.00011073734,0.000008355607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015918791,0.000071709495,0.07343332,0.000002588505,0.00003520209,0.000006025434,0.00013687534,0.35995385,0.00029291192,0.00011372734,0.000028570576,0.56576604],"study_design_scores_gemma":[0.0005583584,0.000026324313,0.1548706,0.0000023801358,0.000017973385,5.559748e-7,0.0005725397,0.8412466,0.0016494271,0.0007552334,0.00022422633,0.00007580726],"about_ca_topic_score_codex":0.00041965538,"about_ca_topic_score_gemma":0.0021298684,"teacher_disagreement_score":0.8214492,"about_ca_system_score_codex":0.000057179837,"about_ca_system_score_gemma":0.00003474116,"threshold_uncertainty_score":0.31544787},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.100663809997761,"score_gpt":0.4084052332996377,"score_spread":0.3077414233018767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170307371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043891757,0.0000020236896,0.99346817,0.0007588559,0.0000719133,0.0002859669,0.00008504647,0.000023220864,0.00091564725],"genre_scores_gemma":[0.92349505,0.000010258358,0.076064885,0.00019335811,0.000021249994,0.000033258075,0.00006847082,0.000010215233,0.00010322788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977874,0.00015948899,0.00048304832,0.00047079148,0.0009197857,0.00017944683],"domain_scores_gemma":[0.99717706,0.0018686106,0.00016816777,0.00016380541,0.0005014008,0.00012094323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010276891,0.00015270595,0.00018720885,0.000474108,0.00012923041,0.00029270176,0.00023320837,0.00005968089,0.00025147529],"category_scores_gemma":[0.0035452023,0.00012468472,0.000011502423,0.0002898249,0.00022618358,0.00015000036,0.000038839084,0.0002407994,0.00007836451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012849986,0.00003647511,0.00027560288,0.000002016048,0.0000023077935,0.0000017264441,0.00012891678,0.6343229,0.000031540294,0.13092735,0.000007707282,0.23413499],"study_design_scores_gemma":[0.000093291485,0.00035114243,0.00029891953,0.000044829314,0.0000024347353,0.0000022253053,0.00015951911,0.8606589,0.00017014281,0.13807252,0.000022293629,0.00012379888],"about_ca_topic_score_codex":0.000026896105,"about_ca_topic_score_gemma":0.0002606476,"teacher_disagreement_score":0.9191059,"about_ca_system_score_codex":0.000063124644,"about_ca_system_score_gemma":0.00007198884,"threshold_uncertainty_score":0.50844955},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.28759561229267017,"score_gpt":0.45380007657920457,"score_spread":0.1662044642865344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187589363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8475081,0.00004127652,0.058643375,0.03363112,0.0020138086,0.0014647926,0.00010788956,0.00026816328,0.056321535],"genre_scores_gemma":[0.99608505,0.000009334422,0.0010257097,0.00030759635,0.00048025383,0.000017191636,0.0000010907027,0.00002185704,0.002051914],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994979,0.00007568267,0.0010556437,0.0007613453,0.0025647648,0.0005635642],"domain_scores_gemma":[0.99508756,0.0011505462,0.000679301,0.0004250294,0.0025046994,0.00015288577],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024147257,0.00027181456,0.00046494033,0.0003088675,0.00047599536,0.00038926443,0.0034093063,0.00014905457,0.00063614483],"category_scores_gemma":[0.014648248,0.00017595282,0.00022835011,0.001674155,0.0008326069,0.0004484412,0.0005901471,0.00061029324,0.0005894009],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001613487,0.00048773852,0.00080767676,0.000021178354,0.000020600477,3.6994376e-7,0.0010882328,0.00018281526,0.024741014,0.33311394,0.0026101638,0.63676494],"study_design_scores_gemma":[0.00007173569,0.00031116707,0.0041031353,0.00007921059,0.000013382071,0.0000032420103,0.0017749639,0.06441732,0.22131239,0.70002455,0.0075237993,0.00036512245],"about_ca_topic_score_codex":0.000043295495,"about_ca_topic_score_gemma":0.00005230113,"teacher_disagreement_score":0.6363998,"about_ca_system_score_codex":0.00006259482,"about_ca_system_score_gemma":0.000104998595,"threshold_uncertainty_score":0.9936518},"labels":[],"label_agreement":null},{"id":"W2189148180","doi":"","title":"Linear multi-resource allocation with semi-bandit feedback","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Task (project management); Resource allocation; Mathematical optimization; Resource (disambiguation); Hypercube; Noise (video); Resource management (computing); Distributed computing; Artificial intelligence; Machine learning; Mathematics; Engineering","score_opus":0.17021817587683175,"score_gpt":0.40578447418840363,"score_spread":0.2355662983115719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189148180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04096811,0.00041175925,0.95179576,0.0011099327,0.0006362041,0.0010650929,0.000025449577,0.00040093262,0.0035867773],"genre_scores_gemma":[0.99349004,0.0000015084615,0.002313033,0.00021103711,0.00024473894,0.000070481525,0.0000656481,0.00001927239,0.003584246],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953234,0.00017044724,0.001005572,0.00029112477,0.0028163027,0.00039314356],"domain_scores_gemma":[0.99614567,0.00019666008,0.0007017625,0.00045720127,0.0022000573,0.0002986827],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021853023,0.00021394891,0.00029968968,0.00043965122,0.00029988354,0.0013549048,0.00066747394,0.000116742,0.000014241222],"category_scores_gemma":[0.0015534671,0.00013933118,0.000039860734,0.0013695594,0.0001342409,0.006230984,0.00009077727,0.0002826301,0.0008768938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002788395,0.00006842649,0.0020796428,0.00016706389,0.000016861602,0.000008047308,0.0078392895,0.8140733,0.00007270838,0.000058778776,0.015718965,0.15961808],"study_design_scores_gemma":[0.0012229267,0.00013654545,0.0004004706,0.00007905158,0.0000048002867,0.00009383946,0.00620962,0.89291954,0.0003060694,0.000043600925,0.098364264,0.00021926982],"about_ca_topic_score_codex":0.00004818053,"about_ca_topic_score_gemma":0.0000085163165,"teacher_disagreement_score":0.9525219,"about_ca_system_score_codex":0.00016892393,"about_ca_system_score_gemma":0.00029430495,"threshold_uncertainty_score":0.99990106},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2723421006942705,"score_gpt":0.49421710476191894,"score_spread":0.22187500406764843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2192203593","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037706789,0.99206936,0.0008349728,0.00036180142,0.0005098327,0.0020711517,0.000039197253,0.000010691662,0.004099198],"genre_scores_gemma":[0.00009756815,0.9967065,0.00089701125,0.000048111935,0.00018075727,0.0000730531,0.0000012225464,0.00004568539,0.0019500982],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99329114,0.00018553817,0.0020024949,0.0004917643,0.0037176523,0.00031143302],"domain_scores_gemma":[0.9892479,0.00068917125,0.005971641,0.0009777179,0.0030461685,0.00006741074],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.008354706,0.0003408393,0.001900953,0.00021124366,0.00022480024,0.00008071012,0.0064576576,0.00017976845,0.00014353555],"category_scores_gemma":[0.010350506,0.00012887454,0.0009367475,0.0023801953,0.00067975424,0.00027067546,0.0009587722,0.0006325917,0.000009534857],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070405695,0.00008676783,0.000029274486,0.056959007,0.00015414893,2.4274144e-7,0.00049116625,0.00027272635,0.000024678202,0.00037440786,0.021565922,0.92003465],"study_design_scores_gemma":[0.00026220066,0.000098285695,0.000011720806,0.18420742,0.0008498965,0.000026718642,0.00027745974,0.00086270383,0.00044080068,0.00602986,0.8065073,0.0004256644],"about_ca_topic_score_codex":0.000012547131,"about_ca_topic_score_gemma":0.000002526982,"teacher_disagreement_score":0.91960895,"about_ca_system_score_codex":0.00011736818,"about_ca_system_score_gemma":0.00039614493,"threshold_uncertainty_score":0.9989179},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.15649261927558675,"score_gpt":0.4209362025593321,"score_spread":0.2644435832837454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2193897973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04498994,0.00006580862,0.94707143,0.0059762425,0.00012094248,0.0009140387,0.00009021087,0.00013803218,0.0006333281],"genre_scores_gemma":[0.9354277,0.00013822268,0.059183076,0.00018171266,0.000058828504,0.00059966446,0.0000078664,0.00003740556,0.004365517],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969379,0.0003771835,0.00058008276,0.00062007445,0.0010266737,0.00045812447],"domain_scores_gemma":[0.9903153,0.002988117,0.00023149243,0.0051903427,0.00094007986,0.0003346775],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012097212,0.00020332138,0.00030404376,0.00038940436,0.0005198455,0.000157033,0.0044569992,0.000093332696,0.000073564916],"category_scores_gemma":[0.0004649297,0.00012129349,0.00007138021,0.0014777964,0.00044551335,0.0003462296,0.00041549763,0.00023303533,0.002871509],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012325757,0.0007229606,0.0029370452,0.000006681001,0.000055476517,0.0000047562326,0.0012553378,0.0022486707,0.37314904,0.00094170694,0.0037829408,0.61477214],"study_design_scores_gemma":[0.0073532574,0.00066615053,0.051391605,0.00039371668,0.00006349689,0.00004545006,0.0021271615,0.08326544,0.3826169,0.0072275787,0.4624815,0.0023677319],"about_ca_topic_score_codex":0.00006174629,"about_ca_topic_score_gemma":0.0015169984,"teacher_disagreement_score":0.8904378,"about_ca_system_score_codex":0.00015798997,"about_ca_system_score_gemma":0.00015302595,"threshold_uncertainty_score":0.9979049},"labels":[],"label_agreement":null},{"id":"W2203325308","doi":"10.48550/arxiv.1206.6487","title":"An Adaptive Algorithm for Finite Stochastic Partial Monitoring","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Algorithm","score_opus":0.3480788863386984,"score_gpt":0.3467574326496035,"score_spread":0.0013214536890948647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2203325308","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019455101,0.00011653305,0.9768123,0.000017702416,0.0020562292,0.0009083312,0.00038220087,0.00013830954,0.000113264694],"genre_scores_gemma":[0.9807831,0.000026040792,0.015427055,0.000009479837,0.001530697,0.000015665335,0.000036681682,0.000058894035,0.0021123819],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99549073,0.00040553306,0.0005129108,0.001868314,0.0007044455,0.0010180655],"domain_scores_gemma":[0.99323237,0.0026963917,0.0005040104,0.0017894084,0.0011166616,0.00066118216],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019918897,0.00049028185,0.00068054517,0.0006969271,0.00044557443,0.00028454742,0.0025647753,0.0004810647,0.000181032],"category_scores_gemma":[0.0010230631,0.0004914725,0.00040004536,0.0009149052,0.00033150747,0.0010399616,0.0013879053,0.0009778619,0.000358225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022469099,0.00017164488,0.0003755909,0.000007446648,0.00008777407,0.000068029694,0.0002880601,0.94561374,0.000015802509,0.0009706288,0.00008246704,0.0520941],"study_design_scores_gemma":[0.0007216429,0.00021613919,0.00048390933,0.00004451857,0.00008170418,0.0000020925308,0.0009065852,0.93702316,0.00024115505,0.059261892,0.00046558995,0.0005516367],"about_ca_topic_score_codex":0.00007190365,"about_ca_topic_score_gemma":0.000012205785,"teacher_disagreement_score":0.96138525,"about_ca_system_score_codex":0.000402834,"about_ca_system_score_gemma":0.00034024863,"threshold_uncertainty_score":0.9997537},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.14211577694936595,"score_gpt":0.45600520281474183,"score_spread":0.3138894258653759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206616202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08970872,0.000046959973,0.9067177,0.0020829053,0.00021268394,0.00061947893,0.000061615174,0.000045926365,0.0005039787],"genre_scores_gemma":[0.9849985,0.0000039625243,0.009343336,0.0007402891,0.00021908108,0.00005449564,0.000008993724,0.000011630442,0.004619703],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974337,0.000069003705,0.00033428875,0.00046676863,0.0012072093,0.0004889795],"domain_scores_gemma":[0.9969792,0.0012409366,0.000058992726,0.00057931355,0.00031500438,0.0008265782],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011894122,0.00013160465,0.00020642353,0.000406285,0.00018849676,0.00010840042,0.00051941164,0.00005941687,0.0008498661],"category_scores_gemma":[0.0027589777,0.0000960667,0.00003312982,0.0010135262,0.000090853064,0.0004671031,0.0003694078,0.00013346816,0.005033597],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058030017,0.0014289687,0.021958172,0.000027577811,0.00009145971,0.000018131674,0.0156629,0.04713886,0.013853387,0.022326183,0.27562818,0.6012859],"study_design_scores_gemma":[0.0032776513,0.0010740567,0.30694494,0.000096846416,0.000062067804,0.0001449549,0.023343762,0.16513398,0.0077648545,0.04312858,0.44664,0.0023883013],"about_ca_topic_score_codex":0.00006163566,"about_ca_topic_score_gemma":0.000076998025,"teacher_disagreement_score":0.8973744,"about_ca_system_score_codex":0.000051959054,"about_ca_system_score_gemma":0.000048377467,"threshold_uncertainty_score":0.9957411},"labels":[],"label_agreement":null},{"id":"W2222041227","doi":"10.6084/m9.figshare.1448973.v1","title":"Human behavior in contextual multi-armed bandit problems - Poster presented at Reinforcement learning and decision making conference in 2015","year":2015,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Reinforcement; Artificial intelligence; Computer science; Machine learning; Psychology; Social psychology","score_opus":0.33005442763166004,"score_gpt":0.4855699151820237,"score_spread":0.15551548755036365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2222041227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96642166,0.002221035,0.0030816935,0.0003689367,0.00038727184,0.008601933,0.015570919,0.00026723673,0.00307934],"genre_scores_gemma":[0.9944631,0.0000025811507,0.00032567355,0.00002444333,0.000028725985,0.0003679875,0.0022354717,0.000022139688,0.0025299105],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9960949,0.00021930493,0.0007776039,0.00069733115,0.0016641957,0.0005466695],"domain_scores_gemma":[0.99775213,0.0008093429,0.00024822901,0.0003639141,0.0005929331,0.00023343661],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009982992,0.00022037285,0.0003636404,0.000599192,0.0001381957,0.00031505738,0.0005735887,0.00014881768,0.026257843],"category_scores_gemma":[0.009154683,0.00017997297,0.00003804838,0.0005809106,0.00004877152,0.00065738714,0.0011509802,0.0004908728,0.000924679],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018327656,0.0011611128,0.32509282,0.0002791162,0.00004928613,0.0025077886,0.02174427,0.09383928,0.0033900621,0.000019505298,0.2811516,0.2689324],"study_design_scores_gemma":[0.025159901,0.0022230174,0.5670281,0.008593146,0.000017559969,0.00015096109,0.0066596,0.30054885,0.0012639881,0.0016340042,0.08460059,0.0021202585],"about_ca_topic_score_codex":0.000050526225,"about_ca_topic_score_gemma":0.0016285809,"teacher_disagreement_score":0.26681215,"about_ca_system_score_codex":0.00030802444,"about_ca_system_score_gemma":0.000110588924,"threshold_uncertainty_score":0.9998532},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06434972756859121,"score_gpt":0.36376769200267167,"score_spread":0.2994179644340805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2241126168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015823407,0.00018664684,0.97427857,0.0018863395,0.00035477168,0.0012263826,0.00001557226,0.00011491756,0.00611339],"genre_scores_gemma":[0.9885115,0.0000042546967,0.0058460603,0.000043817938,0.00036206012,0.00013050358,0.000004008111,0.000017123182,0.0050806524],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99622756,0.0002128997,0.00041167517,0.00035410965,0.0021100033,0.0006837569],"domain_scores_gemma":[0.9963703,0.0023169422,0.00008663452,0.00055434974,0.00046500584,0.00020672265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029775768,0.00016551648,0.00019211357,0.00009832467,0.00054342713,0.00028768744,0.00056528,0.00005820289,0.00035306512],"category_scores_gemma":[0.0008517132,0.00007330171,0.00006645839,0.00064514193,0.0004844212,0.0010098412,0.00007513092,0.00022950495,0.000243046],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036592125,0.0019467504,0.003979241,0.000044938086,0.00030318633,0.000030004707,0.03589255,0.21812256,0.0006472697,0.1430362,0.022973275,0.5693648],"study_design_scores_gemma":[0.009003382,0.004892909,0.017799541,0.0002132172,0.0001717683,0.0004210011,0.06305399,0.18861626,0.0022029819,0.49326098,0.21722558,0.0031383904],"about_ca_topic_score_codex":0.000029071141,"about_ca_topic_score_gemma":0.00017444888,"teacher_disagreement_score":0.97268814,"about_ca_system_score_codex":0.00008333088,"about_ca_system_score_gemma":0.00015267188,"threshold_uncertainty_score":0.4179657},"labels":[],"label_agreement":null},{"id":"W2266817871","doi":"","title":"An expectation-maximization algorithm to compute a stochastic factorization from data","year":2015,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Stochastic matrix; Markov chain; Factorization; Algorithm; Matrix (chemical analysis); Computer science; Matrix decomposition; Matrix multiplication; Probabilistic logic; Mathematical optimization; Markov decision process; Markov process; Mathematics; Artificial intelligence; Machine learning","score_opus":0.6099591275582319,"score_gpt":0.5389729520319333,"score_spread":0.0709861755262986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2266817871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044065444,0.0000060894367,0.98968744,0.0019410605,0.0023017593,0.0003800312,0.0006195767,0.00010783319,0.00054968265],"genre_scores_gemma":[0.9475125,0.0000040085833,0.050281007,0.00024390768,0.0007880368,0.000030602336,0.0009362191,0.000024666948,0.00017904489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99376225,0.0002783758,0.00094492425,0.0012935129,0.0033866675,0.00033424352],"domain_scores_gemma":[0.9939064,0.0008321519,0.00028307026,0.0013963308,0.0030613337,0.0005207506],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001136442,0.0002538388,0.00027804595,0.0006525925,0.00015869412,0.0011473913,0.0038332914,0.00010449083,0.0013217934],"category_scores_gemma":[0.0064566536,0.00023015635,0.000041924683,0.0009842662,0.00012891152,0.0016830021,0.00047968415,0.00026245526,0.0029675874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020276857,0.00026945776,0.00006843404,3.5112726e-7,0.00002409525,0.000014064668,0.0023329153,0.24619266,0.00069298066,0.01552535,0.00063751574,0.7340394],"study_design_scores_gemma":[0.000055943627,0.00019696068,0.00019064154,0.000019996673,0.0000033973001,0.0000016765846,0.0025174352,0.79627603,0.0021130352,0.19794065,0.00046860537,0.00021565573],"about_ca_topic_score_codex":0.00032421798,"about_ca_topic_score_gemma":0.00032440363,"teacher_disagreement_score":0.94310594,"about_ca_system_score_codex":0.00023283002,"about_ca_system_score_gemma":0.00035740717,"threshold_uncertainty_score":0.9998895},"labels":[],"label_agreement":null},{"id":"W2275726605","doi":"10.1007/bfb0009401","title":"On the bandit problem","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in control and information sciences","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science","score_opus":0.04962082229917428,"score_gpt":0.3466692124861482,"score_spread":0.29704839018697393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2275726605","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010226956,0.0011960535,0.30219567,0.03213643,0.00044593096,0.0016315434,0.00012672458,0.00005899993,0.6621064],"genre_scores_gemma":[0.93814963,0.0009156427,0.0026735982,0.025372284,0.00097513985,0.0001486574,0.00002446643,0.0000363323,0.031704225],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956191,0.00007886623,0.0008802414,0.00039397657,0.0026594626,0.00036834634],"domain_scores_gemma":[0.9910065,0.0077026607,0.0004883094,0.00039972027,0.00031723338,0.00008558227],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0043934644,0.00028669153,0.0003985567,0.00084465975,0.00050591235,0.000982803,0.0010887389,0.00024651387,0.0012007551],"category_scores_gemma":[0.0043652337,0.00013914536,0.00009719373,0.00038376593,0.0008720442,0.0019760882,0.000119230725,0.00069073535,0.0006023347],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006530992,0.0000067084598,0.00004053409,0.0000064494257,0.000012019794,0.0000019004051,0.00063050014,0.029207984,0.0000022472116,0.12522629,0.001513716,0.84328634],"study_design_scores_gemma":[0.0004899823,0.00018534996,0.00012386833,0.00006386631,0.0000042551624,0.000009204151,0.000022833296,0.03252907,0.000016524718,0.59111613,0.37521225,0.00022667661],"about_ca_topic_score_codex":0.000011209826,"about_ca_topic_score_gemma":0.00009360231,"teacher_disagreement_score":0.9380474,"about_ca_system_score_codex":0.0000692208,"about_ca_system_score_gemma":0.00019059534,"threshold_uncertainty_score":0.9997123},"labels":[],"label_agreement":null},{"id":"W2281341692","doi":"10.48550/arxiv.1602.07905","title":"Thompson Sampling is Asymptotically Optimal in General Environments","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sampling (signal processing); Asymptotically optimal algorithm; Mathematics; Mathematical economics; Applied mathematics; Computer science; Geography; Environmental science; Statistics; Mathematical optimization; Telecommunications","score_opus":0.2727705402762734,"score_gpt":0.3244993651873518,"score_spread":0.051728824911078386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281341692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37656608,0.000038592327,0.6204466,0.00026369438,0.00037152504,0.0003283225,0.00009085971,0.000035124758,0.0018591832],"genre_scores_gemma":[0.9737153,0.00020982808,0.004320559,0.00009397536,0.00021447068,0.0000019646322,0.0000106941325,0.00003887026,0.02139434],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99526995,0.00036991647,0.00058329344,0.002131412,0.00083244336,0.00081297115],"domain_scores_gemma":[0.99660534,0.00095004897,0.0003268051,0.0016415517,0.00013816026,0.00033807784],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015063109,0.0004159776,0.0006173143,0.0008392896,0.0001593792,0.00018909528,0.0025821973,0.00048999,0.0015458456],"category_scores_gemma":[0.0006878506,0.00036004998,0.00029924992,0.0007389629,0.00039053266,0.00047407113,0.0034272592,0.0009958113,0.0014143877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031493208,0.0002725765,0.03277588,0.00001867017,0.000102968326,0.00089751225,0.00033909248,0.9457955,0.0005149752,0.006735114,0.00063125876,0.011601526],"study_design_scores_gemma":[0.002671969,0.00016171056,0.048283264,0.0002338633,0.000050293726,0.000010236202,0.0003654016,0.554428,0.0010229516,0.3772286,0.014001126,0.0015426314],"about_ca_topic_score_codex":0.00003244385,"about_ca_topic_score_gemma":0.000018530958,"teacher_disagreement_score":0.61612606,"about_ca_system_score_codex":0.0006661649,"about_ca_system_score_gemma":0.0002224422,"threshold_uncertainty_score":0.99988514},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5436472135121365,"score_gpt":0.4912489599546517,"score_spread":0.05239825355748484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293140407","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00461645,0.000071393166,0.8376883,0.00014230641,0.0003791153,0.00012020738,0.0000028329678,0.00011087998,0.15686847],"genre_scores_gemma":[0.67246926,0.000020230578,0.26582512,0.00030466056,0.00025661074,0.00002033805,0.0000011476479,0.000026266878,0.061076336],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973026,0.00007737599,0.00037674818,0.000419128,0.0014764441,0.00034770055],"domain_scores_gemma":[0.9983173,0.00047300707,0.00006163311,0.000611359,0.0003731837,0.00016350714],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018634837,0.00009220904,0.00015700904,0.00026065804,0.00012355343,0.00009309182,0.00089583406,0.000048481004,0.012904265],"category_scores_gemma":[0.0018455277,0.000058809295,0.00007492071,0.00078802253,0.000109309156,0.00044851453,0.00022457041,0.00014536495,0.0063291034],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003436072,0.00011742972,0.003846108,0.0000012380152,0.000015751086,0.00010009022,0.0013317355,0.000104513165,0.00024078376,0.004015279,0.011276098,0.9789166],"study_design_scores_gemma":[0.0011296689,0.0003120866,0.032132994,0.000010103396,0.000006975937,0.000081437196,0.0047567403,0.07841907,0.039189756,0.70906204,0.1341474,0.00075174146],"about_ca_topic_score_codex":0.000057040597,"about_ca_topic_score_gemma":0.00001601653,"teacher_disagreement_score":0.97816485,"about_ca_system_score_codex":0.000021140399,"about_ca_system_score_gemma":0.00004163397,"threshold_uncertainty_score":0.9944446},"labels":[],"label_agreement":null},{"id":"W2293196265","doi":"10.5220/0005458706300636","title":"Improving Online Marketing Experiments with Drifting Multi-armed Bandits","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Marketing; Business","score_opus":0.30746654149901387,"score_gpt":0.4815174979023776,"score_spread":0.1740509564033637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293196265","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39425772,0.0002372804,0.60081387,0.00032133912,0.00040976255,0.0005331105,0.000014495123,0.00022119968,0.0031912131],"genre_scores_gemma":[0.72823715,0.0000026521566,0.25744823,0.00012715772,0.00024178416,0.000025676889,0.000009306303,0.00004208566,0.013865974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948722,0.0003485979,0.00059790985,0.0007635695,0.002757939,0.00065979],"domain_scores_gemma":[0.99629784,0.0014443932,0.00024417267,0.0006417276,0.0009082653,0.00046359713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051228646,0.00021815965,0.00031526078,0.00032112535,0.00021930797,0.00035397115,0.000845599,0.000073046955,0.00037245118],"category_scores_gemma":[0.012604106,0.00013413563,0.000053217103,0.0009549408,0.00013892348,0.00078055647,0.0004684363,0.0002850331,0.00024450626],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013023257,0.0010503215,0.077014625,0.000022934244,0.00009417433,0.000395324,0.0040967492,0.006334767,0.012827645,0.00003166516,0.008039403,0.8887901],"study_design_scores_gemma":[0.013244393,0.00076139695,0.033484824,0.00014382185,0.000018727262,0.000121772035,0.053088546,0.8451511,0.034870747,0.00054398016,0.01704566,0.0015250085],"about_ca_topic_score_codex":0.00010944545,"about_ca_topic_score_gemma":0.0001350895,"teacher_disagreement_score":0.887265,"about_ca_system_score_codex":0.00014111507,"about_ca_system_score_gemma":0.00023628131,"threshold_uncertainty_score":0.9957132},"labels":[],"label_agreement":null},{"id":"W2333014926","doi":"10.3982/te992","title":"Expressible inspections","year":2013,"lang":"en","type":"article","venue":"Theoretical Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Computability; Probabilistic logic; Test (biology); Outcome (game theory); Computer science; Realization (probability); Process (computing); Computable analysis; Conditional probability; Mathematical economics; Artificial intelligence; Mathematics; Theoretical computer science; Statistics; Programming language","score_opus":0.06724342768532615,"score_gpt":0.38675485028641815,"score_spread":0.319511422601092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333014926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5806839,0.00004807292,0.13478808,0.0053079743,0.00059581286,0.00050442904,0.000024278861,0.00015429828,0.27789316],"genre_scores_gemma":[0.99202096,0.000026849315,0.004525517,0.00022910586,0.00017202177,0.000049915754,0.0000014869356,0.00001569189,0.0029584274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99850607,0.000088878565,0.00041971964,0.00038307335,0.00025585623,0.00034642764],"domain_scores_gemma":[0.99748456,0.0013690784,0.00006553128,0.00066909654,0.00017809511,0.00023361489],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00081670523,0.000100970174,0.00020119228,0.00016784371,0.00014954225,0.0003686523,0.00073585054,0.0000702329,0.02625412],"category_scores_gemma":[0.001816138,0.00007493456,0.00008241829,0.00024747427,0.00093700545,0.0005305498,0.0002482815,0.000197251,0.016071338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000727096,0.000030683765,0.00013655516,4.0553877e-7,0.0000048801544,7.1177857e-7,0.00006422588,0.0007290695,0.00007787861,0.9741956,0.0029355853,0.021817125],"study_design_scores_gemma":[0.000157222,0.000032369226,0.0012184217,0.0000012883124,0.0000011859416,0.0000055784703,0.00021993305,0.031982224,0.0010140613,0.9558183,0.009449494,0.00009992359],"about_ca_topic_score_codex":0.000009997567,"about_ca_topic_score_gemma":0.0000029361609,"teacher_disagreement_score":0.4113371,"about_ca_system_score_codex":0.000066777175,"about_ca_system_score_gemma":0.00005066044,"threshold_uncertainty_score":0.9846948},"labels":[],"label_agreement":null},{"id":"W2395778028","doi":"10.7939/r3-dc54-6x83","title":"New representations and approximations for sequential decision making under uncertainty","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Key (lock); Artificial intelligence; Exploit; Observability; Dual (grammatical number); Function (biology); Machine learning; Mathematical optimization; Mathematics","score_opus":0.19214727774047474,"score_gpt":0.5278730889014068,"score_spread":0.3357258111609321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395778028","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058365134,0.000046173504,0.9895475,0.0007220869,0.00020858212,0.00048234867,0.000013849071,0.000047318863,0.003095646],"genre_scores_gemma":[0.3939266,0.000005237769,0.5943244,0.00014704342,0.00020846118,0.000016771874,0.000006860484,0.000013623469,0.011351024],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974199,0.000042666295,0.0005350308,0.0005079323,0.0011431096,0.00035139002],"domain_scores_gemma":[0.9922308,0.006588472,0.000107638385,0.00044610747,0.00044532202,0.00018168624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026479915,0.000102781,0.00015830946,0.00042016804,0.00038923923,0.0003339103,0.00035710054,0.000069461035,0.0007876315],"category_scores_gemma":[0.004073288,0.00007549861,0.000076624005,0.00084848446,0.00009689793,0.00050743396,0.00018025587,0.00010553366,0.000061193256],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015276569,0.000029833214,0.0005092761,0.0000028691852,0.00001591769,0.000003682891,0.00032151473,0.0293308,0.00036039692,0.028974803,0.01310038,0.92719775],"study_design_scores_gemma":[0.0009340961,0.00005449147,0.0073980084,0.000011818782,0.000007314975,0.000019782146,0.0027026818,0.09289081,0.0005511836,0.87831527,0.016942667,0.00017190517],"about_ca_topic_score_codex":0.00005432581,"about_ca_topic_score_gemma":0.0005720553,"teacher_disagreement_score":0.92702585,"about_ca_system_score_codex":0.00007131716,"about_ca_system_score_gemma":0.00012367801,"threshold_uncertainty_score":0.86240125},"labels":[],"label_agreement":null},{"id":"W2396828995","doi":"","title":"A Lazy Approach to Online Learning with Constraints.","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Computer science; Artificial intelligence; Novelty; Mathematical optimization; Bounded function; Online learning; Machine learning; Mathematics","score_opus":0.21612609913797645,"score_gpt":0.43081793676658786,"score_spread":0.2146918376286114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396828995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10462694,0.00001719148,0.8136788,0.000449265,0.000032329703,0.00026847553,0.000007565664,0.00012873205,0.08079073],"genre_scores_gemma":[0.7729436,0.000005201546,0.16885471,0.0002423704,0.00007781198,0.000014513482,0.0000059993727,0.000015179726,0.057840575],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967561,0.00011131133,0.00029630229,0.0005482082,0.00189044,0.00039769022],"domain_scores_gemma":[0.998273,0.0005764921,0.00005634427,0.00040335345,0.00041442958,0.00027635787],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008349875,0.0001250742,0.00023924443,0.00030277477,0.00025784475,0.00007499949,0.0006048848,0.000043180924,0.0008999881],"category_scores_gemma":[0.0019453997,0.00007283024,0.00004321826,0.0013696696,0.0004312448,0.00023077062,0.00016852334,0.00031852355,0.00087258156],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004888495,0.00152859,0.062029768,0.000010376024,0.00009525414,0.000571975,0.0065741753,0.17769146,0.0008166828,0.0033583443,0.036667533,0.710167],"study_design_scores_gemma":[0.0070146634,0.003265209,0.16628009,0.000057205805,0.000017500526,0.0037865422,0.042275645,0.18907753,0.0034716038,0.006084227,0.57618856,0.002481212],"about_ca_topic_score_codex":0.000021170394,"about_ca_topic_score_gemma":0.000018371102,"teacher_disagreement_score":0.70768577,"about_ca_system_score_codex":0.000033730365,"about_ca_system_score_gemma":0.00012097696,"threshold_uncertainty_score":0.99990535},"labels":[],"label_agreement":null},{"id":"W2398037065","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":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Commit; Computer science; Database","score_opus":0.3686539785191696,"score_gpt":0.33170251449792354,"score_spread":0.03695146402124605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398037065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2549816,0.00006886682,0.7018714,0.00041935607,0.0012029954,0.0005470373,0.00013561755,0.00025237617,0.040520784],"genre_scores_gemma":[0.9783825,0.00013149937,0.00016473011,0.000058362282,0.00021685145,0.0000027348597,0.00000903415,0.00004089314,0.020993374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953985,0.00049913663,0.0004657879,0.0020296997,0.0009007686,0.0007061084],"domain_scores_gemma":[0.99335766,0.0025025543,0.00043674267,0.0027079927,0.0006527039,0.00034231922],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013371932,0.0004846768,0.0006414422,0.0009720168,0.00029255197,0.00047441025,0.00387229,0.00042879372,0.0016688993],"category_scores_gemma":[0.0011390666,0.00036618134,0.00040682807,0.0009644918,0.0005405338,0.0008058205,0.002468818,0.0010674851,0.004528654],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008831482,0.00044675425,0.0014673795,0.000054138058,0.0002823452,0.0023632916,0.00093657034,0.5008511,0.000120695055,0.4503167,0.019491673,0.022786215],"study_design_scores_gemma":[0.00063201407,0.00012683662,0.0006178094,0.00010440422,0.000018391042,0.0000023453665,0.0016008659,0.016030233,0.00022459151,0.9749893,0.005144272,0.00050895044],"about_ca_topic_score_codex":0.000033870747,"about_ca_topic_score_gemma":0.00003337224,"teacher_disagreement_score":0.72340095,"about_ca_system_score_codex":0.00037060436,"about_ca_system_score_gemma":0.00046909825,"threshold_uncertainty_score":0.999879},"labels":[],"label_agreement":null},{"id":"W2402248766","doi":"10.1609/aaai.v25i1.7954","title":"Recommendation Sets and Choice Queries: There Is No Exploration/Exploitation Tradeoff!","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Recommender system; Computer science; Set (abstract data type); Preference elicitation; Bayesian probability; Component (thermodynamics); Function (biology); Query optimization; Information retrieval; Data mining; Artificial intelligence; Machine learning; Preference; Mathematics","score_opus":0.46823225723104683,"score_gpt":0.4411107119125127,"score_spread":0.027121545318534113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402248766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7102395,0.00008831095,0.12690634,0.03333016,0.0024494466,0.0036882258,0.00015514623,0.0003099612,0.122832865],"genre_scores_gemma":[0.99561286,0.00012114937,0.0030580028,0.00020990253,0.00007287172,0.000057760866,0.0000014926151,0.00001751135,0.00084847666],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99715924,0.000054243075,0.0008200888,0.0006202602,0.0010431506,0.00030298566],"domain_scores_gemma":[0.99649864,0.0005140081,0.0005733154,0.00027598094,0.002023984,0.000114059585],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014609066,0.00021270399,0.00027045334,0.00023400663,0.0003073452,0.00030291826,0.001026483,0.00010489253,0.0025870698],"category_scores_gemma":[0.004752047,0.00014534405,0.00008152737,0.0008656463,0.00044904804,0.0016901117,0.00021022362,0.0003019008,0.00042098362],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054091285,0.00038174083,0.0022495699,0.000052421816,0.000041205043,6.0258157e-7,0.03112664,0.000021497473,0.017438142,0.115794696,0.0027193686,0.8296332],"study_design_scores_gemma":[0.000061559316,0.00042190778,0.0018012611,0.000093339266,0.000011363541,0.000002557061,0.013104387,0.024836434,0.31950304,0.6378586,0.0020258003,0.0002797013],"about_ca_topic_score_codex":0.00007871849,"about_ca_topic_score_gemma":0.000037966398,"teacher_disagreement_score":0.8293535,"about_ca_system_score_codex":0.000043779346,"about_ca_system_score_gemma":0.000074525575,"threshold_uncertainty_score":0.9983247},"labels":[],"label_agreement":null},{"id":"W2403303158","doi":"","title":"Bayesian optimal control of smoothly parameterized systems","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Parameterized complexity; Markov decision process; Mathematical optimization; Computer science; Thompson sampling; Bayesian probability; Mathematics; Algorithm; Markov process; Artificial intelligence; Machine learning","score_opus":0.18254699853885475,"score_gpt":0.4346419930056865,"score_spread":0.25209499446683176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403303158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014928266,0.0001918932,0.9784997,0.00026292563,0.0003977434,0.00037081217,0.000027112952,0.000044008015,0.0052775526],"genre_scores_gemma":[0.9803636,0.0000016671448,0.01362269,0.000035505,0.00007396101,0.000024229012,0.0000012407111,0.00001169937,0.005865404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957029,0.00035779513,0.0007429768,0.00038623318,0.0024595077,0.0003505447],"domain_scores_gemma":[0.99621683,0.0015478111,0.000213428,0.0007142024,0.00097506173,0.00033266802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037274025,0.00012495983,0.00049393665,0.00027811652,0.00004118092,0.00017610253,0.00085023296,0.000076813936,0.00031208777],"category_scores_gemma":[0.0050165495,0.00007920113,0.00009905214,0.00066560216,0.00020239745,0.00036195735,0.000111357855,0.00012124078,0.0003846546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048670094,0.0011353754,0.021292029,0.0000694036,0.00046471457,0.00038734364,0.0026483566,0.67556775,0.012758812,0.012269151,0.09579182,0.17274824],"study_design_scores_gemma":[0.0047615753,0.00059967436,0.0006793507,0.000014079512,0.000010020188,0.000026752565,0.0026268892,0.9548072,0.00207876,0.006833715,0.027291914,0.00027005008],"about_ca_topic_score_codex":0.00011249694,"about_ca_topic_score_gemma":0.000004558508,"teacher_disagreement_score":0.9654353,"about_ca_system_score_codex":0.000046917477,"about_ca_system_score_gemma":0.00017204741,"threshold_uncertainty_score":0.60056406},"labels":[],"label_agreement":null},{"id":"W2465908909","doi":"","title":"Shifting regret, mirror descent, and matrices","year":2016,"lang":"en","type":"article","venue":"Spiral (Imperial College London)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Base (topology); Computer science; Class (philosophy); Simplex; Matrix (chemical analysis); Gradient descent; Mathematical optimization; Algorithm; Artificial intelligence; Theoretical computer science; Machine learning; Mathematics; Combinatorics; Artificial neural network","score_opus":0.08209789988066338,"score_gpt":0.381714209005795,"score_spread":0.2996163091251316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2465908909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889938,0.0008523363,0.0020327065,0.0027121997,0.0014335098,0.0007435516,0.00024959876,0.00014871714,0.0028335557],"genre_scores_gemma":[0.98428476,0.00012959541,0.005651156,0.0001590417,0.00060549873,0.000039130595,0.000001731429,0.000042558724,0.009086519],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952361,0.0003093701,0.00081268034,0.0009689582,0.0018341311,0.00083873636],"domain_scores_gemma":[0.9967041,0.0015353698,0.00027067435,0.00071495416,0.00039285937,0.00038201743],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021478995,0.00030521376,0.00051784905,0.00042960592,0.00046451352,0.00033666406,0.0009891203,0.0001663729,0.0012669733],"category_scores_gemma":[0.0050159455,0.00017613228,0.00014535936,0.0012094895,0.00044403132,0.0010726673,0.0005974844,0.00019947451,0.00086754636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004550815,0.000365731,0.05653213,0.00008587653,0.00015240411,0.0011264582,0.0012870013,0.0000061920005,0.17738236,0.025349956,0.031143695,0.70201737],"study_design_scores_gemma":[0.021769559,0.0028938309,0.04922165,0.00046378528,0.000076261655,0.00039924018,0.002265681,0.0011660858,0.07617758,0.18984258,0.6525628,0.0031609603],"about_ca_topic_score_codex":0.000064520056,"about_ca_topic_score_gemma":0.00016865389,"teacher_disagreement_score":0.6988564,"about_ca_system_score_codex":0.00012588751,"about_ca_system_score_gemma":0.0001645987,"threshold_uncertainty_score":0.9999104},"labels":[],"label_agreement":null},{"id":"W2483372187","doi":"10.4018/978-1-59140-702-7.ch021","title":"Online Methods for Portfolio Selection","year":2006,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Portfolio; Selection (genetic algorithm); Portfolio optimization; Computer science; Econometrics; Investment strategy; Post-modern portfolio theory; Investment portfolio; Investment (military); Stock (firearms); Stock market; Economics; Financial economics; Replicating portfolio; Artificial intelligence; Finance; Engineering; Geography","score_opus":0.12451742203920636,"score_gpt":0.4819105692302763,"score_spread":0.35739314719106996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2483372187","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003562222,0.0002836764,0.43085444,0.00004783495,0.0005338556,0.00062894897,0.00055746845,0.00010013237,0.5669901],"genre_scores_gemma":[0.00035328284,0.000004322939,0.18970135,0.00018403208,0.0012222466,0.000048470072,0.00003965495,0.00007871593,0.8083679],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99499726,0.0001053451,0.0011528811,0.0012426969,0.0018376095,0.0006642162],"domain_scores_gemma":[0.9958419,0.0010767684,0.00061397493,0.00083966204,0.0013800473,0.00024761772],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019355388,0.00052613876,0.0008900188,0.00040505364,0.0002450845,0.00027976578,0.0010959537,0.0006551421,0.00030420691],"category_scores_gemma":[0.0011269341,0.0004367945,0.0005685289,0.00013453944,0.00021079258,0.0001236229,0.00027990213,0.000505389,0.00024696646],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009938587,0.000032601423,0.0000074864683,0.000011145178,0.00007103818,0.000020867132,0.0000059832355,0.00024991162,0.000031091826,0.39765033,0.08151557,0.5203046],"study_design_scores_gemma":[0.00026281795,0.00011690146,0.000025650786,0.000019872015,0.000025328372,0.000035551056,0.000004350438,0.0013261347,0.00009563134,0.5589336,0.4388891,0.0002650656],"about_ca_topic_score_codex":0.00007190003,"about_ca_topic_score_gemma":0.0002066376,"teacher_disagreement_score":0.52003956,"about_ca_system_score_codex":0.00055704894,"about_ca_system_score_gemma":0.0005102606,"threshold_uncertainty_score":0.9998084},"labels":[],"label_agreement":null},{"id":"W2509437949","doi":"","title":"Deep learning games","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Nash equilibrium; Computer science; Deep learning; Artificial intelligence; Regret; Karush–Kuhn–Tucker conditions; Artificial neural network; Game theory; Differentiable function; Equivalence (formal languages); Bijection; Mathematical optimization; Machine learning; Mathematics; Mathematical economics; Discrete mathematics","score_opus":0.07726177950359157,"score_gpt":0.39242078176238665,"score_spread":0.31515900225879506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509437949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020402761,0.0004998479,0.9705402,0.0010862057,0.0008944252,0.00036155406,0.0000047637773,0.00034263745,0.0058675627],"genre_scores_gemma":[0.99422914,0.000010331386,0.00025809903,0.00007431392,0.00015695323,0.000038202856,0.0000032306166,0.000009143352,0.0052206167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964124,0.00017271047,0.00091777596,0.00021521402,0.0019134111,0.00036850147],"domain_scores_gemma":[0.99745065,0.00059092656,0.000539568,0.0002787984,0.001011183,0.00012887153],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001684718,0.00013913805,0.00022312472,0.00042948243,0.0003602492,0.0012062123,0.0005641742,0.00007891341,0.000113969734],"category_scores_gemma":[0.0040308745,0.00007338279,0.000055076594,0.0007784728,0.00010559154,0.0077967052,0.000102298116,0.00017203987,0.0018168519],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016162756,0.0000041692124,0.0011861138,0.000025951626,0.000002375253,0.0000014058594,0.000680299,0.011334268,0.00018198793,0.000103243096,0.0007867366,0.9856773],"study_design_scores_gemma":[0.0007783263,0.000105934465,0.002604413,0.00014876768,0.0000030314714,0.000092230126,0.0033733926,0.70765746,0.0006053607,0.0010839392,0.2832368,0.00031031595],"about_ca_topic_score_codex":0.000007975512,"about_ca_topic_score_gemma":0.0000013039887,"teacher_disagreement_score":0.985367,"about_ca_system_score_codex":0.00008993807,"about_ca_system_score_gemma":0.00006313591,"threshold_uncertainty_score":0.9998306},"labels":[],"label_agreement":null},{"id":"W2545509292","doi":"10.1109/globalsip.2013.6737014","title":"Consensus-based distributed online prediction and optimization","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Computer science; Lipschitz continuity; Point (geometry); Gradient descent; Stochastic gradient descent; Optimization problem; Function (biology); Node (physics); Data stream; Distributed computing; Mathematical optimization; Algorithm; Artificial intelligence; Machine learning; Artificial neural network; Mathematics","score_opus":0.08648565861720116,"score_gpt":0.39760601744012514,"score_spread":0.311120358822924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545509292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027778707,0.000024603105,0.9685819,0.002702863,0.00008104451,0.0002929874,0.00017176183,0.000081651335,0.0002844559],"genre_scores_gemma":[0.7905656,0.00001660891,0.20404941,0.00031007495,0.00011884479,0.000040749866,0.0003235926,0.000017389164,0.0045576915],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983025,0.00009263955,0.00032050448,0.0003080241,0.0007947432,0.00018159079],"domain_scores_gemma":[0.99800193,0.00087704294,0.000069284135,0.00027287926,0.00064618234,0.0001326642],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045833673,0.00007868424,0.00012040197,0.00016137579,0.00011320305,0.00019728426,0.00016257036,0.000054801858,0.0032166212],"category_scores_gemma":[0.0024626357,0.000053057163,0.000022956117,0.00054016727,0.00014600666,0.00023143826,0.000060259124,0.0000905165,0.0001437018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030272216,0.00012754832,0.008358527,0.0000030896397,0.000008191162,0.0000037808072,0.000021294998,0.90477264,0.00030642966,0.00007099405,0.03195916,0.05433808],"study_design_scores_gemma":[0.00042547658,0.00005950392,0.019474631,0.0000027803844,0.0000016173324,0.0000034298928,0.00014249467,0.976175,0.00028769058,0.0016237197,0.0017444107,0.00005922809],"about_ca_topic_score_codex":0.000037253933,"about_ca_topic_score_gemma":0.000013760827,"teacher_disagreement_score":0.7645325,"about_ca_system_score_codex":0.00002954754,"about_ca_system_score_gemma":0.000047010046,"threshold_uncertainty_score":0.99769455},"labels":[],"label_agreement":null},{"id":"W2550845292","doi":"10.1007/s10898-018-0688-0","title":"A Bayesian optimization approach to find Nash equilibria","year":2018,"lang":"en","type":"article","venue":"Journal of Global Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Booth University College","funders":"Universiteit Leiden; National Science Foundation","keywords":"Bayesian probability; Nash equilibrium; Mathematical economics; Computer science; Economics; Mathematical optimization; Mathematics; Artificial intelligence","score_opus":0.06602853053884729,"score_gpt":0.4121978716972752,"score_spread":0.3461693411584279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550845292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017571403,0.000055778815,0.9881338,0.00083511695,0.00064842775,0.00025584592,0.000015903086,0.000019816,0.008278212],"genre_scores_gemma":[0.14816046,0.000015963125,0.85016674,0.0002491813,0.0008343351,0.000003165518,0.00000554548,0.000018348084,0.0005462545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99536836,0.0002685364,0.0011401519,0.0003787138,0.0024630667,0.00038117493],"domain_scores_gemma":[0.99508053,0.00018876872,0.0007359305,0.0004211876,0.0031819965,0.0003915749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023889896,0.00018111101,0.0003864865,0.0003713878,0.00019526713,0.00048344818,0.0010186228,0.00013216326,0.000508823],"category_scores_gemma":[0.0048339,0.00013826907,0.0001449006,0.0029938938,0.00013867133,0.001371672,0.00020242172,0.00017163638,0.00007085613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020415673,0.0000991506,0.000447414,0.0000016610917,0.000017805924,0.000005063113,0.000106948406,0.98605335,0.00003169144,0.00012892293,0.0065676942,0.0063361228],"study_design_scores_gemma":[0.0006752184,0.00048625682,0.00072996906,0.000020744088,0.000013086065,0.0001299094,0.00017833147,0.99504733,0.000064612796,0.0013666624,0.0011362197,0.00015168454],"about_ca_topic_score_codex":0.0000044289663,"about_ca_topic_score_gemma":0.0000024923122,"teacher_disagreement_score":0.14640331,"about_ca_system_score_codex":0.0003688764,"about_ca_system_score_gemma":0.00030346768,"threshold_uncertainty_score":0.57869786},"labels":[],"label_agreement":null},{"id":"W2552858844","doi":"10.48550/arxiv.1702.03040","title":"Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Alberta","keywords":"Sublinear function; Regret; Bounded function; Logarithm; Boundary (topology); Domain (mathematical analysis); Constraint (computer-aided design); Regular polygon; Curvature; Computer science; Algorithm; Mathematical optimization; Mathematics; Upper and lower bounds; Discrete mathematics; Geometry; Mathematical analysis","score_opus":0.25291467637716164,"score_gpt":0.32576508533834175,"score_spread":0.07285040896118011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552858844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859969,0.00012962462,0.011550687,0.00060973206,0.00017518608,0.00019734174,0.000025084888,0.000021687227,0.0012937279],"genre_scores_gemma":[0.99548143,0.00004867704,0.00013626779,0.000046225636,0.000037391175,5.5095444e-7,5.437981e-7,0.000007330536,0.0042415587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987867,0.00015885552,0.00015688493,0.00045877753,0.00020464751,0.00023413189],"domain_scores_gemma":[0.99857545,0.00058242487,0.000099875804,0.00056838454,0.0000878324,0.00008605397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011870525,0.00011055621,0.0001790258,0.00014526465,0.0006613257,0.0002868297,0.0005354048,0.00007147066,0.000055345863],"category_scores_gemma":[0.00078607624,0.00008076173,0.000049409522,0.00021212322,0.0010002424,0.0006749554,0.00031208983,0.00021133303,0.000017716218],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014261507,0.000059784976,0.9687643,0.000013370896,0.00008422316,0.0004894467,0.0022145289,0.0063442667,0.00016417408,0.009706487,0.0004511295,0.0115656685],"study_design_scores_gemma":[0.0041656536,0.00016506991,0.44089416,0.00013017684,0.000039687253,0.000049958766,0.02702905,0.41725785,0.00053755566,0.101975255,0.007242475,0.0005131307],"about_ca_topic_score_codex":0.00012534128,"about_ca_topic_score_gemma":0.0003203874,"teacher_disagreement_score":0.5278702,"about_ca_system_score_codex":0.000029053303,"about_ca_system_score_gemma":0.000042257743,"threshold_uncertainty_score":0.50864494},"labels":[],"label_agreement":null},{"id":"W2553665199","doi":"","title":"The Forget-me-not Process","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Piecewise; Computer science; Logarithm; Probabilistic logic; Sequence (biology); Task (project management); Partition (number theory); Range (aeronautics); Process (computing); Data mining; Parametric statistics; Bayesian probability; Algorithm; Identification (biology); Artificial intelligence; Machine learning; Mathematics; Statistics; Engineering","score_opus":0.09964141962034775,"score_gpt":0.4246329324623445,"score_spread":0.3249915128419968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553665199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1024968,0.0019170078,0.84954435,0.022235695,0.00609411,0.0032038835,0.00012793437,0.0010554254,0.01332477],"genre_scores_gemma":[0.9922076,0.000017296601,0.000054101427,0.00016930954,0.00021031225,0.00013449883,0.0000024460987,0.000011546175,0.0071929307],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950955,0.00014640059,0.0012143522,0.00024493903,0.002782738,0.00051609706],"domain_scores_gemma":[0.9956794,0.0011651301,0.0007193568,0.00051652465,0.0017761864,0.00014342407],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0029824635,0.00017428008,0.00022052556,0.00024569305,0.0010287575,0.0021030267,0.0012230958,0.00008607092,0.00001371007],"category_scores_gemma":[0.004628016,0.000071318056,0.00006634726,0.0008997413,0.00022394658,0.007812628,0.00011269158,0.00016646665,0.0006845546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059133643,0.0000060394627,0.0003393521,0.000042713535,0.0000042743472,9.197072e-7,0.0006866737,0.0011856479,0.00020909685,0.00036059247,0.0029157486,0.9941898],"study_design_scores_gemma":[0.001585638,0.00017467806,0.0014862851,0.00026230377,0.0000073562624,0.00016083094,0.0082284855,0.33149397,0.0063996906,0.008270257,0.6413179,0.0006126252],"about_ca_topic_score_codex":0.000006457011,"about_ca_topic_score_gemma":0.000003285446,"teacher_disagreement_score":0.9935772,"about_ca_system_score_codex":0.00009249312,"about_ca_system_score_gemma":0.00018592288,"threshold_uncertainty_score":0.9989329},"labels":[],"label_agreement":null},{"id":"W2559019597","doi":"10.1109/cec.2016.7744386","title":"Contextual bandit algorithm for risk-aware recommender systems","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Genome British Columbia; Genome Canada","keywords":"Recommender system; Computer science; Reinforcement learning; Context (archaeology); Machine learning; Artificial intelligence; Risk analysis (engineering)","score_opus":0.17491537736588925,"score_gpt":0.44714640914436493,"score_spread":0.2722310317784757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559019597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003090357,0.00014906371,0.99409044,0.0012335249,0.0012107772,0.0008021464,0.00061220647,0.000119385404,0.0014734177],"genre_scores_gemma":[0.49458292,0.0003739097,0.07499427,0.000532985,0.0029157803,0.0010998676,0.00003259484,0.0001773642,0.42529032],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995713,0.00033100313,0.00077817653,0.0008218473,0.0016695614,0.0006864317],"domain_scores_gemma":[0.98854434,0.008960642,0.00028104766,0.0008584099,0.0010652572,0.00029030876],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003952858,0.00021954298,0.00044047236,0.00031608882,0.00032938068,0.00030101681,0.0010235995,0.0001399825,0.0022167393],"category_scores_gemma":[0.004160277,0.00010711373,0.00019183228,0.00044305273,0.00017101534,0.0006623731,0.00020541347,0.0001454417,0.0018387766],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002895124,0.000033711385,0.00031802422,0.0000018795046,0.000028028484,0.000003290345,0.000041653464,0.00002507313,0.000028712393,0.00027487514,0.14427778,0.85493803],"study_design_scores_gemma":[0.004345475,0.00049756345,0.0007000783,0.000044378907,0.000014465318,0.00002520923,0.0027041335,0.10506818,0.0015778319,0.02690566,0.8575465,0.0005705294],"about_ca_topic_score_codex":0.00007254933,"about_ca_topic_score_gemma":0.00004288321,"teacher_disagreement_score":0.9190962,"about_ca_system_score_codex":0.00014561189,"about_ca_system_score_gemma":0.00010638747,"threshold_uncertainty_score":0.9989384},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Computer science; Algebra over a field; Calculus (dental); Mathematical economics; Pure mathematics; Medicine","score_opus":0.18861928299444541,"score_gpt":0.44523061759891325,"score_spread":0.25661133460446783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561282814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12641075,0.000063443906,0.8710493,0.000363667,0.0008073623,0.00011334146,0.0000023867042,0.00003570631,0.0011540655],"genre_scores_gemma":[0.96155363,0.000005157028,0.03797325,0.000022106959,0.00040926633,0.0000072470084,2.4464322e-7,0.000006199581,0.000022908505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99530727,0.0002195722,0.0005174397,0.0004792919,0.002798354,0.0006781044],"domain_scores_gemma":[0.9956476,0.0024469518,0.00014981044,0.0007867954,0.00059838424,0.0003704661],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00736225,0.00011911232,0.0002376774,0.00034422628,0.0002102596,0.00020638574,0.0018086111,0.000046868096,0.00020223591],"category_scores_gemma":[0.00377963,0.000081869664,0.000071922404,0.0020725683,0.0041321213,0.0010194721,0.0006574076,0.00018516874,0.00029213514],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037503094,0.00015471957,0.011888319,0.0000063897446,0.000004316914,0.0000024025762,0.0020180817,0.000736916,0.0052675684,0.67327,0.00005050898,0.3065633],"study_design_scores_gemma":[0.00036674424,0.00027500925,0.12788895,0.000047900085,0.0000077122495,0.000017920218,0.0003709767,0.50149965,0.12164664,0.24623938,0.0012850683,0.00035401498],"about_ca_topic_score_codex":0.0000012340134,"about_ca_topic_score_gemma":4.129242e-8,"teacher_disagreement_score":0.83514285,"about_ca_system_score_codex":0.000055730507,"about_ca_system_score_gemma":0.000099045224,"threshold_uncertainty_score":0.9985781},"labels":[],"label_agreement":null},{"id":"W2561826351","doi":"10.1109/isit.2005.1523524","title":"Tracking the best quantizer","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Quantization (signal processing); Sequence (biology); Algorithm; Lossy compression; Quadratic equation; Mathematics; Piecewise; Scalar (mathematics); Computer science; Monotone polygon; Computational complexity theory; Piecewise linear function; Mathematical optimization; Artificial intelligence","score_opus":0.3106148670222755,"score_gpt":0.516547703061707,"score_spread":0.20593283603943158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561826351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10305809,0.0008276669,0.7003019,0.048659373,0.000584691,0.00053281506,0.000007107115,0.00015743067,0.14587092],"genre_scores_gemma":[0.9421139,0.000016079579,0.0056190393,0.0005082706,0.00034097597,0.000006858709,2.4373983e-7,0.000007915462,0.05138676],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99743605,0.00009986208,0.00029836892,0.00027707408,0.0016044445,0.00028421558],"domain_scores_gemma":[0.99729705,0.0017460511,0.00004960696,0.00058722054,0.0002504961,0.000069595524],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021925392,0.00007199029,0.000106822656,0.000105017694,0.00024589358,0.0003287176,0.000981557,0.000031895925,0.0035803395],"category_scores_gemma":[0.0021894595,0.000032146778,0.00006910457,0.0006355983,0.00014129038,0.00047876989,0.00014087575,0.00017703933,0.009655859],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073689507,0.000039694936,0.00096422725,2.3342436e-7,0.0000041762582,0.0000040137256,0.00023016395,0.0019136168,0.0002537667,0.0023226049,0.014949787,0.97931033],"study_design_scores_gemma":[0.00027082942,0.00004068552,0.0037681975,0.0000031491247,0.0000023168918,0.000019721314,0.0024973513,0.031766273,0.0057621566,0.0171833,0.9385485,0.000137489],"about_ca_topic_score_codex":0.00001641263,"about_ca_topic_score_gemma":0.00013453462,"teacher_disagreement_score":0.9791729,"about_ca_system_score_codex":0.000024655941,"about_ca_system_score_gemma":0.00003420388,"threshold_uncertainty_score":0.99733055},"labels":[],"label_agreement":null},{"id":"W2568832377","doi":"10.1109/isit.2012.6284689","title":"Efficient tracking of large classes of experts","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Base (topology); Computer science; Binary number; Class (philosophy); Sequence (biology); Upper and lower bounds; Algorithm; Set (abstract data type); Block (permutation group theory); Artificial intelligence; Theoretical computer science; Mathematics; Machine learning; Combinatorics; Arithmetic","score_opus":0.19343292246344623,"score_gpt":0.5014377617839864,"score_spread":0.3080048393205401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568832377","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.766556,0.0005650018,0.22560093,0.0001233093,0.00026678198,0.00013777394,0.000011708134,0.000017283588,0.0067211636],"genre_scores_gemma":[0.9943488,0.000004324056,0.004201641,0.000018142013,0.000053042055,0.000003172164,3.825777e-7,0.000006112845,0.001364344],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99725646,0.000097408454,0.00043300813,0.00017171155,0.0016797716,0.0003616275],"domain_scores_gemma":[0.9975401,0.001354603,0.00016016628,0.00041541405,0.00042389176,0.00010583669],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002310022,0.0000705838,0.00023571735,0.00024230631,0.000043735938,0.000016491034,0.00042572318,0.00004236583,0.001486984],"category_scores_gemma":[0.002586659,0.00004392069,0.000087028726,0.0006409718,0.00010844911,0.00017626153,0.00016575963,0.00005761679,0.00006962055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002988998,0.005943718,0.2946607,0.0001014523,0.00011766584,0.000014912268,0.019562151,0.019247849,0.14542726,0.031228228,0.03578252,0.44761464],"study_design_scores_gemma":[0.0014415488,0.00023176623,0.09559049,0.000048940314,0.000009186945,0.00001351782,0.018761974,0.040327,0.7819029,0.00288732,0.058402218,0.0003831013],"about_ca_topic_score_codex":0.000006909084,"about_ca_topic_score_gemma":0.000005321654,"teacher_disagreement_score":0.6364757,"about_ca_system_score_codex":0.000017714785,"about_ca_system_score_gemma":0.000033930297,"threshold_uncertainty_score":0.99942577},"labels":[],"label_agreement":null},{"id":"W2569695769","doi":"10.1007/978-3-319-50502-2_3","title":"Markov Multi-armed Bandit","year":2016,"lang":"en","type":"book-chapter","venue":"Wireless networks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Markov chain; Computer science; Markov model; Variable-order Markov model; Markov process; Markov property; Markov decision process; Markov kernel; Mathematical optimization; Markov renewal process; Examples of Markov chains; Mathematics; Machine learning; Statistics","score_opus":0.10221312763472323,"score_gpt":0.3813151395114032,"score_spread":0.27910201187668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569695769","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011439097,0.0025923469,0.6091687,0.00045896217,0.0029556067,0.00089732883,0.00019406162,0.00022933425,0.3834922],"genre_scores_gemma":[0.0073455386,0.0014133004,0.0011370397,0.00018885596,0.0029063926,0.0000523042,0.00004299397,0.00022002496,0.98669356],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919656,0.00016452651,0.0013810362,0.0017860512,0.0035299172,0.0011728603],"domain_scores_gemma":[0.9922968,0.0033021218,0.0007982861,0.0022136916,0.00083665666,0.0005524011],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021653164,0.00079405936,0.0012806898,0.0006580658,0.00034768647,0.00038300813,0.0026480507,0.0011988444,0.009833977],"category_scores_gemma":[0.0005387412,0.00053114136,0.00054984255,0.00023657292,0.0008002787,0.00035492663,0.0009373375,0.0014678204,0.005172589],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013448395,0.00003221064,0.000051739138,0.000009273656,0.00011605106,0.00032597635,0.000034005003,0.0010872339,0.0000055892538,0.0068787215,0.06832538,0.9229993],"study_design_scores_gemma":[0.0017514077,0.000102898484,0.00019548231,0.00046700807,0.000035609548,0.000039862887,0.000017691178,0.0512771,0.000015026571,0.045881387,0.8989516,0.0012649335],"about_ca_topic_score_codex":0.000004300942,"about_ca_topic_score_gemma":0.00007205,"teacher_disagreement_score":0.9217344,"about_ca_system_score_codex":0.00029586325,"about_ca_system_score_gemma":0.00021775231,"threshold_uncertainty_score":0.999714},"labels":[],"label_agreement":null},{"id":"W2596047044","doi":"","title":"An Economic Model of Induction","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Argument (complex analysis); Incentive; Test (biology); Political science; Operations research; Management; Economics; Engineering; Medicine","score_opus":0.22913483422267705,"score_gpt":0.4730171926103604,"score_spread":0.24388235838768335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596047044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64583856,0.000004086913,0.34694463,0.0002359201,0.0000849667,0.00012114437,0.0000034602995,0.000018415272,0.0067488393],"genre_scores_gemma":[0.978207,0.0000024598478,0.016193157,0.000019573947,0.000039162056,0.000009090336,6.855222e-7,0.000004225033,0.005524641],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893105,0.000037273076,0.00026963872,0.00021498592,0.00042319638,0.00012386823],"domain_scores_gemma":[0.99910986,0.00012911159,0.00006492616,0.00043104723,0.0001866954,0.000078343095],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005742965,0.000043451982,0.00010455772,0.00017250581,0.000033247816,0.00006946169,0.00041728927,0.000034841327,0.0040001543],"category_scores_gemma":[0.00016278254,0.000029116207,0.000028284772,0.0001231199,0.00007146362,0.0011618563,0.00005049068,0.000057392153,0.0018611322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010125913,0.00007135205,0.0011746488,0.0000011159533,0.0000059037434,1.795177e-7,0.0002419083,0.55130506,0.027502717,0.003612736,0.010819991,0.4052543],"study_design_scores_gemma":[0.00007295592,0.000035032488,0.0015260293,3.3060627e-7,2.893298e-7,5.6857743e-7,0.0002795306,0.8476868,0.010321407,0.13990381,0.00013569786,0.00003750772],"about_ca_topic_score_codex":0.0001579735,"about_ca_topic_score_gemma":0.000026167527,"teacher_disagreement_score":0.40521678,"about_ca_system_score_codex":0.000030302255,"about_ca_system_score_gemma":0.000055135453,"threshold_uncertainty_score":0.99891603},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3279068753148421,"score_gpt":0.5299592419994449,"score_spread":0.2020523666846028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602868127","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028014611,0.0008036362,0.93163,0.0062112445,0.0058993506,0.0034994334,0.0009337723,0.00022400427,0.04799706],"genre_scores_gemma":[0.13514125,0.0007145871,0.09808184,0.0005153912,0.005084095,0.0013703527,0.00033383688,0.00025076198,0.7585079],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919838,0.00019619631,0.0011962099,0.0020694037,0.0035839553,0.00097045855],"domain_scores_gemma":[0.988667,0.0037728592,0.00088530505,0.004408743,0.0018540506,0.00041200197],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0056394734,0.0005263555,0.0011442845,0.000568228,0.0007602947,0.0021775472,0.00618203,0.0007122125,0.0029269815],"category_scores_gemma":[0.014794732,0.0003706185,0.00072992005,0.00020654828,0.00045076103,0.00045754822,0.003895822,0.0010798209,0.003218768],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037224632,0.0001841393,0.0012346973,0.00011114952,0.00019318088,0.00003874295,0.00032376783,0.0045097615,0.000040592906,0.0011322069,0.5605967,0.4312628],"study_design_scores_gemma":[0.0016422569,0.000116993804,0.0035715748,0.000080571,0.000026966145,0.000008627107,0.00013410366,0.01821712,0.0011052896,0.44413906,0.53022087,0.0007365999],"about_ca_topic_score_codex":0.00011153389,"about_ca_topic_score_gemma":0.0001929534,"teacher_disagreement_score":0.8335482,"about_ca_system_score_codex":0.00016441377,"about_ca_system_score_gemma":0.00060038804,"threshold_uncertainty_score":0.9998746},"labels":[],"label_agreement":null},{"id":"W2604713477","doi":"10.48550/arxiv.1703.02626","title":"Horde of Bandits using Gaussian Markov Random Fields","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Thompson sampling; Computer science; Scalability; Cluster analysis; Regret; Markov chain; Graph; Gaussian; Recommender system; Theoretical computer science; Mathematical optimization; Artificial intelligence; Algorithm; Machine learning; Mathematics","score_opus":0.2722265457874038,"score_gpt":0.3314936328505302,"score_spread":0.05926708706312639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604713477","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64530927,0.00003175628,0.34474277,0.000097009804,0.00027651916,0.00015896729,0.000015004167,0.00001884842,0.009349878],"genre_scores_gemma":[0.9920891,0.000050151048,0.0006625301,0.000013744693,0.00007266345,1.5065538e-7,7.424601e-7,0.000009989703,0.007100943],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982793,0.00016068986,0.00027112983,0.00056489283,0.000379914,0.00034412672],"domain_scores_gemma":[0.99703306,0.0006401943,0.00036875272,0.0014566162,0.00032747962,0.0001739088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011040372,0.00014032325,0.00033931626,0.00030986912,0.0005915743,0.00015358106,0.0018428554,0.00012085421,0.00060363265],"category_scores_gemma":[0.0018241078,0.00012282848,0.00017058429,0.0004322654,0.00044673178,0.00085011264,0.0005087536,0.00021133064,0.000100862584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056546624,0.0006831632,0.47508857,0.00011329103,0.00052447687,0.0038876673,0.001420053,0.37931582,0.0035744768,0.033896305,0.0076341275,0.088207394],"study_design_scores_gemma":[0.009833585,0.0002842285,0.11056655,0.00011684303,0.00009178227,0.000026352387,0.0011347366,0.7379425,0.004928225,0.12891237,0.005319893,0.0008429224],"about_ca_topic_score_codex":0.000205739,"about_ca_topic_score_gemma":0.00015646525,"teacher_disagreement_score":0.364522,"about_ca_system_score_codex":0.00005914772,"about_ca_system_score_gemma":0.00010605526,"threshold_uncertainty_score":0.66093546},"labels":[],"label_agreement":null},{"id":"W2611974834","doi":"","title":"Rewards and errors in multi-arm bandits for interactive education","year":2016,"lang":"en","type":"preprint","venue":"LillOA (Université de Lille (University Of Lille))","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Maximization; Utility maximization; Estimation; Artificial intelligence; Machine learning; Mathematical optimization; Engineering","score_opus":0.07773655344355909,"score_gpt":0.3737362547816234,"score_spread":0.2959997013380643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611974834","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.716697,0.0016658565,0.24341588,0.0102869095,0.0023616476,0.0039856886,0.0018151596,0.00019360619,0.01957827],"genre_scores_gemma":[0.8896959,0.001157803,0.03112953,0.00009438111,0.00014879351,0.000008088464,0.00011393809,0.00007461512,0.077576965],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99604154,0.00035585774,0.0004268634,0.001451802,0.0010557782,0.0006681589],"domain_scores_gemma":[0.99526405,0.0014902327,0.00085698685,0.0010134974,0.000967725,0.0004075133],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013489003,0.00043605303,0.0009542367,0.0021876346,0.00052304444,0.00006614005,0.0018670041,0.0006544993,0.0006676796],"category_scores_gemma":[0.0010031055,0.0004653283,0.0004050045,0.0008270225,0.0005967364,0.0009130174,0.0034711286,0.0006954896,0.0000554303],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013075613,0.0043721846,0.039781123,0.0014889379,0.0016840199,0.00086095644,0.1605854,0.004667657,0.0041442853,0.008636041,0.08097049,0.6797333],"study_design_scores_gemma":[0.025794102,0.0019033991,0.16657908,0.0032444657,0.00053834147,0.00016553076,0.2703954,0.061904453,0.0019096122,0.17093265,0.2917942,0.004838779],"about_ca_topic_score_codex":0.000824808,"about_ca_topic_score_gemma":0.002265452,"teacher_disagreement_score":0.6748945,"about_ca_system_score_codex":0.0016614574,"about_ca_system_score_gemma":0.00097592047,"threshold_uncertainty_score":0.9997798},"labels":[],"label_agreement":null},{"id":"W2613496886","doi":"10.23919/date.2017.7927235","title":"Multi-armed bandits for efficient lifetime estimation in MPSoC design","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"MPSoC; Computer science; Estimation; System on a chip; Embedded system; Engineering; Systems engineering","score_opus":0.28522129695402665,"score_gpt":0.5120190131924317,"score_spread":0.22679771623840506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613496886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008110001,0.00002714855,0.98939043,0.0007960532,0.0002818624,0.0010069269,0.000010151833,0.00003395032,0.00034350128],"genre_scores_gemma":[0.6479826,0.0000032737623,0.34598523,0.000038289178,0.000048352253,0.0001329195,0.0000028591955,0.000014249038,0.005792233],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972232,0.0001348415,0.0004889279,0.00054151716,0.0011748283,0.00043668994],"domain_scores_gemma":[0.99565375,0.0026751917,0.00022506037,0.00093880744,0.0003685425,0.00013866452],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0045436127,0.00013208107,0.0002549844,0.0003377925,0.00051976595,0.000572695,0.0012410217,0.000086293265,0.00030553635],"category_scores_gemma":[0.0222004,0.00009306799,0.00007327887,0.0002244986,0.00016747414,0.00042605412,0.0002047037,0.00012262858,0.0006211936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031021863,0.00042057963,0.0018535269,0.000010280065,0.000014226034,0.000023397184,0.0006147095,0.6983349,0.0015319585,0.00021475503,0.0079168845,0.2887546],"study_design_scores_gemma":[0.0016975859,0.00007242616,0.025909446,0.000011528385,0.0000017429965,0.0000015055657,0.00007616431,0.96283185,0.004378501,0.004080618,0.0008104221,0.00012818362],"about_ca_topic_score_codex":0.000034623372,"about_ca_topic_score_gemma":0.000054505766,"teacher_disagreement_score":0.64340514,"about_ca_system_score_codex":0.000095567346,"about_ca_system_score_gemma":0.00011868307,"threshold_uncertainty_score":0.986036},"labels":[],"label_agreement":null},{"id":"W2740079300","doi":"10.24963/ijcai.2017/281","title":"Efficiency Through Procrastination: Approximately Optimal Algorithm Configuration with Runtime Guarantees","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Procrastination; Computer science; Algorithm; Asymptotically optimal algorithm; Algorithm design; Distributed computing","score_opus":0.11211907534675045,"score_gpt":0.42880950455152594,"score_spread":0.3166904292047755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740079300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006953541,0.00004528525,0.94746566,0.0013106394,0.000189535,0.0006688781,0.000015958634,0.0001233128,0.0432272],"genre_scores_gemma":[0.66870093,0.00001605619,0.3072652,0.00008658986,0.00030007056,0.00011447177,0.0000150987635,0.00003864186,0.02346298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948144,0.000095401,0.0005901204,0.00090042024,0.0030362932,0.0005633543],"domain_scores_gemma":[0.9960528,0.0004768893,0.00049849984,0.001409965,0.0014473404,0.00011449844],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016211168,0.00026408437,0.00037314504,0.00018634513,0.0016665072,0.0019872154,0.0019433757,0.00009721586,0.0014161263],"category_scores_gemma":[0.002281258,0.00016084801,0.00007817344,0.0004446413,0.0007430172,0.002970714,0.00027254582,0.00025217189,0.0010506305],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003923048,0.00071769254,0.0016068775,0.000027582797,0.00008315534,0.00024027024,0.0022792285,0.009056876,0.0012042698,0.010379923,0.0056567914,0.968355],"study_design_scores_gemma":[0.004416842,0.0014789536,0.024303915,0.00008970213,0.000029106204,0.0002644105,0.00366825,0.85920596,0.05472552,0.026047768,0.024519473,0.0012501006],"about_ca_topic_score_codex":0.000055944194,"about_ca_topic_score_gemma":0.000019034183,"teacher_disagreement_score":0.9671049,"about_ca_system_score_codex":0.000057158057,"about_ca_system_score_gemma":0.00019781572,"threshold_uncertainty_score":0.9997272},"labels":[],"label_agreement":null},{"id":"W2765574662","doi":"10.1109/tac.2017.2765501","title":"The Multi-Armed Bandit With Stochastic Plays","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Sublinear function; Mathematical optimization; Upper and lower bounds; Stochastic process; Process (computing); Computer science; Power (physics); Work (physics); Demand response; Mathematics; Engineering; Machine learning; Statistics; Discrete mathematics","score_opus":0.07040009105956221,"score_gpt":0.3874683501386741,"score_spread":0.31706825907911185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765574662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049687806,0.000027962978,0.9908764,0.002203481,0.00065893383,0.00091619504,0.00005994089,0.00013021305,0.000158103],"genre_scores_gemma":[0.99353415,0.000004937705,0.0018506614,0.00008175645,0.000057326273,0.00030461783,2.7334738e-7,0.000029565537,0.0041366946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961112,0.00022513181,0.0005733356,0.00052141154,0.0019886706,0.0005802649],"domain_scores_gemma":[0.99166,0.0053048893,0.00037401484,0.002092493,0.00033942302,0.00022917776],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017108887,0.00025446093,0.00040633278,0.00021944274,0.003404996,0.0012259671,0.0018174686,0.00008415945,0.00047482728],"category_scores_gemma":[0.0009812792,0.0001336353,0.00016879666,0.00023570175,0.0007191563,0.00048820014,0.0000043870564,0.00037000634,0.00096883863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005177029,0.0003900393,0.000035073397,0.000008361273,0.00028297023,0.00006204664,0.0005293963,0.1877837,0.00031513482,0.000042224245,0.00052656897,0.8095068],"study_design_scores_gemma":[0.004811674,0.00025586537,0.002668387,0.00003940271,0.00004813846,0.00002983502,0.00027495652,0.9897996,0.00043769283,0.0008836203,0.00053283875,0.00021795131],"about_ca_topic_score_codex":0.00003571733,"about_ca_topic_score_gemma":0.0005827101,"teacher_disagreement_score":0.9890257,"about_ca_system_score_codex":0.00010340054,"about_ca_system_score_gemma":0.00018303847,"threshold_uncertainty_score":0.9998109},"labels":[],"label_agreement":null},{"id":"W2768553781","doi":"10.3386/w24046","title":"Fast and Slow Learning From Reviews","year":2017,"lang":"en","type":"report","venue":"National Bureau of Economic Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Army Research Office; Multidisciplinary University Research Initiative","keywords":"Computer science; Psychology","score_opus":0.7586984365747184,"score_gpt":0.6545416765619062,"score_spread":0.10415676001281216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768553781","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008551614,0.020993352,0.0006539434,0.0014316337,0.0013594436,0.0015896261,0.00039077253,0.000025380099,0.9727007],"genre_scores_gemma":[0.1518884,0.0910054,0.004348586,0.00003086492,0.008170642,0.00045970854,0.0012672332,0.00020743074,0.7426217],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98686635,0.0011316768,0.00176129,0.0014780875,0.008111769,0.00065084547],"domain_scores_gemma":[0.980934,0.010431513,0.0014095288,0.0012257146,0.005703755,0.00029543546],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.04323959,0.00031199196,0.001313766,0.0017706943,0.0006848381,0.000762479,0.0025808606,0.0005156159,0.0023933605],"category_scores_gemma":[0.088937916,0.0002554909,0.00028714724,0.00027192073,0.001095875,0.0006473248,0.0013153022,0.002227524,0.0019669803],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009095774,0.000060275997,0.0030688953,0.000093009585,0.00016204773,0.000022896462,0.00015367757,0.0012481047,0.00008907251,0.0026431887,0.50401926,0.4883486],"study_design_scores_gemma":[0.00033339392,0.000085759355,0.0025710703,0.00019465243,0.00000625152,0.000014069998,0.00008135692,0.0030114758,0.00006181038,0.35362312,0.6397848,0.00023224631],"about_ca_topic_score_codex":0.0020639913,"about_ca_topic_score_gemma":0.0003207663,"teacher_disagreement_score":0.48811635,"about_ca_system_score_codex":0.0012997458,"about_ca_system_score_gemma":0.005517885,"threshold_uncertainty_score":0.99998975},"labels":[],"label_agreement":null},{"id":"W2770008080","doi":"","title":"Efficient Sublinear-Regret Algorithms for Online Sparse Linear Regression with Limited Observation","year":2017,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Regret; Sublinear function; Computer science; Algorithm; Linear regression; Constraint (computer-aided design); Task (project management); Exponential function; Mathematical optimization; Mathematics; Machine learning; Discrete mathematics","score_opus":0.25850632172385657,"score_gpt":0.4470429972754272,"score_spread":0.1885366755515706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770008080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31148985,0.0001963521,0.68138736,0.0025499244,0.0014657464,0.0021724214,0.00026906992,0.00028011386,0.00018916297],"genre_scores_gemma":[0.96892196,0.000007079455,0.027248595,0.00019509207,0.0007165697,0.00020135369,0.00039345058,0.00004125137,0.002274651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949041,0.00010759138,0.001371098,0.00046581205,0.002604946,0.0005464558],"domain_scores_gemma":[0.9924403,0.00042855515,0.0021359716,0.0011198594,0.0036597564,0.00021557052],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022742492,0.00032182864,0.00048852206,0.0005060181,0.0017760693,0.0031273025,0.0013099964,0.00018476321,0.000011200556],"category_scores_gemma":[0.0048961686,0.00019578838,0.000098591336,0.00067794626,0.00023259995,0.004613444,0.00017844352,0.0003298494,0.0000541893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007516705,0.0001569789,0.0024416568,0.00037107934,0.000022441767,0.000008401428,0.0012415476,0.47088408,0.00018244208,0.00009444678,0.0026540123,0.52119124],"study_design_scores_gemma":[0.001505864,0.0002177994,0.0035308758,0.0002833797,0.000009897922,0.000034263714,0.0008152613,0.97308725,0.0003388921,0.000063044616,0.019848865,0.00026461072],"about_ca_topic_score_codex":0.000059067886,"about_ca_topic_score_gemma":0.000015033342,"teacher_disagreement_score":0.6574321,"about_ca_system_score_codex":0.00012488132,"about_ca_system_score_gemma":0.00024370044,"threshold_uncertainty_score":0.99952346},"labels":[],"label_agreement":null},{"id":"W2788451989","doi":"10.1088/1742-5468/ab3988","title":"Online learning of quantum states*","year":2019,"lang":"en","type":"article","venue":"Journal of Statistical Mechanics Theory and Experiment","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Noise (video); State (computer science); Quantum state; Quantum; Quantum measurement; Quantum error correction; Quantum information; Quantum algorithm","score_opus":0.05046056171250354,"score_gpt":0.4264589322504994,"score_spread":0.3759983705379959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788451989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17791687,0.0005080844,0.82111126,0.00006388273,0.00025537316,0.0000751758,0.000029101631,0.0000029145995,0.000037323898],"genre_scores_gemma":[0.985238,0.00018385456,0.014198353,0.000033808865,0.000049085866,8.2485917e-7,0.0000021086166,0.000010748046,0.00028317518],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968868,0.0005718371,0.0008465303,0.0001850972,0.0012964723,0.00021324874],"domain_scores_gemma":[0.9943077,0.0044160644,0.00044979516,0.0001726738,0.00046709905,0.0001866765],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051102834,0.00010659631,0.00042540455,0.00018893123,0.000055048782,0.000048142734,0.0003097816,0.000047221394,0.0012313761],"category_scores_gemma":[0.003259954,0.00006926994,0.000063304054,0.00017688095,0.00007512977,0.00018188007,0.00014233832,0.00035651386,0.000029995894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010543802,0.00030026166,0.000038025482,0.000014718589,0.000047016343,0.000046479,0.0011677593,0.0018032726,0.014260391,0.9491997,0.00013302232,0.031935006],"study_design_scores_gemma":[0.0007368877,0.0019722637,0.00008638784,0.00004309363,0.00000976169,0.00004624569,0.008831724,0.06203042,0.013110423,0.91142446,0.0016095082,0.0000988205],"about_ca_topic_score_codex":0.000001370444,"about_ca_topic_score_gemma":1.05724354e-7,"teacher_disagreement_score":0.8073212,"about_ca_system_score_codex":0.00003575748,"about_ca_system_score_gemma":0.000057644953,"threshold_uncertainty_score":0.99968165},"labels":[],"label_agreement":null},{"id":"W2796264871","doi":"10.1007/978-3-319-89656-4_3","title":"A Novel Evaluation Methodology for Assessing Off-Policy Learning Methods in Contextual Bandits","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Robustness (evolution); Outcome (game theory); Observational study; Machine learning; Artificial intelligence; Evaluation function; Policy learning; Quality (philosophy)","score_opus":0.42374252120565437,"score_gpt":0.5813126106282402,"score_spread":0.15757008942258588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796264871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015324914,0.0005079332,0.99506855,0.0005874262,0.0015200953,0.0011648816,0.000010917729,0.000041711784,0.000945215],"genre_scores_gemma":[0.008648114,0.00001737052,0.988436,0.00039898627,0.0013968729,0.00006241976,0.000010616246,0.000052866504,0.0009767778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990051,0.0012826404,0.0014197576,0.002484955,0.0036434012,0.0011182971],"domain_scores_gemma":[0.9643184,0.031321704,0.00079117867,0.0010090207,0.002371603,0.0001881136],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05228436,0.00052776566,0.0011388768,0.004207607,0.00045418914,0.0008935766,0.0026954452,0.0005960916,0.00025393776],"category_scores_gemma":[0.067138396,0.00043069382,0.00020305211,0.002097528,0.0018590282,0.0009400331,0.0011277191,0.0014313919,0.000041323772],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002994944,0.000017104492,0.000028383543,0.000008076645,0.0000067928704,0.0000050497306,0.0010422703,0.093210086,0.0010471026,0.0004035408,0.000013111424,0.9041885],"study_design_scores_gemma":[0.00076035724,0.00019193915,0.00031814122,0.00014631782,0.0000080474465,0.000037109923,0.000006390933,0.65596986,0.0013798717,0.33657315,0.004244145,0.00036464483],"about_ca_topic_score_codex":0.00004909739,"about_ca_topic_score_gemma":0.0002835125,"teacher_disagreement_score":0.9038239,"about_ca_system_score_codex":0.0010562775,"about_ca_system_score_gemma":0.0027497548,"threshold_uncertainty_score":0.9998145},"labels":[],"label_agreement":null},{"id":"W2798538355","doi":"","title":"Online Regression with Partial Information: Generalization and Linear Projection","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Generalization; Computer science; Artificial intelligence; Projection (relational algebra); Regression; Mathematics; Statistics; Algorithm","score_opus":0.10514613752246296,"score_gpt":0.4469563311111556,"score_spread":0.3418101935886927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798538355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12352128,0.000012052752,0.87419176,0.00078042864,0.00015704575,0.00024295015,0.0000074454847,0.00006672637,0.001020317],"genre_scores_gemma":[0.8267766,0.00007236836,0.16042201,0.0007335987,0.0019922056,0.000035894303,0.00011233612,0.000022205417,0.009832735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982878,0.00006674267,0.0002894725,0.00020200181,0.0009998241,0.00015414247],"domain_scores_gemma":[0.9987151,0.00008874126,0.00011260514,0.0002398527,0.0007670521,0.000076670716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057603663,0.000080730635,0.00010015967,0.00022457963,0.0002258348,0.00016360177,0.00013963657,0.000049689115,0.00036697355],"category_scores_gemma":[0.000642907,0.000042265397,0.00001213742,0.0007508711,0.00017543015,0.0015898859,0.00008422088,0.0000741234,0.00010714752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010300628,0.00024696972,0.025158264,0.000019608322,0.000029031757,0.000007855349,0.0031763457,0.0029204742,0.00069242145,0.0017312915,0.026599752,0.93838793],"study_design_scores_gemma":[0.00090202154,0.0007258828,0.005894767,0.000024453071,0.00000371261,0.00003935617,0.0008193201,0.8245689,0.009671765,0.0014698262,0.15570463,0.00017531679],"about_ca_topic_score_codex":0.000028960587,"about_ca_topic_score_gemma":0.0000977942,"teacher_disagreement_score":0.93821263,"about_ca_system_score_codex":0.000020408257,"about_ca_system_score_gemma":0.00006176106,"threshold_uncertainty_score":0.4018103},"labels":[],"label_agreement":null},{"id":"W2803847628","doi":"10.48550/arxiv.1805.09247","title":"Cleaning up the neighborhood: A full classification for adversarial partial monitoring","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Generalization; Adversarial system; Bartok; Computer science; Class (philosophy); Mathematical optimization; Artificial intelligence; Algorithm; Mathematics; Mathematical economics; Machine learning","score_opus":0.41563477076657585,"score_gpt":0.3521115529404013,"score_spread":0.06352321782617454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803847628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10770326,0.000036999078,0.8846433,0.00026261446,0.005124665,0.0010298691,0.00007740181,0.00011745538,0.0010044291],"genre_scores_gemma":[0.99275523,0.00005518179,0.0007431131,0.000016723048,0.0024542431,0.000011451611,0.000018540557,0.00003775954,0.0039077457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961334,0.0004050957,0.0005227861,0.0016307149,0.00066561607,0.00064237526],"domain_scores_gemma":[0.994023,0.002151021,0.00064035814,0.0018216175,0.0011486041,0.00021537606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002464359,0.00034573974,0.0004278135,0.0003817323,0.00078981905,0.0004355881,0.0029427186,0.00039799194,0.00021214182],"category_scores_gemma":[0.0026096764,0.00027716183,0.0004042057,0.0009619076,0.00046590943,0.0005036368,0.0016870752,0.0008240693,0.00036904003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008352321,0.00049971906,0.028328462,0.00014925645,0.0009550865,0.0002110801,0.00545188,0.7765324,0.0014236019,0.06813061,0.022097636,0.08786791],"study_design_scores_gemma":[0.0013132512,0.00018282617,0.0027088562,0.0000637246,0.00010518607,0.0000027619121,0.0026893301,0.84711814,0.0005847932,0.13362367,0.0111118555,0.000495594],"about_ca_topic_score_codex":0.00004289521,"about_ca_topic_score_gemma":0.000025958276,"teacher_disagreement_score":0.88505197,"about_ca_system_score_codex":0.00039239338,"about_ca_system_score_gemma":0.00039854148,"threshold_uncertainty_score":0.99996805},"labels":[],"label_agreement":null},{"id":"W2806928859","doi":"10.1609/aaai.v32i1.12183","title":"Imitation Upper Confidence Bound for Bandits on a Graph","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Institut de Valorisation des Données","keywords":"Graph; Upper and lower bounds; Computer science; Imitation; Extension (predicate logic); Theoretical computer science; Mathematics; Mathematical optimization; Artificial intelligence; Psychology","score_opus":0.31198128436934186,"score_gpt":0.4631698758885268,"score_spread":0.15118859151918496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806928859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67392707,0.000065720684,0.26658392,0.016534893,0.0036775249,0.0044207145,0.00015533381,0.00019590375,0.034438908],"genre_scores_gemma":[0.9959992,0.000020311907,0.001545956,0.00030731971,0.00030620827,0.00009903599,9.3286326e-7,0.000021535401,0.0016995086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955236,0.000041292948,0.0009455759,0.00086451817,0.0020711813,0.00055388187],"domain_scores_gemma":[0.9924998,0.0015658992,0.00062970934,0.00047508764,0.004678448,0.0001510564],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025239051,0.00027116746,0.00037601352,0.00043981406,0.00058570673,0.00055771845,0.0022753403,0.00013129329,0.00051056116],"category_scores_gemma":[0.012488029,0.00017653136,0.0002215828,0.0013947401,0.0013574731,0.0005461868,0.00021616813,0.000317042,0.0006867611],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011760405,0.0002417044,0.0002648122,0.00002440372,0.000026667574,4.2717312e-7,0.0021270914,0.00010402781,0.037582852,0.7951377,0.0038931232,0.15942118],"study_design_scores_gemma":[0.000046106743,0.00071693497,0.00034288154,0.000107451415,0.0000067087103,0.0000017424587,0.0012102727,0.011951301,0.39998594,0.5846598,0.00081483444,0.00015600365],"about_ca_topic_score_codex":0.000021036643,"about_ca_topic_score_gemma":0.000033761888,"teacher_disagreement_score":0.3624031,"about_ca_system_score_codex":0.00006789115,"about_ca_system_score_gemma":0.00016830303,"threshold_uncertainty_score":0.9958302},"labels":[],"label_agreement":null},{"id":"W2809048072","doi":"10.1002/asmb.2355","title":"A Bayesian two‐armed bandit model","year":2018,"lang":"en","type":"article","venue":"Applied Stochastic Models in Business and Industry","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Stochastic game; Monotonic function; Mathematical optimization; Multi-armed bandit; Dynamic programming; Computer science; Bayesian probability; Outcome (game theory); Value (mathematics); Term (time); Sequence (biology); Stochastic programming; Mathematical economics; Economics; Mathematics; Artificial intelligence; Machine learning","score_opus":0.1201796460493762,"score_gpt":0.3928292364248337,"score_spread":0.2726495903754575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809048072","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05298108,0.000045449884,0.9391434,0.00041725353,0.00015932704,0.00040262673,0.000020837511,0.00004336054,0.006786672],"genre_scores_gemma":[0.9930406,0.0000055869195,0.00546069,0.00021082717,0.00037226948,0.0001259521,0.000004958086,0.000035958004,0.0007431355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996143,0.000044415137,0.0007022817,0.000977546,0.0014179562,0.00071482843],"domain_scores_gemma":[0.9978403,0.00046575154,0.00016366744,0.0007424291,0.0005204445,0.00026743027],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012860642,0.0003075599,0.00049613445,0.0005844543,0.0002849272,0.00024495847,0.00074590836,0.00043143312,0.00026519073],"category_scores_gemma":[0.00054196443,0.0002462768,0.000034265464,0.001854635,0.0007403991,0.00054236996,0.0004478958,0.0008204002,0.00006266899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017941237,0.00009158714,0.000048037364,0.000007070912,0.000009305966,0.000011339638,0.0005481168,0.9375579,0.0001756474,0.016990019,0.0006944018,0.043687213],"study_design_scores_gemma":[0.0011648936,0.000018881505,0.00028327448,0.000025620531,0.0000043898026,0.000010243891,0.00024686044,0.7084045,0.00004028249,0.28953642,0.000045022083,0.00021965157],"about_ca_topic_score_codex":0.000072139395,"about_ca_topic_score_gemma":0.00006990269,"teacher_disagreement_score":0.94005954,"about_ca_system_score_codex":0.00007774447,"about_ca_system_score_gemma":0.00025927916,"threshold_uncertainty_score":0.9999989},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16252772352173464,"score_gpt":0.46404372301064795,"score_spread":0.3015159994889133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810504435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6783255,0.00011270192,0.32034513,0.0000822525,0.0007046404,0.0002655656,0.0000058398855,0.000049414364,0.00010897457],"genre_scores_gemma":[0.9917893,0.00003098185,0.006997591,0.0002156027,0.00058291154,0.00004117454,0.0000019787117,0.00003998768,0.0003004681],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99546343,0.00033905148,0.00078495045,0.0009723946,0.0014962828,0.0009438819],"domain_scores_gemma":[0.9971382,0.000976267,0.00022582423,0.00089683617,0.00052354025,0.00023930117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002357392,0.0002611593,0.00047171794,0.00059823814,0.0002927054,0.00071577326,0.0023195015,0.00018321947,0.00026434902],"category_scores_gemma":[0.0008723973,0.00021304456,0.000117780255,0.0022326238,0.00050423405,0.0010709612,0.0005755471,0.00042453746,0.00048073975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008240364,0.0012208108,0.3496886,0.000040068346,0.00014080926,0.003461173,0.0031300616,0.09214539,0.019195508,0.000071867806,0.0061385003,0.5239432],"study_design_scores_gemma":[0.0028742536,0.00021498362,0.02385244,0.000104698214,0.000005538033,0.00012375395,0.00040236753,0.940993,0.020671457,0.004225096,0.0056675104,0.0008649067],"about_ca_topic_score_codex":0.00013563459,"about_ca_topic_score_gemma":0.001087583,"teacher_disagreement_score":0.8488476,"about_ca_system_score_codex":0.00012225015,"about_ca_system_score_gemma":0.00009394437,"threshold_uncertainty_score":0.86877054},"labels":[],"label_agreement":null},{"id":"W2884790233","doi":"10.1007/978-3-319-92988-0_4","title":"Learning in a Game of Strategic Experimentation with Three-Armed Exponential Bandits","year":2018,"lang":"en","type":"book-chapter","venue":"Static & dynamic game theory: foundations & applications","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Exponential function; Mathematical economics; Computer science; Operations research; Mathematics; Mathematical analysis","score_opus":0.09269191808257796,"score_gpt":0.41238929095090215,"score_spread":0.3196973728683242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884790233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0087241195,0.00016364637,0.9426685,0.00018475752,0.00011962278,0.0032337066,0.00028549967,0.00013033065,0.044489816],"genre_scores_gemma":[0.83607876,0.00013452124,0.012070434,0.000030197398,0.00016352277,0.0021502883,0.001527762,0.00021218622,0.14763235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940248,0.0003164988,0.0016708239,0.0012523206,0.0021697332,0.00056578766],"domain_scores_gemma":[0.9930187,0.0026780488,0.0014544078,0.0014583921,0.001200898,0.00018957687],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021608775,0.00056127313,0.00087164715,0.0015426042,0.0003117417,0.0003011948,0.0011999913,0.00026004243,0.0054741604],"category_scores_gemma":[0.00037575292,0.0004887788,0.00018129523,0.00092557445,0.0016314471,0.00048283977,0.00020390618,0.0007756903,0.0011842572],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081545685,0.0005961965,0.00009305218,0.00011779638,0.0005899908,0.000020896712,0.009446617,0.015945897,0.0012842927,0.8591747,0.00013449222,0.111780584],"study_design_scores_gemma":[0.0011851494,0.00043561717,0.00029526875,0.00014204082,0.000108719796,0.000014694696,0.0032790196,0.02451743,0.00004919715,0.9638896,0.0055471114,0.00053617364],"about_ca_topic_score_codex":0.000042727967,"about_ca_topic_score_gemma":0.0010126771,"teacher_disagreement_score":0.9305981,"about_ca_system_score_codex":0.0005202824,"about_ca_system_score_gemma":0.0009302591,"threshold_uncertainty_score":0.9997564},"labels":[],"label_agreement":null},{"id":"W2885586573","doi":"","title":"MRG_UWaterloo and WaterlooCormack Participation in the TREC 2017 Common Core Track.","year":2017,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Core (optical fiber); Telecommunications; Operating system","score_opus":0.354013297376704,"score_gpt":0.5097599940313238,"score_spread":0.15574669665461977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885586573","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99248147,0.000074855874,0.0010052786,0.0022308484,0.00017993384,0.0005004735,0.000022255972,0.000023085953,0.003481803],"genre_scores_gemma":[0.99702984,0.000078169316,0.00010544232,0.00008975925,0.00008057982,0.000019580528,0.00000677194,0.00000952735,0.0025803056],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964394,0.00032818367,0.00058565335,0.0005757079,0.0015589204,0.00051214197],"domain_scores_gemma":[0.99647766,0.0011408412,0.0003286458,0.0015585962,0.00035084639,0.00014342337],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0039143334,0.00019835425,0.0003588877,0.00016722722,0.00073771545,0.0015758822,0.0021925105,0.00011821954,0.00033199505],"category_scores_gemma":[0.0026996247,0.00011375236,0.0000551833,0.00025208388,0.0007304106,0.0010509748,0.00033116553,0.00046944237,0.00037513333],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012929424,0.00036864876,0.20076455,0.00003432153,0.000027123624,0.0003570848,0.020049268,0.00009467639,0.004368275,0.005300851,0.002603775,0.7647385],"study_design_scores_gemma":[0.0013251159,0.00032048183,0.9216443,0.000044733715,0.000011770802,0.00003339603,0.0011437368,0.018129148,0.0053748097,0.045671783,0.0059843864,0.0003163752],"about_ca_topic_score_codex":0.000293035,"about_ca_topic_score_gemma":0.0009712568,"teacher_disagreement_score":0.7644221,"about_ca_system_score_codex":0.000037852657,"about_ca_system_score_gemma":0.000088532826,"threshold_uncertainty_score":0.9994606},"labels":[],"label_agreement":null},{"id":"W2888696679","doi":"10.1287/moor.2021.1168","title":"Multiplayer Bandits Without Observing Collision Information","year":2021,"lang":"en","type":"preprint","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Institut de Valorisation des Données; Université de Montréal; Banco Bilbao Vizcaya Argentaria; Ministerio de Economía y Competitividad; Canada First Research Excellence Fund; Centre de Recherches Mathématiques; Fundación BBVA","keywords":"Regret; Logarithm; Collision; Square root; Computer science; Nash equilibrium; Square (algebra); Mathematical optimization; Root (linguistics); Mathematical economics; Mathematics; Computer security; Mathematical analysis; Machine learning; Geometry","score_opus":0.45722932184973136,"score_gpt":0.5586788726154809,"score_spread":0.10144955076574952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888696679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5031856,0.00038576443,0.48789847,0.00097335526,0.0006271983,0.00287858,0.00033006218,0.00007096797,0.0036500103],"genre_scores_gemma":[0.7704714,0.00023338126,0.22475488,0.000020362726,0.00016539924,0.0004227397,0.00031243797,0.000051666157,0.0035677487],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9857937,0.0010218053,0.0023938732,0.0007629242,0.009307857,0.0007198015],"domain_scores_gemma":[0.9797072,0.0037747729,0.00032588717,0.0028473742,0.013077546,0.00026725826],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01472623,0.00034918747,0.00096200453,0.0021018097,0.0007713684,0.003033222,0.0029254786,0.00050602725,0.0011181241],"category_scores_gemma":[0.04280111,0.00027837086,0.0002624699,0.0023893733,0.00042215647,0.0018821053,0.0052398825,0.002037273,0.0005742277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005270423,0.0008468533,0.0005138811,0.0009842527,0.00015301793,0.000024196657,0.02009699,0.9541693,0.0031430388,0.001950874,0.0053897453,0.012675191],"study_design_scores_gemma":[0.0005667354,0.000088791494,0.0006798301,0.0006905843,0.000013460352,0.000012737404,0.010919224,0.96089876,0.013121457,0.011173224,0.0014689728,0.0003662319],"about_ca_topic_score_codex":0.000232365,"about_ca_topic_score_gemma":0.0004100826,"teacher_disagreement_score":0.2672858,"about_ca_system_score_codex":0.00032045034,"about_ca_system_score_gemma":0.0017288195,"threshold_uncertainty_score":0.99996686},"labels":[],"label_agreement":null},{"id":"W2895703110","doi":"10.1007/s10107-018-1336-7","title":"Faster algorithms for extensive-form game solving via improved smoothing functions","year":2018,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Army Research Laboratory; Directorate for Engineering; Directorate for Computer and Information Science and Engineering; Facebook","keywords":"Regret; Game tree; Mathematics; Smoothing; Weighting; Rate of convergence; Mathematical optimization; Logarithm; Entropy (arrow of time); Algorithm; Function (biology); Computer science; Game theory; Mathematical economics; Sequential game; Statistics","score_opus":0.1317707157070351,"score_gpt":0.4261131786377163,"score_spread":0.2943424629306812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895703110","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028290444,0.000050468207,0.99360424,0.00058544165,0.00047452754,0.0013749446,0.000009730445,0.00022992263,0.000841695],"genre_scores_gemma":[0.2623493,0.0000013326346,0.7263937,0.000261457,0.0014702633,0.0006424423,0.000010406901,0.000115223535,0.008755862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952096,0.000087543616,0.001105293,0.0009087172,0.0015232518,0.0011656182],"domain_scores_gemma":[0.9938582,0.003024926,0.0002868342,0.0009133226,0.0015660824,0.0003505881],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036293776,0.00031756572,0.0005688661,0.00035532026,0.0007028071,0.0008908658,0.00085440767,0.00017461398,0.00067623414],"category_scores_gemma":[0.009800911,0.00022819737,0.00030865837,0.00090036343,0.0005880416,0.00082551077,0.00042823784,0.00036995503,0.0012968],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004699783,0.00015463968,0.000019202937,0.000047231322,0.000036508154,0.000006382468,0.001550554,0.000009923167,0.0014575609,0.0005845891,0.0005154424,0.99557096],"study_design_scores_gemma":[0.0009497763,0.0006786409,0.000058479618,0.00008727766,0.000036880865,0.00007006526,0.002707691,0.6483694,0.0019388576,0.27940044,0.065201744,0.0005007818],"about_ca_topic_score_codex":0.0000064645847,"about_ca_topic_score_gemma":0.000012962341,"teacher_disagreement_score":0.99507016,"about_ca_system_score_codex":0.00012164474,"about_ca_system_score_gemma":0.00007151896,"threshold_uncertainty_score":0.9994808},"labels":[],"label_agreement":null},{"id":"W2897984390","doi":"10.1007/s10994-019-05833-y","title":"Combining Bayesian optimization and Lipschitz optimization","year":2019,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institute for Advanced Research","keywords":"Lipschitz continuity; Bayesian optimization; Heuristics; Regret; Mathematical optimization; Computer science; Bayesian probability; Constant (computer programming); Optimization problem; Function (biology); Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.05627383965606547,"score_gpt":0.3841076774584195,"score_spread":0.32783383780235403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897984390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015203854,0.0008416001,0.99286467,0.00071481825,0.0006703257,0.0005665836,0.000019671246,0.00018840074,0.0026135352],"genre_scores_gemma":[0.6659848,0.0005854549,0.32079318,0.0001563053,0.0004233613,0.000057268797,0.0005836512,0.00018198248,0.011234011],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944639,0.00090996677,0.00087182986,0.0013454778,0.0019120212,0.00049675576],"domain_scores_gemma":[0.9962934,0.0014231125,0.0007406874,0.0008620419,0.00047793746,0.00020276823],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032875924,0.00042200836,0.0007110097,0.0008745902,0.00046614886,0.0011939545,0.0009172485,0.0003993274,0.0010351839],"category_scores_gemma":[0.0059672836,0.00037101735,0.00013402312,0.00068035757,0.00012614578,0.00042701335,0.0023928867,0.0020998153,0.00008652739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026859547,0.000019414127,0.010160468,0.000030031384,0.000022026274,0.000008326792,0.00041268746,0.9703333,0.0000046205496,0.000026942675,0.00008636732,0.01886895],"study_design_scores_gemma":[0.0005467594,0.000089719375,0.00040418413,0.00009771563,0.000016118845,0.000012541116,0.00017802787,0.9948166,0.000014916299,0.0014746932,0.0019663812,0.00038232937],"about_ca_topic_score_codex":0.0000856247,"about_ca_topic_score_gemma":0.000012019328,"teacher_disagreement_score":0.6720715,"about_ca_system_score_codex":0.00010774473,"about_ca_system_score_gemma":0.00015552064,"threshold_uncertainty_score":0.999878},"labels":[],"label_agreement":null},{"id":"W2903574704","doi":"10.1609/aaai.v33i01.33013943","title":"Meta-Descent for Online, Continual Prediction","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stochastic gradient descent; Computer science; Gradient descent; Range (aeronautics); Mathematical optimization; Descent (aeronautics); Hessian matrix; Artificial intelligence; Algorithm; Mathematics; Applied mathematics; Artificial neural network","score_opus":0.5329035804286594,"score_gpt":0.47185202673754284,"score_spread":0.061051553691116534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903574704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2898013,0.0010239761,0.6149903,0.027892826,0.018955944,0.023749126,0.009547911,0.0006231183,0.01341551],"genre_scores_gemma":[0.9871867,0.00013226953,0.006116076,0.000147526,0.000507541,0.00035541737,0.000020265885,0.000057513582,0.005476735],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9921551,0.00007572273,0.0021186417,0.0016397663,0.0033263299,0.0006844362],"domain_scores_gemma":[0.98896617,0.0014206644,0.0019428385,0.0010186762,0.006472613,0.00017905165],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0039114133,0.0005879289,0.0013650166,0.0005219295,0.00024844555,0.00074997696,0.00497557,0.00046367405,0.00049631984],"category_scores_gemma":[0.008964201,0.00036616955,0.0010549938,0.0007940918,0.0006503559,0.00037696082,0.0020518492,0.001373971,0.00021150165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003716139,0.0030428884,0.0011940867,0.0010586936,0.0032991776,0.0000022897532,0.0044194665,0.03718725,0.024908766,0.32306662,0.019614412,0.5784902],"study_design_scores_gemma":[0.00008243765,0.0004641557,0.00031415335,0.00033204307,0.0004660518,0.0000026498385,0.0015359374,0.18128598,0.15838513,0.65405273,0.0026038326,0.00047492218],"about_ca_topic_score_codex":0.00004064166,"about_ca_topic_score_gemma":0.000028906401,"teacher_disagreement_score":0.6973854,"about_ca_system_score_codex":0.0001659041,"about_ca_system_score_gemma":0.0005016752,"threshold_uncertainty_score":0.999879},"labels":[],"label_agreement":null},{"id":"W2904232271","doi":"10.1609/aaai.v33i01.33016112","title":"Leveraging Observations in Bandits: Between Risks and Benefits","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Multi-armed bandit; Leverage (statistics); Computer science; Optimism; Context (archaeology); Thompson sampling; Order (exchange); Task (project management); Artificial intelligence; Machine learning; Dependency (UML); Economics; Psychology","score_opus":0.534976651882224,"score_gpt":0.4463792313613104,"score_spread":0.08859742052091357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904232271","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9934001,0.000040326024,0.0013486226,0.0022020282,0.00018578686,0.0004979267,0.000015421158,0.000020218818,0.0022895932],"genre_scores_gemma":[0.9986663,0.00004481131,0.00062360085,0.00006459908,0.000057925492,0.000016757314,6.365495e-7,0.000012176433,0.00051320443],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967798,0.000034674395,0.0008355797,0.00062617793,0.0013375552,0.00038620929],"domain_scores_gemma":[0.997282,0.0009888215,0.0003749671,0.00031715448,0.000936763,0.00010026662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020395285,0.0001862796,0.00037369432,0.0003770996,0.00015713742,0.00030355316,0.0014423375,0.000097261385,0.00023195767],"category_scores_gemma":[0.0034397643,0.00012905367,0.000071877475,0.0014828673,0.00026465073,0.00060394674,0.000451759,0.00045637882,0.00021273727],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013463755,0.00014030901,0.46263266,0.00003936654,0.000021020212,6.9641635e-7,0.0038469143,0.0028548585,0.008324088,0.12992945,0.00013842194,0.39193758],"study_design_scores_gemma":[0.00010353817,0.00020020166,0.26919535,0.00035229864,0.00000885749,0.000002189592,0.005174913,0.034589425,0.12629099,0.5634787,0.0002654003,0.00033811067],"about_ca_topic_score_codex":0.00009205228,"about_ca_topic_score_gemma":0.000036710047,"teacher_disagreement_score":0.43354926,"about_ca_system_score_codex":0.000055549008,"about_ca_system_score_gemma":0.00008415789,"threshold_uncertainty_score":0.5262656},"labels":[],"label_agreement":null},{"id":"W2906115048","doi":"10.1287/moor.2021.1220","title":"A Primal–Dual Learning Algorithm for Personalized Dynamic Pricing with an Inventory Constraint","year":2022,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematical optimization; Curse of dimensionality; Regret; Dual (grammatical number); Dynamic pricing; Computer science; Revenue management; Constraint (computer-aided design); Revenue; Mathematics; Artificial intelligence; Machine learning; Economics; Microeconomics","score_opus":0.21645571140289932,"score_gpt":0.49928447950654015,"score_spread":0.2828287681036408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906115048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10284472,0.00010406776,0.893934,0.0004086913,0.000046927973,0.0018800573,0.00016028712,0.00004454074,0.0005767064],"genre_scores_gemma":[0.3847758,0.000011638214,0.5950463,0.000017472372,0.000059211347,0.0013848473,0.00009939696,0.000073597395,0.018531743],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921001,0.001000477,0.0007754818,0.0005996236,0.0048967507,0.0006275417],"domain_scores_gemma":[0.9941263,0.0025138794,0.00012374076,0.0006968058,0.0023451599,0.00019406916],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013873767,0.00016504097,0.00042368466,0.0011032649,0.0020124658,0.00037637103,0.0010276908,0.000049173057,0.0014399285],"category_scores_gemma":[0.004262734,0.0001294245,0.00010096185,0.001782133,0.00083294854,0.00047403146,0.00056640245,0.0008841141,0.000023092367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053881,0.0046745613,0.0002341702,0.00033920645,0.00037215566,0.00013481935,0.068823315,0.5196187,0.018010404,0.08145364,0.0011342904,0.3046659],"study_design_scores_gemma":[0.0009691857,0.0014780192,0.00001643414,0.00002098897,0.0000068362924,0.00006339336,0.04561574,0.94248104,0.0004890437,0.0071003246,0.0016031462,0.00015585936],"about_ca_topic_score_codex":0.00003536182,"about_ca_topic_score_gemma":0.00007144506,"teacher_disagreement_score":0.42286232,"about_ca_system_score_codex":0.00035151216,"about_ca_system_score_gemma":0.0010095779,"threshold_uncertainty_score":0.9994729},"labels":[],"label_agreement":null},{"id":"W2909800602","doi":"10.3929/ethz-b-000337731","title":"No-Regret Bayesian Optimization with Unknown Hyperparameters","year":2019,"lang":"en","type":"article","venue":"Repository for Publications and Research Data (ETH Zurich)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Hyperparameter; Bayesian optimization; Computer science; Regret; Benchmark (surveying); Gaussian process; Hyperparameter optimization; Mathematical optimization; Convergence (economics); Machine learning; Kernel (algebra); Black box; Artificial intelligence; Function (biology); Bayesian probability; Algorithm; Gaussian; Mathematics; Support vector machine","score_opus":0.2288060053411779,"score_gpt":0.4751225414535335,"score_spread":0.2463165361123556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909800602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009541967,0.00079784845,0.94935375,0.006909068,0.0005520494,0.004688456,0.0008245227,0.0002074167,0.027124938],"genre_scores_gemma":[0.33917865,0.0004887873,0.3873954,0.00014941981,0.00094361935,0.0011380543,0.0030731738,0.00019756945,0.2674353],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940729,0.00056309626,0.0005641484,0.0014502546,0.0026336703,0.0007159191],"domain_scores_gemma":[0.9876356,0.0042562364,0.00019808432,0.003729729,0.0037593136,0.000421014],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0070254896,0.00018567026,0.00030267925,0.0010161288,0.0010549896,0.0018518779,0.0027237998,0.00014087374,0.00018499767],"category_scores_gemma":[0.006466191,0.00012266818,0.00004882142,0.002530041,0.0005506877,0.0027785138,0.0010287272,0.00047974568,0.00015329794],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018564644,0.0020941603,0.043006472,0.00046400947,0.00069739355,0.000037410617,0.0009795519,0.08019652,0.0042703394,0.024951097,0.70225984,0.13918673],"study_design_scores_gemma":[0.00072866835,0.0004419582,0.0013779217,0.000026557529,0.000009715608,0.0000506452,0.00029210502,0.3813692,0.00022794057,0.0008039978,0.6144389,0.00023240165],"about_ca_topic_score_codex":0.00007025912,"about_ca_topic_score_gemma":0.000017528691,"teacher_disagreement_score":0.5619583,"about_ca_system_score_codex":0.00010832035,"about_ca_system_score_gemma":0.00048496513,"threshold_uncertainty_score":0.9991843},"labels":[],"label_agreement":null},{"id":"W2910547178","doi":"10.1609/icaps.v29i1.3505","title":"Robust and Adaptive Planning under Model Uncertainty","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Robustness (evolution); Computation; Mathematical optimization; Computer science; Adversary; Monte Carlo method; Tree (set theory); Decision tree; Monte Carlo tree search; Bayesian probability; Artificial intelligence; Algorithm; Mathematics","score_opus":0.2897143656682048,"score_gpt":0.4215858200438864,"score_spread":0.1318714543756816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910547178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96611905,0.00038166923,0.020769222,0.002182487,0.00075240724,0.0005156384,0.00014152713,0.0002425404,0.008895442],"genre_scores_gemma":[0.98843515,0.00004102605,0.010501551,0.00012217279,0.000077393524,0.000020086274,0.000009729501,0.000026569927,0.0007663322],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99585146,0.000031814692,0.00072166696,0.000977456,0.0020760605,0.00034152335],"domain_scores_gemma":[0.99643344,0.0006517818,0.00091791275,0.00024202892,0.0016312688,0.00012354844],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017710121,0.0003756681,0.0005558572,0.00051562017,0.0002332016,0.00087467686,0.001702132,0.0003259618,0.000030244624],"category_scores_gemma":[0.0017224835,0.0002601492,0.00010951313,0.0002317903,0.00027398125,0.0003208224,0.0020007421,0.0013148221,0.0000069513035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017901699,0.000020315507,0.002640448,0.00003996111,0.00009441901,0.0000015580486,0.0009844503,0.9884625,0.00072239316,0.0059421165,0.00027481565,0.00063798774],"study_design_scores_gemma":[0.00033342745,0.000050926432,0.0022178881,0.0014224502,0.00001768622,0.000013425895,0.0033899997,0.9371794,0.0005065016,0.054597568,0.0000106824045,0.0002600867],"about_ca_topic_score_codex":0.000028416425,"about_ca_topic_score_gemma":8.4732227e-7,"teacher_disagreement_score":0.051283162,"about_ca_system_score_codex":0.00011912704,"about_ca_system_score_gemma":0.0002808471,"threshold_uncertainty_score":0.9999851},"labels":[],"label_agreement":null},{"id":"W2911952628","doi":"10.1109/tac.2019.2895253","title":"Thompson Sampling for Stochastic Control: The Continuous Parameter Case","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sampling (signal processing); Regret; Stochastic control; Mathematics; Control (management); Mathematical optimization; State (computer science); Class (philosophy); Thompson sampling; Computer science; Applied mathematics; Control theory (sociology); Optimal control; Statistics; Algorithm; Artificial intelligence","score_opus":0.07199831115677265,"score_gpt":0.3889426739652809,"score_spread":0.3169443628085083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911952628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035586935,0.00005273363,0.9572486,0.0016349225,0.0013280462,0.0036539128,0.0002684323,0.00017762293,0.00004877672],"genre_scores_gemma":[0.99316895,9.915666e-7,0.0034441508,0.00059633236,0.000092808856,0.0007677448,8.6101363e-7,0.00004616329,0.0018820112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99584395,0.00041417833,0.00095999095,0.00069753703,0.0013791566,0.00070517155],"domain_scores_gemma":[0.96882176,0.02903291,0.00029645461,0.0011879944,0.0004791225,0.00018175365],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0028978628,0.00032322726,0.0007566158,0.0003602495,0.00059245276,0.0004378768,0.00076032203,0.00013639963,0.0012214604],"category_scores_gemma":[0.0011362036,0.00019703532,0.00047508252,0.00054661714,0.0001844498,0.0003186432,0.0000026589066,0.00038327582,0.0009257573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052453426,0.00025214787,0.00001291035,0.000023454812,0.00027242338,0.00006156402,0.0005662738,0.46078873,0.0006755481,0.00006895396,0.00024186505,0.5365116],"study_design_scores_gemma":[0.006154603,0.00044050728,0.00007746379,0.00003301128,0.00011516751,0.0003626335,0.0007458288,0.9876035,0.00018227809,0.0032804322,0.0007492211,0.00025537828],"about_ca_topic_score_codex":0.000021697142,"about_ca_topic_score_gemma":0.000063949905,"teacher_disagreement_score":0.957582,"about_ca_system_score_codex":0.0001166436,"about_ca_system_score_gemma":0.00012463416,"threshold_uncertainty_score":0.9998521},"labels":[],"label_agreement":null},{"id":"W2913189977","doi":"10.48550/arxiv.1902.05454","title":"Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Procrastination; Computer science; Parameterized complexity; Property (philosophy); Heuristic; Algorithm; Work (physics); Running time; Mathematical optimization; Mathematics; Artificial intelligence","score_opus":0.17310895493980513,"score_gpt":0.29484459573338645,"score_spread":0.12173564079358132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913189977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047081243,0.00006985963,0.9464799,0.00008209798,0.00039291134,0.0014024943,0.00013074766,0.00017000591,0.0041907076],"genre_scores_gemma":[0.9614579,0.000044494063,0.020219238,0.000045604833,0.00015193949,0.0000074153354,0.00005206568,0.000060794715,0.017960567],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941435,0.0005153564,0.00065318693,0.002563238,0.0013064025,0.00081833184],"domain_scores_gemma":[0.9923722,0.00167753,0.0010634249,0.0017450205,0.002790934,0.0003508621],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017401511,0.0006238859,0.0008761582,0.00062153966,0.00053124875,0.000790311,0.0023013994,0.00048521537,0.0008298462],"category_scores_gemma":[0.0011157613,0.00054713356,0.00024108606,0.0018592215,0.0008423601,0.0011477892,0.0014800511,0.001678027,0.0014192874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027619777,0.0000905011,0.00087058026,0.000023426304,0.00011335467,0.0004875021,0.00037614824,0.9845583,0.000023265004,0.0020217227,0.00068817165,0.010470843],"study_design_scores_gemma":[0.0010330344,0.000428937,0.001192584,0.0001950867,0.000061391824,0.000021547503,0.0021044929,0.9771705,0.00040474575,0.015806837,0.00086064544,0.00072019984],"about_ca_topic_score_codex":0.00018710614,"about_ca_topic_score_gemma":0.000039564573,"teacher_disagreement_score":0.9262607,"about_ca_system_score_codex":0.00046902444,"about_ca_system_score_gemma":0.0015089278,"threshold_uncertainty_score":0.99969804},"labels":[],"label_agreement":null},{"id":"W2913530954","doi":"","title":"New Algorithms for Multiplayer Bandits when Arm Means Vary Among Players","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Constant (computer programming); Combinatorics; Mathematics; Zero (linguistics); Computer science; Algorithm; Kappa; Statistics; Geometry; Programming language","score_opus":0.1970939867519552,"score_gpt":0.2941718692337994,"score_spread":0.09707788248184421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913530954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1647029,0.000033505396,0.82952005,0.00009522924,0.0007664833,0.00093126844,0.000066407054,0.00011948077,0.0037646517],"genre_scores_gemma":[0.90063,0.000018916719,0.0079724295,0.00007967188,0.00021110564,0.000002117592,0.000014702943,0.00004187213,0.0910292],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99657345,0.00015097344,0.00040580783,0.0014092196,0.0006571565,0.0008033681],"domain_scores_gemma":[0.9954622,0.002108613,0.0002491871,0.0011533563,0.00048366303,0.0005429854],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001146075,0.00031963538,0.00047282802,0.00061684416,0.00027958155,0.00017881431,0.0017695652,0.00021801761,0.002420852],"category_scores_gemma":[0.0007069767,0.00029356836,0.00032575562,0.0012221328,0.0001711676,0.0014605114,0.00039087533,0.00035533763,0.002045136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017651006,0.00054299674,0.120134346,0.000052616608,0.00047881686,0.00072587444,0.0024330725,0.7398168,0.00082745956,0.018019918,0.0626641,0.052538924],"study_design_scores_gemma":[0.0051928847,0.00044968366,0.008889851,0.000035735302,0.00004929767,0.000011165487,0.0015890994,0.8720937,0.0013528394,0.07587725,0.033675972,0.00078253105],"about_ca_topic_score_codex":0.00020701422,"about_ca_topic_score_gemma":0.00014348343,"teacher_disagreement_score":0.8215476,"about_ca_system_score_codex":0.00022115104,"about_ca_system_score_gemma":0.000237339,"threshold_uncertainty_score":0.99995166},"labels":[],"label_agreement":null},{"id":"W2914526782","doi":"10.48550/arxiv.1602.04282","title":"Conservative Bandits","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Mathematical optimization; Constraint (computer-aided design); Complement (music); Computer science; Revenue; Baseline (sea); Adversarial system; Upper and lower bounds; Mathematical economics; Mathematics; Economics; Artificial intelligence; Machine learning; Finance","score_opus":0.33433048380332875,"score_gpt":0.30347587737871823,"score_spread":0.03085460642461052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914526782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3990838,0.000016846972,0.5925953,0.0006964866,0.00021664372,0.0001581743,0.000035659592,0.00008329321,0.0071138158],"genre_scores_gemma":[0.9431086,0.000030298064,0.00016137419,0.00008083206,0.00005426118,3.653365e-7,5.957099e-7,0.000009456108,0.056554183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981105,0.00022971992,0.00020489575,0.0007201609,0.00035059234,0.000384149],"domain_scores_gemma":[0.99611145,0.0023203206,0.00012762888,0.0007056475,0.00051442924,0.00022053272],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00085715944,0.00013438285,0.00020498587,0.00029628992,0.00018852003,0.00005293389,0.0009973433,0.00007452298,0.0019025289],"category_scores_gemma":[0.002060306,0.00008591445,0.000104469604,0.0013836977,0.00041276825,0.00084979215,0.000274477,0.0001101888,0.004067836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016808258,0.0006266852,0.32010666,0.000014565364,0.0003398776,0.004237635,0.0009866875,0.020241423,0.006737906,0.371061,0.10398265,0.1699841],"study_design_scores_gemma":[0.0045657544,0.00036488895,0.07547168,0.000060145485,0.00002551465,0.000023165998,0.0011980232,0.026783515,0.007196148,0.75509274,0.12834872,0.00086970226],"about_ca_topic_score_codex":0.0000192396,"about_ca_topic_score_gemma":0.000053370677,"teacher_disagreement_score":0.5924339,"about_ca_system_score_codex":0.00013298116,"about_ca_system_score_gemma":0.0001067061,"threshold_uncertainty_score":0.99900985},"labels":[],"label_agreement":null},{"id":"W2916603395","doi":"10.24963/ijcai.2019/386","title":"Perturbed-History Exploration in Stochastic Multi-Armed Bandits","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Bernoulli's principle; Offset (computer science); Argument (complex analysis); Computer science; Optimism; Mathematical optimization; Mathematics; Psychology; Machine learning; Engineering; Social psychology","score_opus":0.40352070611907126,"score_gpt":0.4707663724538747,"score_spread":0.06724566633480344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916603395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030950238,0.0010498054,0.987567,0.0005581289,0.0040946826,0.0014652271,0.000027758022,0.00010921407,0.0020331424],"genre_scores_gemma":[0.8888991,0.000106120235,0.011728345,0.0002805285,0.00043985056,0.00045239105,0.000101426034,0.00008790088,0.097904354],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930082,0.00047940982,0.0011563811,0.0016316841,0.0031213847,0.0006029534],"domain_scores_gemma":[0.9945634,0.0023336413,0.0004124111,0.0017731359,0.00071249687,0.00020489666],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003012296,0.00041657715,0.0007927764,0.0015524606,0.00005958096,0.00021886289,0.0018680869,0.0005114861,0.002890768],"category_scores_gemma":[0.008142646,0.00032172244,0.00021024137,0.0005004869,0.00018558903,0.0007500534,0.0016423576,0.0014723006,0.003618156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013356314,0.0003199152,0.00039546567,0.00003956392,0.000027509825,0.00006387584,0.0040806197,0.93279713,0.00013044149,0.000110440255,0.034782376,0.027119087],"study_design_scores_gemma":[0.0016486371,0.00008464836,0.0039061597,0.00013432786,0.0000081278395,0.0000052503146,0.0015095554,0.95928717,0.000096484684,0.017451845,0.015084916,0.0007828798],"about_ca_topic_score_codex":0.00019157982,"about_ca_topic_score_gemma":0.00055398187,"teacher_disagreement_score":0.97583866,"about_ca_system_score_codex":0.0014595939,"about_ca_system_score_gemma":0.0010087552,"threshold_uncertainty_score":0.99992347},"labels":[],"label_agreement":null},{"id":"W2920229473","doi":"10.48550/arxiv.1903.01026","title":"Learning Modular Safe Policies in the Bandit Setting with Application to Adaptive Clinical Trials","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Robustness (evolution); Outlier; Computer science; Modular design; Mathematical optimization; Measure (data warehouse); Estimator; Flexibility (engineering); Suite; Artificial intelligence; Machine learning; Mathematics; Data mining; Statistics","score_opus":0.4112833942530587,"score_gpt":0.4118405645397245,"score_spread":0.0005571702866657979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920229473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34364018,0.000025755999,0.65277904,0.0004949184,0.0001501907,0.0015889897,0.000026740094,0.000038768852,0.0012554382],"genre_scores_gemma":[0.99600416,0.000064227104,0.0009784108,0.00015452989,0.00025520197,0.000010912329,0.000016488704,0.000025768164,0.0024902704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9909417,0.0049094968,0.0010425582,0.0017005567,0.0008666996,0.0005389628],"domain_scores_gemma":[0.9849326,0.011608263,0.0009994823,0.0016856042,0.0005798647,0.00019416165],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023443779,0.00033656633,0.0010118331,0.0007920297,0.00025457636,0.0002672101,0.002670631,0.00035616034,0.00006215647],"category_scores_gemma":[0.008800589,0.00022783832,0.00032398844,0.0019833737,0.00025671284,0.0003054026,0.0014180507,0.0019658539,0.0006093191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041139196,0.000059566868,0.01870765,0.00000679732,0.000046421366,0.000059168793,0.0008623391,0.9696072,0.000008476795,0.0014848039,0.00023710295,0.00850911],"study_design_scores_gemma":[0.0017311237,0.00063376455,0.056294743,0.00015584264,0.000084658685,0.0000061218566,0.012149981,0.8786664,0.000040582967,0.04222046,0.0073263287,0.00068998185],"about_ca_topic_score_codex":0.0003066083,"about_ca_topic_score_gemma":0.00021810216,"teacher_disagreement_score":0.652364,"about_ca_system_score_codex":0.00026130193,"about_ca_system_score_gemma":0.00037516258,"threshold_uncertainty_score":0.99954873},"labels":[],"label_agreement":null},{"id":"W2922444559","doi":"10.24963/ijcai.2019/66","title":"Computing Approximate Equilibria in Sequential Adversarial Games by Exploitability Descent","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute","keywords":"Fictitious play; Convergence (economics); Nash equilibrium; Computer science; Counterfactual thinking; Benchmark (surveying); Mathematical optimization; Perfect information; Regret; Descent (aeronautics); Class (philosophy); Zero (linguistics); Imperfect; Mathematical economics; Mathematics; Economics; Artificial intelligence","score_opus":0.15620157088492598,"score_gpt":0.44148653121042214,"score_spread":0.28528496032549616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922444559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39232776,0.0002959724,0.59794724,0.00044442207,0.0037929916,0.002104257,0.00019232088,0.00018461286,0.0027104516],"genre_scores_gemma":[0.98273647,0.00003148386,0.014358377,0.000060295322,0.00042679274,0.000044001034,0.00011246347,0.00005765481,0.0021724503],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9886282,0.0014643413,0.002000412,0.00263505,0.0040868726,0.0011851393],"domain_scores_gemma":[0.9933455,0.0027728202,0.00061213516,0.0024091837,0.0005728174,0.00028756418],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009937959,0.00058219803,0.0012800349,0.0006362904,0.00013145551,0.00087307446,0.0031143166,0.0005880599,0.0016634869],"category_scores_gemma":[0.005465235,0.00046739492,0.00040072945,0.00079499505,0.0003705536,0.0005664912,0.008073648,0.0022242146,0.00067469676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026930566,0.0029041122,0.07827062,0.0009572558,0.0003823143,0.00024124321,0.008029146,0.46832928,0.011896531,0.0008121552,0.08301345,0.34247082],"study_design_scores_gemma":[0.0024291992,0.000097782526,0.0026135016,0.00016542996,0.000013511062,0.000006524717,0.0017183908,0.9344377,0.003896782,0.049408574,0.00413364,0.0010789849],"about_ca_topic_score_codex":0.00053402537,"about_ca_topic_score_gemma":0.0000940434,"teacher_disagreement_score":0.59040874,"about_ca_system_score_codex":0.0007631243,"about_ca_system_score_gemma":0.0007399292,"threshold_uncertainty_score":0.99994886},"labels":[],"label_agreement":null},{"id":"W2945633694","doi":"","title":"Fiduciary Bandits","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fiduciary; Ask price; Incentive; Action (physics); Computer science; Recommender system; Constraint (computer-aided design); Ex-ante; Face (sociological concept); Operations research; Mathematical economics; Economics; Microeconomics; Finance; Mathematics; Law; Machine learning; Political science","score_opus":0.3111492193743946,"score_gpt":0.31343074353404116,"score_spread":0.002281524159646553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945633694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32919452,0.0003371474,0.6380315,0.0003335299,0.0038184437,0.0011462556,0.00027316395,0.00027997186,0.0265855],"genre_scores_gemma":[0.93524593,0.00018167497,0.0002810314,0.00007796561,0.00026374674,0.00000104633,0.00003141463,0.000036879188,0.06388028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953551,0.0004509727,0.00047473458,0.002210592,0.0008356835,0.0006728724],"domain_scores_gemma":[0.99406517,0.0015532831,0.00044833767,0.0028561563,0.00075806427,0.0003190038],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017844436,0.00041603777,0.0006912061,0.00091344945,0.00021493313,0.0002847372,0.0036934456,0.00052486255,0.0019215357],"category_scores_gemma":[0.001459001,0.0003931506,0.00043999782,0.001438975,0.00028517283,0.00052836625,0.003963389,0.0013718941,0.007854275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013292997,0.00011452625,0.009223427,0.00003630142,0.00010040979,0.0007600929,0.00015185094,0.96212,0.000016205346,0.004111824,0.019146668,0.0040857648],"study_design_scores_gemma":[0.0012231596,0.00012182171,0.011887876,0.00011685685,0.00006738009,0.000011978151,0.00056689524,0.48984164,0.0002581843,0.4564401,0.03829843,0.0011656713],"about_ca_topic_score_codex":0.000080872116,"about_ca_topic_score_gemma":0.000046461817,"teacher_disagreement_score":0.63775045,"about_ca_system_score_codex":0.00034917466,"about_ca_system_score_gemma":0.00054062385,"threshold_uncertainty_score":0.99985206},"labels":[],"label_agreement":null},{"id":"W2948647439","doi":"10.48550/arxiv.1902.01239","title":"A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Sublinear function; Computer science; Minimax; Matching (statistics); Mathematical optimization; Collision; Algorithm; Mathematics; Machine learning; Discrete mathematics; Computer security; Statistics","score_opus":0.2895327430734515,"score_gpt":0.3426463910670395,"score_spread":0.053113647993587976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948647439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017727349,0.0000407703,0.9756459,0.00022892392,0.0017587426,0.0021183859,0.0005803115,0.00017105363,0.0017285835],"genre_scores_gemma":[0.8880637,0.00012788174,0.06924141,0.00014969936,0.00066433166,0.000025988345,0.00015516103,0.0001449977,0.041426826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99319464,0.00055237196,0.00078981207,0.0030782598,0.0012083268,0.0011765745],"domain_scores_gemma":[0.9883873,0.00630309,0.00081693043,0.0024591228,0.0013947241,0.00063881825],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002780988,0.0007113402,0.0010987481,0.001122731,0.0004072589,0.00046295745,0.0028270055,0.0009397115,0.00093003234],"category_scores_gemma":[0.003267182,0.00067783054,0.00078479626,0.00093272555,0.0005580414,0.0012740704,0.0027932057,0.0018761893,0.0011642753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011029234,0.0011678395,0.008720304,0.00015127809,0.0009839593,0.0020757644,0.0012430958,0.89176154,0.000029920366,0.0048594605,0.06165558,0.026248325],"study_design_scores_gemma":[0.0020086162,0.00020492187,0.0010453658,0.00007710534,0.0001240545,0.000012779782,0.0008268534,0.92579925,0.0001621747,0.05765396,0.01127832,0.0008066177],"about_ca_topic_score_codex":0.00017470345,"about_ca_topic_score_gemma":0.00013780614,"teacher_disagreement_score":0.9064045,"about_ca_system_score_codex":0.0006083723,"about_ca_system_score_gemma":0.00088323286,"threshold_uncertainty_score":0.99998325},"labels":[],"label_agreement":null},{"id":"W2950236408","doi":"","title":"Prediction by Random-Walk Perturbation","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Random walk; Perturbation (astronomy); Order (exchange); Mathematics; Combinatorics; Time horizon; Computer science; Mathematical optimization; Discrete mathematics; Statistics; Physics; Economics","score_opus":0.2137636876773428,"score_gpt":0.27774421428219465,"score_spread":0.06398052660485185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950236408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1995716,0.00022793318,0.79134446,0.000262101,0.0012752677,0.0010206527,0.0002734011,0.00022794862,0.005796647],"genre_scores_gemma":[0.9237083,0.00034344662,0.00023500116,0.000046695928,0.00021084976,0.000005938316,0.0001245413,0.000029455372,0.075295776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960558,0.00050868373,0.00051076734,0.0016435774,0.00080118317,0.00047997764],"domain_scores_gemma":[0.99564356,0.0011521379,0.00046246726,0.001466136,0.0009760601,0.00029965464],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014269156,0.00035212713,0.0005171421,0.0006215875,0.00029186282,0.0003727641,0.0017975002,0.0004944803,0.001736717],"category_scores_gemma":[0.0016736564,0.00032166133,0.00030155003,0.0010469197,0.00027539203,0.0008899496,0.0012853335,0.0009528952,0.0018068766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007332813,0.0003888391,0.006454266,0.00006206453,0.0002663258,0.00017949031,0.0006312873,0.76807004,0.00040202317,0.0061400835,0.19471791,0.021954358],"study_design_scores_gemma":[0.0018189591,0.00007646977,0.0011267563,0.00003778291,0.000044216817,0.0000035696987,0.00032789554,0.71318364,0.00024778838,0.26449326,0.018229777,0.00040989523],"about_ca_topic_score_codex":0.00013908834,"about_ca_topic_score_gemma":0.000014588753,"teacher_disagreement_score":0.79110944,"about_ca_system_score_codex":0.000421469,"about_ca_system_score_gemma":0.00019462265,"threshold_uncertainty_score":0.9999235},"labels":[],"label_agreement":null},{"id":"W2951017703","doi":"","title":"On Local Regret","year":2012,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Locality; Disjunct; Computer science; Generalization; Online learning; Artificial intelligence; Jump; Set (abstract data type); Machine learning; Statistical learning; Graph; Theoretical computer science; Mathematics; Psychology; Cognitive psychology; World Wide Web","score_opus":0.27637977516590406,"score_gpt":0.5120107174168465,"score_spread":0.2356309422509424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951017703","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014311181,0.00023828314,0.8925693,0.0011591016,0.0019035975,0.0003616698,0.00004069665,0.00011293993,0.10218331],"genre_scores_gemma":[0.8921529,0.000033034066,0.009483485,0.0004647111,0.0007832019,0.00006175687,0.00002221953,0.000045891862,0.0969528],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933134,0.00027707938,0.0006093887,0.0009849673,0.0042138435,0.0006013313],"domain_scores_gemma":[0.99415565,0.0026370767,0.00020660079,0.0021922705,0.00047210188,0.0003363176],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003430774,0.00028203317,0.000477183,0.00048183967,0.000101001795,0.0003111976,0.0021779228,0.0003961669,0.0120740775],"category_scores_gemma":[0.003724362,0.00017409108,0.00022366937,0.000413092,0.0002908229,0.00017073045,0.0026075183,0.001367073,0.017068109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009612682,0.00017249465,0.0001938834,0.000012689011,0.000032917418,0.00004664266,0.00019492013,0.021483991,0.0000064339165,0.013284656,0.22912987,0.73534536],"study_design_scores_gemma":[0.00031184347,0.00008488995,0.0016576251,0.000050010225,0.000006781102,0.000010270643,0.00029011504,0.024140922,0.001048775,0.85552716,0.11632264,0.0005489748],"about_ca_topic_score_codex":0.00004518013,"about_ca_topic_score_gemma":0.00002446942,"teacher_disagreement_score":0.8907218,"about_ca_system_score_codex":0.00021872489,"about_ca_system_score_gemma":0.00019475791,"threshold_uncertainty_score":0.988829},"labels":[],"label_agreement":null},{"id":"W2951277631","doi":"","title":"An Adaptive Algorithm for Finite Stochastic Partial Monitoring","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Logarithm; Minimax; Space (punctuation); Mathematical optimization; Computer science; Algorithm; Mathematics; Machine learning","score_opus":0.3480788863386984,"score_gpt":0.3467574326496035,"score_spread":0.0013214536890948647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951277631","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019455101,0.00011653305,0.9768123,0.000017702416,0.0020562292,0.0009083312,0.00038220087,0.00013830954,0.000113264694],"genre_scores_gemma":[0.9807831,0.000026040792,0.015427055,0.000009479837,0.001530697,0.000015665335,0.000036681682,0.000058894035,0.0021123819],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99549073,0.00040553306,0.0005129108,0.001868314,0.0007044455,0.0010180655],"domain_scores_gemma":[0.99323237,0.0026963917,0.0005040104,0.0017894084,0.0011166616,0.00066118216],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019918897,0.00049028185,0.00068054517,0.0006969271,0.00044557443,0.00028454742,0.0025647753,0.0004810647,0.000181032],"category_scores_gemma":[0.0010230631,0.0004914725,0.00040004536,0.0009149052,0.00033150747,0.0010399616,0.0013879053,0.0009778619,0.000358225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022469099,0.00017164488,0.0003755909,0.000007446648,0.00008777407,0.000068029694,0.0002880601,0.94561374,0.000015802509,0.0009706288,0.00008246704,0.0520941],"study_design_scores_gemma":[0.0007216429,0.00021613919,0.00048390933,0.00004451857,0.00008170418,0.0000020925308,0.0009065852,0.93702316,0.00024115505,0.059261892,0.00046558995,0.0005516367],"about_ca_topic_score_codex":0.00007190365,"about_ca_topic_score_gemma":0.000012205785,"teacher_disagreement_score":0.96138525,"about_ca_system_score_codex":0.000402834,"about_ca_system_score_gemma":0.00034024863,"threshold_uncertainty_score":0.9997537},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.35771277002683183,"score_gpt":0.3531140666372869,"score_spread":0.004598703389544934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951455820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3627128,0.000050042927,0.634823,0.00017668188,0.0005664622,0.00052043214,0.0000569374,0.00007094208,0.001022694],"genre_scores_gemma":[0.96774024,0.00007363586,0.00070888986,0.000036913007,0.00014400051,0.0000021812339,0.000022362125,0.00003653679,0.03123524],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955888,0.00043253254,0.0005229362,0.0020065706,0.0007186888,0.0007304902],"domain_scores_gemma":[0.9952799,0.001017472,0.00045983252,0.0021909333,0.000625235,0.00042660517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019596217,0.0003926125,0.00076817814,0.0015398198,0.00035331454,0.00034060157,0.004061396,0.0003866181,0.0001854523],"category_scores_gemma":[0.0041886005,0.0003993936,0.00025816986,0.0010387454,0.00024582096,0.0006473802,0.0044573094,0.0019797196,0.00071396556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013912591,0.00010286222,0.000703137,0.0000072250873,0.000018693761,0.00036501404,0.00034939693,0.99187475,0.000005112718,0.0007330445,0.00020765452,0.005493996],"study_design_scores_gemma":[0.0006595529,0.00006169849,0.0020444735,0.000116228686,0.000013030469,0.0000022118643,0.0005580829,0.8280902,0.0000049911137,0.16735654,0.00070814596,0.00038484618],"about_ca_topic_score_codex":0.0004150115,"about_ca_topic_score_gemma":0.0008108923,"teacher_disagreement_score":0.6341141,"about_ca_system_score_codex":0.0004514724,"about_ca_system_score_gemma":0.0003439254,"threshold_uncertainty_score":0.9998458},"labels":[],"label_agreement":null},{"id":"W2952123902","doi":"10.48550/arxiv.1801.01301","title":"Sequential Decision Making with Limited Observation Capability: Application to Wireless Networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lagrangian relaxation; Interval (graph theory); Index (typography); Mathematical optimization; State (computer science); Computation; Computer science; State space; Relaxation (psychology); Markov decision process; Decision maker; Function (biology); Bellman equation; Mathematics; Space (punctuation); Operations research; Algorithm; Markov process; Statistics","score_opus":0.1943918856240933,"score_gpt":0.31734796998432135,"score_spread":0.12295608436022806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952123902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42517194,0.000008556496,0.5734911,0.000057062298,0.00027700976,0.00075345405,0.000020347748,0.00009483079,0.00012572251],"genre_scores_gemma":[0.99044704,0.00002491574,0.008333908,0.0001086726,0.00037643468,0.000011647448,0.000053299835,0.00004836178,0.0005956877],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99492264,0.00039418935,0.0006167132,0.0024979305,0.0009403908,0.00062811875],"domain_scores_gemma":[0.9929562,0.0014000762,0.00060304755,0.002564424,0.0021532432,0.0003229632],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021370153,0.00043964086,0.0005856728,0.00081051595,0.00041182747,0.00040452622,0.0024378346,0.00050470646,0.00015594871],"category_scores_gemma":[0.0008946834,0.00039900694,0.00018942406,0.0033605606,0.00035749192,0.00058567955,0.0022451354,0.00082626345,0.00036204752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007480007,0.00007434975,0.012821356,0.0000129571135,0.00004188156,0.000056839166,0.000119130695,0.94862473,0.00002917451,0.0007763018,0.00045560455,0.036239695],"study_design_scores_gemma":[0.00045558202,0.00014828329,0.014071888,0.0001714833,0.000045035154,0.0000038809067,0.00018001461,0.92932457,0.00007480515,0.054051023,0.0009794375,0.0004939793],"about_ca_topic_score_codex":0.00012632507,"about_ca_topic_score_gemma":0.00067971874,"teacher_disagreement_score":0.56527513,"about_ca_system_score_codex":0.0007729356,"about_ca_system_score_gemma":0.0003073069,"threshold_uncertainty_score":0.99984616},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.1870917374975287,"score_gpt":0.38669317927830393,"score_spread":0.19960144178077524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952908320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2693606,0.00018236,0.72045386,0.0016823428,0.001244753,0.0024288935,0.0022331101,0.00014986633,0.0022642056],"genre_scores_gemma":[0.96677417,0.000018649907,0.023112047,0.000031741623,0.0003185915,0.000015187366,0.00036313818,0.000054633896,0.009311835],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99515116,0.00019080627,0.0005181239,0.0011708314,0.0022422024,0.00072684645],"domain_scores_gemma":[0.994529,0.0008812545,0.0009923559,0.0014672356,0.0017499449,0.00038020144],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001154332,0.0004317666,0.0008945831,0.00071826106,0.0007386587,0.00026159376,0.0026082976,0.00041247328,0.00060545944],"category_scores_gemma":[0.00065151165,0.0004055002,0.00033790123,0.00075337326,0.0007522317,0.0009925504,0.0012296448,0.0006247593,0.000068648864],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.023253435,0.0063201664,0.105533116,0.011247755,0.004771782,0.0020230135,0.15869612,0.041197818,0.002008117,0.006427559,0.11057096,0.52795017],"study_design_scores_gemma":[0.022890553,0.0045404453,0.41918752,0.0047150906,0.0023203096,0.00029145787,0.0850728,0.10003365,0.0016662675,0.15085647,0.19978614,0.008639302],"about_ca_topic_score_codex":0.00010553073,"about_ca_topic_score_gemma":0.00056490145,"teacher_disagreement_score":0.69741356,"about_ca_system_score_codex":0.00020486812,"about_ca_system_score_gemma":0.0008226739,"threshold_uncertainty_score":0.99983966},"labels":[],"label_agreement":null},{"id":"W2952938032","doi":"10.48550/arxiv.1110.6755","title":"PAC-Bayes-Bernstein Inequality for Martingales and its Application to\\n Multiarmed Bandits","year":2011,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Bayes' theorem; Computer science; Inequality; Mathematical optimization; Interdependence; Artificial intelligence; Mathematics; Bayesian probability","score_opus":0.27802706403055605,"score_gpt":0.3265386299181593,"score_spread":0.04851156588760325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952938032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36240378,0.00015399825,0.6322049,0.00019910524,0.000453447,0.0037272102,0.00039524265,0.00009723548,0.0003650946],"genre_scores_gemma":[0.9909636,0.00046460106,0.0021657986,0.000084288586,0.00027029202,0.000057433885,0.00005926019,0.000077703524,0.005857027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9914093,0.0008484653,0.0012975484,0.0043109525,0.0007564072,0.0013773526],"domain_scores_gemma":[0.9900946,0.0030407708,0.0012290888,0.0022296773,0.0021785595,0.0012273235],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048077577,0.00090755924,0.0012875157,0.0011441017,0.0009570891,0.0003026016,0.0025786224,0.0008109635,0.0003645751],"category_scores_gemma":[0.0045077805,0.0009572697,0.00047397395,0.0020526422,0.0006373525,0.00095282635,0.0034345493,0.0010271372,0.00079152547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015120915,0.0039478852,0.06876649,0.0030195299,0.0017634272,0.0006540622,0.0135225775,0.47328186,0.010949769,0.12161785,0.002445239,0.28491038],"study_design_scores_gemma":[0.004117868,0.00069034647,0.021276493,0.00031928014,0.00026749293,0.000010351362,0.0017478438,0.7933979,0.0082725,0.15816604,0.00949316,0.002240725],"about_ca_topic_score_codex":0.00029548144,"about_ca_topic_score_gemma":0.0004232664,"teacher_disagreement_score":0.6300391,"about_ca_system_score_codex":0.00051110185,"about_ca_system_score_gemma":0.00046706758,"threshold_uncertainty_score":0.99998647},"labels":[],"label_agreement":null},{"id":"W2954365962","doi":"10.48550/arxiv.1806.05819","title":"BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Learning to rank; Computer science; Ranking (information retrieval); Regret; Rank (graph theory); Online learning; Relevance (law); Quality (philosophy); Base (topology); Information retrieval; Machine learning; Artificial intelligence; World Wide Web; Mathematics","score_opus":0.21393704804264105,"score_gpt":0.332489253193239,"score_spread":0.11855220515059797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954365962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5069759,0.00005415,0.4865701,0.00045632003,0.00091702683,0.000777624,0.00013084385,0.00021969498,0.0038983566],"genre_scores_gemma":[0.9473605,0.00016212948,0.003728879,0.00025573839,0.0007854779,0.0000027279941,0.000076082084,0.00008717374,0.047541287],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99287117,0.00071768835,0.0008993752,0.0031453106,0.0011472026,0.0012192534],"domain_scores_gemma":[0.9924526,0.0014580257,0.00064129167,0.002782941,0.0017996199,0.0008654997],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024332656,0.00069035316,0.0010795401,0.001485526,0.0006291503,0.00040013957,0.0044929725,0.0006671713,0.0028199393],"category_scores_gemma":[0.0025544453,0.0006842391,0.0005331304,0.003179637,0.00046861,0.0005356717,0.005773919,0.0022102015,0.0074006882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008163798,0.00032115355,0.010495208,0.00005111969,0.00020805284,0.00065242045,0.0009427807,0.9442927,0.00031593954,0.00048594386,0.009590076,0.031828173],"study_design_scores_gemma":[0.0035323007,0.0011801382,0.038523637,0.0004157509,0.00019597607,0.000037140027,0.0037876407,0.6107159,0.00078146614,0.18509817,0.15240812,0.003323732],"about_ca_topic_score_codex":0.0003948399,"about_ca_topic_score_gemma":0.0004946473,"teacher_disagreement_score":0.48284122,"about_ca_system_score_codex":0.00064714294,"about_ca_system_score_gemma":0.0003523028,"threshold_uncertainty_score":0.9995609},"labels":[],"label_agreement":null},{"id":"W2957302152","doi":"10.48550/arxiv.1907.05772","title":"Exploration by Optimisation in Partial Monitoring","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Observable; Bounded function; Minimax; Upper and lower bounds; Simple (philosophy); Matching (statistics); Action (physics); Degenerate energy levels; Mathematics; Outcome (game theory); Combinatorics; Mathematical optimization; Computer science; Discrete mathematics; Mathematical economics; Statistics; Physics; Mathematical analysis","score_opus":0.36010931496061505,"score_gpt":0.3313054139223404,"score_spread":0.028803901038274626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2957302152","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5638228,0.00006179441,0.43415442,0.00010162356,0.0009267743,0.00045043687,0.00003471913,0.00005263921,0.00039476834],"genre_scores_gemma":[0.9948958,0.00019559605,0.00030860674,0.000006824794,0.00018644556,0.0000031932063,0.00004700001,0.000012699044,0.004343795],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971491,0.0003390717,0.00040266867,0.0012036494,0.00053807325,0.00036743956],"domain_scores_gemma":[0.99776405,0.00064361125,0.00031703105,0.0008253345,0.00032320622,0.00012678446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012230484,0.0002318711,0.00034948988,0.00045707612,0.00009115757,0.00021161042,0.0011389839,0.00031311208,0.0001623404],"category_scores_gemma":[0.0005913803,0.00022075938,0.00012433702,0.0010154028,0.00007166098,0.0010779863,0.0009264612,0.0007034214,0.00050763076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070855574,0.000051610412,0.015713552,0.000007149711,0.000009991618,0.00004561054,0.00017695698,0.9788988,0.00017656117,0.00015567224,0.00048328313,0.004209925],"study_design_scores_gemma":[0.000848387,0.00006532043,0.0034260678,0.00008353499,0.0000147879155,7.1687873e-7,0.0013891391,0.93929595,0.0030154237,0.048941437,0.0024109005,0.0005083657],"about_ca_topic_score_codex":0.00015757985,"about_ca_topic_score_gemma":0.00003888725,"teacher_disagreement_score":0.43384582,"about_ca_system_score_codex":0.00047738606,"about_ca_system_score_gemma":0.00014763193,"threshold_uncertainty_score":0.9002306},"labels":[],"label_agreement":null},{"id":"W2962856402","doi":"10.1093/ej/uez043","title":"Learning While Experimenting","year":2019,"lang":"en","type":"article","venue":"The Economic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"","keywords":"Pessimism; State (computer science); Computer science; Epistemology","score_opus":0.09921364006409483,"score_gpt":0.4137674019392119,"score_spread":0.3145537618751171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962856402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9759886,0.00021334404,0.0026972627,0.0007422893,0.0011206502,0.00008840105,6.5445613e-7,0.0000142000235,0.019134546],"genre_scores_gemma":[0.97881734,0.000025187925,0.0002564045,0.000053185606,0.0005655125,0.0000017145318,1.7078604e-7,0.00001141138,0.02026909],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99840224,0.00022803387,0.00042267027,0.00019902649,0.0004260319,0.00032197215],"domain_scores_gemma":[0.9983382,0.00091141986,0.0002740782,0.0003225175,0.000065003165,0.00008877888],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0049281116,0.00007714443,0.00016054173,0.00012858208,0.00040521534,0.00059094816,0.0009787154,0.000026388634,0.010377052],"category_scores_gemma":[0.0003669422,0.000044554366,0.00009910657,0.00009224869,0.00005866191,0.0005199966,0.00020934007,0.00056600216,0.013800932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017301254,0.000039461025,0.045860313,0.0000035970122,0.00011036089,0.000035726724,0.010553236,0.5602634,0.0046778526,0.0017894178,0.028229818,0.34826383],"study_design_scores_gemma":[0.003715826,0.0005304133,0.013809472,0.000048226382,0.000011580143,0.001481663,0.045538228,0.24624975,0.008571652,0.09669404,0.5826186,0.00073057384],"about_ca_topic_score_codex":0.000004862438,"about_ca_topic_score_gemma":0.000001555827,"teacher_disagreement_score":0.55438876,"about_ca_system_score_codex":0.00019087591,"about_ca_system_score_gemma":0.00012550992,"threshold_uncertainty_score":0.9905276},"labels":[],"label_agreement":null},{"id":"W2962980921","doi":"","title":"TopRank: A practical algorithm for online stochastic ranking","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Generality; Generalization; Learning to rank; Regret; Online algorithm; sort; Ranking (information retrieval); Rank (graph theory); Machine learning; Algorithm; Artificial intelligence; Sorting algorithm; Theoretical computer science; Sorting; Mathematics; Information retrieval","score_opus":0.18174090392477427,"score_gpt":0.48522840909620396,"score_spread":0.3034875051714297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962980921","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017750826,0.00008006848,0.9949054,0.00071137585,0.001210475,0.0008691658,0.00009211199,0.00014625766,0.00021006836],"genre_scores_gemma":[0.84880847,0.0000017589306,0.14324386,0.0009994168,0.0031677366,0.00034436793,0.00014065515,0.00004753401,0.0032461754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99570656,0.00012312362,0.0012662414,0.00032127136,0.00206441,0.00051841117],"domain_scores_gemma":[0.9946969,0.0011129298,0.00070073514,0.0003743501,0.0029484967,0.0001665964],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002402772,0.00020129468,0.00034809887,0.00047649196,0.00064036204,0.0016438541,0.0005254372,0.00012877588,0.000051248902],"category_scores_gemma":[0.0049288827,0.00014716134,0.00008879824,0.0010136756,0.00020815153,0.0062218895,0.00011024469,0.00025711826,0.00024066691],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069097856,0.00003278702,0.000006818028,0.00005538555,0.000008309825,0.000001346149,0.0008662914,0.003440154,0.00002942876,0.00010776719,0.0030376532,0.992345],"study_design_scores_gemma":[0.0007786024,0.00018165015,0.000050771338,0.000060911625,0.0000065543186,0.00011871977,0.001333446,0.9296043,0.00008781325,0.0008365278,0.066767186,0.00017354815],"about_ca_topic_score_codex":0.000010627338,"about_ca_topic_score_gemma":0.000004895153,"teacher_disagreement_score":0.9921714,"about_ca_system_score_codex":0.000082153965,"about_ca_system_score_gemma":0.00022715855,"threshold_uncertainty_score":0.9993925},"labels":[],"label_agreement":null},{"id":"W2963004721","doi":"10.1145/3178876.3186075","title":"Online Compact Convexified Factorization Machine","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Machine learning; Regret; Artificial intelligence; Online machine learning; Feature (linguistics); Online learning; Projection (relational algebra); Convex optimization; Algorithm; Active learning (machine learning); Regular polygon; Mathematics","score_opus":0.24648509767850507,"score_gpt":0.5073324829073448,"score_spread":0.2608473852288397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963004721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038770836,0.00002973781,0.94413966,0.0014972874,0.00059525593,0.00020019597,0.00007532622,0.00012536615,0.014566347],"genre_scores_gemma":[0.9765329,0.0000048350735,0.0029909192,0.0002510541,0.00037687068,8.364476e-7,0.00003145733,0.00001102047,0.01980015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731356,0.000116140036,0.00038910206,0.0003787902,0.0015216296,0.00028075022],"domain_scores_gemma":[0.9977243,0.0007225429,0.00009585617,0.0005406756,0.0007583366,0.00015831568],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008216504,0.000109536195,0.00019543734,0.00024937312,0.00016827059,0.00015925792,0.0006274947,0.00005404998,0.010833728],"category_scores_gemma":[0.0024486464,0.00006838685,0.000050427236,0.0009448343,0.00024094917,0.00037737426,0.00009988046,0.0001327366,0.0028528306],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067296595,0.0019337251,0.09533721,0.000012180876,0.00013947759,0.00006036566,0.002401282,0.0013942311,0.025565922,0.013653069,0.22563434,0.6331952],"study_design_scores_gemma":[0.0020296532,0.001041532,0.17401396,0.000010729704,0.0000068066242,0.000019603674,0.00087510765,0.29331273,0.031112919,0.085657485,0.41133472,0.00058473076],"about_ca_topic_score_codex":0.0000758667,"about_ca_topic_score_gemma":0.0001477333,"teacher_disagreement_score":0.94114876,"about_ca_system_score_codex":0.0000412864,"about_ca_system_score_gemma":0.000055607976,"threshold_uncertainty_score":0.99792355},"labels":[],"label_agreement":null},{"id":"W2963004847","doi":"","title":"Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Thompson sampling; Asymptotically optimal algorithm; Index (typography); Frequentist inference; Gaussian; Mathematical optimization; Computer science; Mathematics; Mathematical economics; Bayesian probability; Statistics; Artificial intelligence; Bayesian inference","score_opus":0.2738514103519363,"score_gpt":0.45927265146056295,"score_spread":0.18542124110862668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963004847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0753321,0.000037674796,0.92131346,0.0005330324,0.00024188489,0.00044418257,0.00009442045,0.000055432098,0.0019478335],"genre_scores_gemma":[0.97462237,0.000029716555,0.00037805794,0.000028148079,0.00005332951,0.00004372451,0.000004959138,0.000020184485,0.024819486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588895,0.0010593417,0.00062012405,0.00067865435,0.0012905984,0.00046234962],"domain_scores_gemma":[0.98563784,0.011719859,0.00055931014,0.0009901285,0.00096462975,0.00012820362],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051325406,0.00021431445,0.0005271848,0.0006949424,0.00031508514,0.00012213887,0.0015011723,0.00015200103,0.0014449119],"category_scores_gemma":[0.030114017,0.000102831495,0.00036620453,0.0017583502,0.00059653015,0.00022018285,0.00022083407,0.0003834568,0.00010473119],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009838894,0.00019100955,0.026225843,0.000011508776,0.0005148713,0.000004701164,0.00087605655,0.041100945,0.0030542715,0.055278964,0.0003487114,0.87140924],"study_design_scores_gemma":[0.0052628336,0.0023309344,0.20755823,0.00036542147,0.00042479415,0.0000021464714,0.005722305,0.47520635,0.01167509,0.27471787,0.015692653,0.0010413965],"about_ca_topic_score_codex":0.0000062992376,"about_ca_topic_score_gemma":0.000036728663,"teacher_disagreement_score":0.9209354,"about_ca_system_score_codex":0.000063679145,"about_ca_system_score_gemma":0.0002685223,"threshold_uncertainty_score":0.9994679},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.24964690891773292,"score_gpt":0.44080407780224784,"score_spread":0.19115716888451492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963110737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012509822,0.000012165003,0.97022104,0.00016940266,0.00014172141,0.00032067366,0.0000035092833,0.000048209477,0.02895819],"genre_scores_gemma":[0.30216414,0.000010412192,0.67380816,0.00014858207,0.00010444137,0.000086735905,0.000014204668,0.000017440563,0.023645857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841624,0.000039263046,0.00032828713,0.00031688862,0.0006913781,0.00020796075],"domain_scores_gemma":[0.998523,0.00031394314,0.0000901382,0.00037953543,0.0006006956,0.00009269524],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012295499,0.00006936734,0.00010893192,0.0002401095,0.00010729244,0.00007059029,0.00041653358,0.000049157785,0.005233518],"category_scores_gemma":[0.0016753011,0.00004942949,0.000054504853,0.0005244887,0.000047939593,0.0005045469,0.000049583203,0.000042730313,0.0001660537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037456304,0.00043642247,0.0037645325,0.000010835032,0.000047742156,0.000010856698,0.0017469419,0.14177139,0.00030220053,0.038050808,0.07334824,0.7401355],"study_design_scores_gemma":[0.00047033865,0.00014940847,0.0018130329,0.0000024921185,0.0000042014085,0.0000046075775,0.00053011643,0.88400745,0.0055299522,0.09690581,0.01041542,0.00016716297],"about_ca_topic_score_codex":0.000018912104,"about_ca_topic_score_gemma":0.000014362826,"teacher_disagreement_score":0.7422361,"about_ca_system_score_codex":0.000026372394,"about_ca_system_score_gemma":0.000054854514,"threshold_uncertainty_score":0.99567586},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5456077650671064,"score_gpt":0.5258773785639367,"score_spread":0.019730386503169717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963246254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007214133,0.000030676085,0.98222834,0.0005493456,0.000060326467,0.00013711704,0.0000749496,0.000056736742,0.009648376],"genre_scores_gemma":[0.5151808,0.0000015643162,0.4806665,0.000047179474,0.000072488,0.000005994982,0.000108261076,0.000012359767,0.003904827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99624133,0.0001303891,0.00030232104,0.0005509907,0.0024954393,0.00027955617],"domain_scores_gemma":[0.9969198,0.0010931971,0.00007411904,0.0011753764,0.00043470672,0.0003027643],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023757068,0.000103189814,0.00017052476,0.0001379741,0.00008311386,0.0004868607,0.0013179301,0.00003723351,0.00090935663],"category_scores_gemma":[0.0024114237,0.00005692643,0.000008376201,0.0005576206,0.00023016798,0.0009678762,0.0003861863,0.00014002853,0.00138043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008267559,0.0005047561,0.0061068707,0.0000144385,0.00008397733,0.00043506312,0.0009682518,0.31787467,0.000042402415,0.042338293,0.120052025,0.5107525],"study_design_scores_gemma":[0.00044908316,0.000207464,0.0006703534,0.0000028487316,0.0000037412217,0.000023730352,0.0020361037,0.879962,0.00004915238,0.11401922,0.0024614292,0.000114818075],"about_ca_topic_score_codex":0.000040888946,"about_ca_topic_score_gemma":0.00007351554,"teacher_disagreement_score":0.56208736,"about_ca_system_score_codex":0.00003186176,"about_ca_system_score_gemma":0.00036189507,"threshold_uncertainty_score":0.9993971},"labels":[],"label_agreement":null},{"id":"W2963280733","doi":"","title":"DCM bandits: learning to rank with multiple clicks","year":2016,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Logarithm; Online learning; Matching (statistics); Learning to rank; Rank (graph theory); Web page; Machine learning; Upper and lower bounds; Artificial intelligence; World Wide Web; Mathematics; Ranking (information retrieval); Statistics","score_opus":0.11166585086489081,"score_gpt":0.4292146443664688,"score_spread":0.31754879350157794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963280733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20436738,0.000033813692,0.7331016,0.022027893,0.0007950065,0.000557915,0.00006453379,0.00035463666,0.03869724],"genre_scores_gemma":[0.95916176,0.000028210654,0.002240046,0.00023546236,0.0002477938,0.000043127042,0.000014966269,0.000035526522,0.03799311],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948521,0.000421174,0.0005279975,0.00088537775,0.0028174084,0.0004959271],"domain_scores_gemma":[0.9952353,0.0027191525,0.0002707114,0.00039498415,0.0010973716,0.00028247197],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017496689,0.00027286418,0.00032211252,0.00071473833,0.00032610568,0.00043551612,0.0013845311,0.00008123818,0.0070375553],"category_scores_gemma":[0.011830646,0.00015431292,0.000091726244,0.0004633946,0.0001367362,0.0005363576,0.00034158575,0.0007819473,0.0043527186],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018666248,0.00012839625,0.24843355,0.0000034765496,0.00010892278,0.00013304081,0.0010455672,0.04959701,0.009946195,0.005239718,0.00082223344,0.6826753],"study_design_scores_gemma":[0.00767687,0.00306478,0.066471964,0.00056344445,0.000014392203,0.000097149394,0.001890168,0.31962556,0.005362794,0.01147492,0.5823237,0.0014342811],"about_ca_topic_score_codex":0.00008716188,"about_ca_topic_score_gemma":0.00016292618,"teacher_disagreement_score":0.75479436,"about_ca_system_score_codex":0.00016280886,"about_ca_system_score_gemma":0.00011446229,"threshold_uncertainty_score":0.9964931},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.13487576751992256,"score_gpt":0.4272213443219531,"score_spread":0.29234557680203055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963582321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069055825,0.00083291164,0.9094979,0.002391006,0.0019705563,0.0026182488,0.000030956173,0.0003608538,0.013241702],"genre_scores_gemma":[0.9941895,0.000021702643,0.0005779187,0.000078127145,0.00017543559,0.00010946272,0.000029425826,0.000015743746,0.0048026624],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964268,0.00007328281,0.0011378294,0.00029831805,0.0015475265,0.0005162232],"domain_scores_gemma":[0.9961886,0.0003914144,0.0015260357,0.00059548585,0.0011138516,0.00018460338],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032634465,0.00022299796,0.00036419916,0.00040685132,0.0032439823,0.006460275,0.0007948293,0.00012964143,0.000014071214],"category_scores_gemma":[0.004696167,0.00016559073,0.00007012072,0.0002666835,0.00024910748,0.009944907,0.00024456237,0.00032197026,0.00005600717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017898504,0.0000123820255,0.0046629338,0.0008027201,0.00002379052,0.0000042075853,0.005301728,0.10961309,0.00011228934,0.0016922558,0.0018171503,0.87577844],"study_design_scores_gemma":[0.0008668543,0.00016520923,0.0011149321,0.00017037777,0.0000067304995,0.000040622483,0.0038048448,0.90072495,0.00015080368,0.0009675877,0.091745526,0.00024156607],"about_ca_topic_score_codex":0.00006792674,"about_ca_topic_score_gemma":0.000006990971,"teacher_disagreement_score":0.9251337,"about_ca_system_score_codex":0.00012836303,"about_ca_system_score_gemma":0.00014429497,"threshold_uncertainty_score":0.99805367},"labels":[],"label_agreement":null},{"id":"W2963735997","doi":"10.1609/aaai.v33i01.33013943","title":"Meta-Descent for Online, Continual Prediction","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Stochastic gradient descent; Gradient descent; Range (aeronautics); Mathematical optimization; Hessian matrix; Artificial intelligence; Machine learning; Algorithm; Mathematics; Applied mathematics; Artificial neural network","score_opus":0.3855954766612691,"score_gpt":0.4881601340619269,"score_spread":0.10256465740065779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963735997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08736714,0.00022508702,0.9016883,0.0017648849,0.0013424527,0.0018677074,0.0005308857,0.0001628696,0.0050506745],"genre_scores_gemma":[0.54274327,0.000023369894,0.094509125,0.00056241394,0.00055319344,0.00016710612,0.00006993591,0.000041203308,0.36133036],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99735636,0.00006865978,0.00043739993,0.00046172622,0.0013830637,0.00029278555],"domain_scores_gemma":[0.9972679,0.0014240278,0.000091938375,0.00049566285,0.00061955774,0.00010093176],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016889342,0.000103206985,0.00031865932,0.00017940586,0.00006310724,0.00012315363,0.00048474746,0.000056635035,0.003967132],"category_scores_gemma":[0.0011914836,0.000060028426,0.00023081368,0.00036274132,0.00004466866,0.0004069346,0.00010343226,0.000104820065,0.0010118566],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095203926,0.001331504,0.022526773,0.000041531603,0.0022732883,0.000010559988,0.00057515345,0.010713884,0.007033982,0.010836526,0.29680964,0.6468951],"study_design_scores_gemma":[0.0023453063,0.0006851796,0.016001709,0.0000047819535,0.00016310634,0.00000816891,0.0011304286,0.12999536,0.005526801,0.034135446,0.8097176,0.0002861376],"about_ca_topic_score_codex":0.000008818352,"about_ca_topic_score_gemma":0.000028450859,"teacher_disagreement_score":0.80717915,"about_ca_system_score_codex":0.000035815672,"about_ca_system_score_gemma":0.000054293665,"threshold_uncertainty_score":0.999766},"labels":[],"label_agreement":null},{"id":"W2963812988","doi":"10.1016/j.tcs.2013.09.024","title":"Adaptive and optimal online linear regression on <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si1.gif\" overflow=\"scroll\"><mml:msup><mml:mrow><mml:mi>ℓ</mml:mi></mml:mrow><mml:mrow><mml:mn>1</mml:mn></mml:mrow></mml:msup></mml:math>-balls","year":2013,"lang":"lv","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Agence Nationale de la Recherche; European Commission","keywords":"Regret; Ball (mathematics); Dimension (graph theory); Mathematics; Linear regression; Minimax; Algorithm; Discrete mathematics; Applied mathematics; Computer science; Combinatorics; Mathematical optimization; Statistics; Mathematical analysis","score_opus":0.030323114225871677,"score_gpt":0.2978322730377435,"score_spread":0.2675091588118718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963812988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7423239,0.00084274367,0.049962673,0.0021214825,0.0036056247,0.00012085372,0.00036755172,0.0002661235,0.2003891],"genre_scores_gemma":[0.9604973,0.0005974955,0.034352537,0.001479082,0.0018789726,0.00032749743,0.00018370392,0.00033229828,0.00035108515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9853652,0.00074869033,0.0018703007,0.0029215373,0.00604317,0.003051094],"domain_scores_gemma":[0.98852855,0.0047254274,0.0013345283,0.0029692403,0.00055180956,0.0018904253],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.004501185,0.0008997749,0.00046309218,0.0007820461,0.0021571508,0.0026426446,0.004644618,0.0015271106,0.19913352],"category_scores_gemma":[0.0039457595,0.0012827392,0.0010463218,0.0023481478,0.009512961,0.0027092071,0.0054641934,0.0022327474,0.0046182447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014822608,0.00044271356,0.000005229841,0.00021426006,0.00029136,0.0011994872,0.0017195604,0.0054405625,0.0010561317,0.9080134,0.06245868,0.017676355],"study_design_scores_gemma":[0.0012018174,0.002882975,0.00011604575,0.00077032397,0.00018344972,0.0007554562,0.0008804389,0.64001703,0.35039315,0.0009020537,0.00094873115,0.000948529],"about_ca_topic_score_codex":0.00039672476,"about_ca_topic_score_gemma":0.00009751965,"teacher_disagreement_score":0.90711135,"about_ca_system_score_codex":0.00003083574,"about_ca_system_score_gemma":0.001832093,"threshold_uncertainty_score":0.9997691},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.27494721211460194,"score_gpt":0.4837384434734039,"score_spread":0.20879123135880195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964007796","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034978574,0.0001330417,0.9798943,0.00133653,0.0044421954,0.0007228196,0.000052353313,0.00012428564,0.009796612],"genre_scores_gemma":[0.93435425,0.0000024198841,0.010750596,0.00020840416,0.0018685975,0.00017731162,0.000029376602,0.000052626292,0.05255643],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952238,0.00013201316,0.0005732274,0.00065792503,0.0028078225,0.00060521817],"domain_scores_gemma":[0.99437994,0.002688484,0.00014775878,0.00079336116,0.001478438,0.000511998],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038409662,0.0001933882,0.00038570323,0.00031955662,0.00023554522,0.00043655644,0.0011116769,0.00013729808,0.0005143999],"category_scores_gemma":[0.013217187,0.00013030168,0.00013338524,0.0008715993,0.00023490672,0.00056912267,0.00023080262,0.00020897943,0.00088985736],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008359877,0.00025712553,0.00030989,0.000007616881,0.000048286667,0.000024288815,0.0008265041,0.0034158374,0.0001465249,0.05527543,0.919773,0.01907953],"study_design_scores_gemma":[0.0035426167,0.00055423786,0.000071945506,0.000007296758,0.000007738437,0.000014987166,0.0006039245,0.0231155,0.000782885,0.77509886,0.19591372,0.00028629924],"about_ca_topic_score_codex":0.000019405172,"about_ca_topic_score_gemma":0.000024889508,"teacher_disagreement_score":0.9691437,"about_ca_system_score_codex":0.00016892141,"about_ca_system_score_gemma":0.0004290447,"threshold_uncertainty_score":0.99988806},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.26156167212854786,"score_gpt":0.4801871304299516,"score_spread":0.21862545830140373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964072175","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00457761,0.00012492033,0.3452262,0.0033178756,0.0012081923,0.0011441488,0.00009283567,0.00016227122,0.64414597],"genre_scores_gemma":[0.027838284,0.000010532452,0.010270418,0.0001321643,0.00015266881,0.00004882641,0.00001533415,0.00002042039,0.9615114],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972905,0.0003223597,0.00037704318,0.00045692362,0.0012274088,0.00032579672],"domain_scores_gemma":[0.9973278,0.00083126663,0.000109524604,0.00046207316,0.0009614637,0.00030789498],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00176153,0.000111720525,0.00022452227,0.00020287614,0.0020496363,0.0030745424,0.0012210202,0.000067722525,0.0026639346],"category_scores_gemma":[0.004271632,0.00008916679,0.00005967616,0.00433756,0.00010305418,0.00071593426,0.0007271202,0.00038610824,0.0007976955],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011052306,0.00022028307,0.00008127338,2.780211e-7,0.000027819653,0.000009491454,0.00020893746,0.0761482,0.000016070271,0.00005584281,0.9133675,0.009753751],"study_design_scores_gemma":[0.0016698599,0.00040905387,0.00078958337,0.0000065866666,0.0000090947715,0.000055111064,0.010136779,0.04472781,0.00012367034,0.07783684,0.8639784,0.0002572083],"about_ca_topic_score_codex":0.002537008,"about_ca_topic_score_gemma":0.004360516,"teacher_disagreement_score":0.33495578,"about_ca_system_score_codex":0.00022117996,"about_ca_system_score_gemma":0.00049208855,"threshold_uncertainty_score":0.9999803},"labels":[],"label_agreement":null},{"id":"W2964096186","doi":"","title":"{Bayesian Multi-Scale Optimistic Optimization}","year":2014,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayesian optimization; Regret; Mathematical optimization; Computer science; Gaussian process; Global optimization; Optimization problem; Convergence (economics); Derivative-free optimization; Test functions for optimization; Continuous optimization; Random optimization; Bayesian probability; Function (biology); Gaussian; Multi-swarm optimization; Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.06710112123898992,"score_gpt":0.3386387153824301,"score_spread":0.2715375941434402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964096186","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005143179,0.00002126576,0.9545676,0.0011505391,0.00010453524,0.0006277935,0.0002765376,0.00010378456,0.038004752],"genre_scores_gemma":[0.3262738,0.0009228276,0.620073,0.00004604773,0.00014208675,7.694108e-7,0.0001736768,0.00007567092,0.052292097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99118865,0.001975413,0.00040963278,0.0013675928,0.0036799284,0.0013787854],"domain_scores_gemma":[0.9913243,0.00357488,0.00035083314,0.0016598257,0.0021040533,0.0009860734],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.0045663156,0.00035049938,0.00073308556,0.0027353854,0.0021124163,0.00016381279,0.004792875,0.0002264005,0.0020298054],"category_scores_gemma":[0.0024740633,0.0003987274,0.000399883,0.0036789435,0.002736361,0.0014415833,0.0026693626,0.0011653822,0.00013540013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004990942,0.0024525218,0.03353444,0.00024447226,0.0005116709,0.0010741068,0.010387807,0.7149705,0.0015097846,0.014275748,0.034180027,0.18186794],"study_design_scores_gemma":[0.0027045878,0.0005535039,0.005351181,0.000052115665,0.000027401431,0.000013340904,0.013260772,0.71786845,0.000051827185,0.00600511,0.25366876,0.00044295288],"about_ca_topic_score_codex":0.00045682426,"about_ca_topic_score_gemma":0.0013142109,"teacher_disagreement_score":0.33449456,"about_ca_system_score_codex":0.00038758246,"about_ca_system_score_gemma":0.00053469045,"threshold_uncertainty_score":0.99997765},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.39633834779057253,"score_gpt":0.5102858031466518,"score_spread":0.11394745535607931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964240248","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102221616,0.00029324892,0.41111216,0.0029173545,0.012425034,0.0006130665,0.00001484222,0.0003756171,0.47002706],"genre_scores_gemma":[0.98383963,0.0000015801285,0.0017924444,0.00007506541,0.00050063647,0.000006790435,0.0000012313654,0.000010194188,0.013772426],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962918,0.00014138555,0.0003221099,0.0003535793,0.0025656635,0.000325472],"domain_scores_gemma":[0.99752027,0.0009351509,0.00006085712,0.0004626836,0.0006488671,0.00037219093],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003282182,0.00008906741,0.00018415746,0.00022765974,0.00009932084,0.00024648,0.00071391586,0.000059345795,0.0008635415],"category_scores_gemma":[0.008257305,0.000058387526,0.00005190054,0.0008379899,0.00008931689,0.00050534576,0.00023521438,0.00015110969,0.0039841686],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024661954,0.00023738472,0.010586821,0.0000026299658,0.00003386574,0.00025646866,0.0018432208,0.0023233006,0.0003147748,0.09369286,0.73198247,0.1584796],"study_design_scores_gemma":[0.0017328331,0.00016850432,0.0008536639,0.000002969629,0.0000019670756,0.000028437415,0.0011842367,0.010107745,0.003145239,0.62927055,0.3532938,0.00021003264],"about_ca_topic_score_codex":0.000036062967,"about_ca_topic_score_gemma":0.000013054626,"teacher_disagreement_score":0.881618,"about_ca_system_score_codex":0.00008860133,"about_ca_system_score_gemma":0.00014594282,"threshold_uncertainty_score":0.99679136},"labels":[],"label_agreement":null},{"id":"W2964278219","doi":"","title":"Thompson Sampling for Combinatorial Semi-Bandits.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Thompson sampling; Matroid; Oracle; Sampling (signal processing); Mathematics; Mathematical optimization; Independence (probability theory); Computer science; Combinatorics; Statistics","score_opus":0.27226303544098335,"score_gpt":0.5115727209194741,"score_spread":0.2393096854784908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964278219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038872704,0.000056435245,0.876223,0.007860162,0.009188243,0.0006977632,0.0001550353,0.0002613452,0.06668529],"genre_scores_gemma":[0.9862724,0.000014032949,0.003384513,0.00015998534,0.0018837713,0.000038157235,0.00006253165,0.000026281514,0.008158306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99634326,0.00018484305,0.00050579006,0.0006658003,0.0019172358,0.00038306578],"domain_scores_gemma":[0.99563515,0.0018819023,0.000279973,0.00030987253,0.0017614235,0.00013167779],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021138808,0.00019870936,0.00026550225,0.00034214492,0.00045254364,0.0005660841,0.0012546323,0.00009751853,0.0038150046],"category_scores_gemma":[0.009208562,0.0001597294,0.00012639661,0.00032198554,0.00018875368,0.0003482532,0.00022051306,0.00055657147,0.0008005794],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030121196,0.00039690558,0.01931644,0.000014959184,0.0002164804,0.00002651023,0.0018656986,0.012813391,0.009623867,0.46602952,0.0053274124,0.48135668],"study_design_scores_gemma":[0.0017921856,0.0008651336,0.001680142,0.0000543652,0.0000053807485,0.000009800691,0.0003037155,0.53743833,0.0022101968,0.19962019,0.2556994,0.00032119278],"about_ca_topic_score_codex":0.000027407481,"about_ca_topic_score_gemma":0.000026300266,"teacher_disagreement_score":0.94739974,"about_ca_system_score_codex":0.0001156936,"about_ca_system_score_gemma":0.000112909904,"threshold_uncertainty_score":0.9999774},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3686539785191696,"score_gpt":0.33170251449792354,"score_spread":0.03695146402124605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964315724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2549816,0.00006886682,0.7018714,0.00041935607,0.0012029954,0.0005470373,0.00013561755,0.00025237617,0.040520784],"genre_scores_gemma":[0.9783825,0.00013149937,0.00016473011,0.000058362282,0.00021685145,0.0000027348597,0.00000903415,0.00004089314,0.020993374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953985,0.00049913663,0.0004657879,0.0020296997,0.0009007686,0.0007061084],"domain_scores_gemma":[0.99335766,0.0025025543,0.00043674267,0.0027079927,0.0006527039,0.00034231922],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013371932,0.0004846768,0.0006414422,0.0009720168,0.00029255197,0.00047441025,0.00387229,0.00042879372,0.0016688993],"category_scores_gemma":[0.0011390666,0.00036618134,0.00040682807,0.0009644918,0.0005405338,0.0008058205,0.002468818,0.0010674851,0.004528654],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008831482,0.00044675425,0.0014673795,0.000054138058,0.0002823452,0.0023632916,0.00093657034,0.5008511,0.000120695055,0.4503167,0.019491673,0.022786215],"study_design_scores_gemma":[0.00063201407,0.00012683662,0.0006178094,0.00010440422,0.000018391042,0.0000023453665,0.0016008659,0.016030233,0.00022459151,0.9749893,0.005144272,0.00050895044],"about_ca_topic_score_codex":0.000033870747,"about_ca_topic_score_gemma":0.00003337224,"teacher_disagreement_score":0.72340095,"about_ca_system_score_codex":0.00037060436,"about_ca_system_score_gemma":0.00046909825,"threshold_uncertainty_score":0.999879},"labels":[],"label_agreement":null},{"id":"W2965415665","doi":"10.24963/ijcai.2019/532","title":"Learning Multi-Objective Rewards and User Utility Function in Contextual Bandits for Personalized Ranking","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National University of Singapore","keywords":"Computer science; Ranking (information retrieval); Weighting; Context (archaeology); Function (biology); Machine learning; Artificial intelligence; Learning to rank","score_opus":0.11000894557218811,"score_gpt":0.4211775392848835,"score_spread":0.3111685937126954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965415665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49254954,0.00014387853,0.5050118,0.00012823625,0.00025958847,0.00095685106,0.000009389687,0.000044391294,0.00089636113],"genre_scores_gemma":[0.9679478,0.000009064954,0.0032615054,0.0000553484,0.000044126908,0.000045818855,0.000004833355,0.000013707984,0.028617801],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99725133,0.0003278431,0.000399301,0.0007073563,0.00094011193,0.000374032],"domain_scores_gemma":[0.99590456,0.003188208,0.000110285866,0.00023141844,0.00047916744,0.000086364795],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004191521,0.00014337499,0.00035250146,0.0003140165,0.00017044965,0.00016140241,0.00020954674,0.00010511249,0.0011061929],"category_scores_gemma":[0.0054978402,0.000105142404,0.000085584834,0.00049145566,0.0001353287,0.00063463685,0.00012954956,0.00031285948,0.00011632898],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056213033,0.0002448171,0.6013199,0.00004834024,0.00008623531,0.000009798107,0.008281542,0.0023065035,0.0027937656,0.0014081432,0.0014830634,0.37639657],"study_design_scores_gemma":[0.015878726,0.0009047494,0.5199004,0.000051100455,0.0000118147655,0.000009450328,0.024686381,0.36177635,0.0009923842,0.0064104632,0.068884626,0.00049357675],"about_ca_topic_score_codex":0.000093661656,"about_ca_topic_score_gemma":0.00027563894,"teacher_disagreement_score":0.5017503,"about_ca_system_score_codex":0.00008149256,"about_ca_system_score_gemma":0.00007791881,"threshold_uncertainty_score":0.99980694},"labels":[],"label_agreement":null},{"id":"W2966286942","doi":"","title":"An Information-Theoretic Approach to Minimax Regret in Partial Monitoring.","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Minimax; Mathematics; Bayesian probability; Mathematical economics; Degenerate energy levels; Mathematical optimization; Computer science; Discrete mathematics; Statistics","score_opus":0.09132089929786394,"score_gpt":0.4067404308935916,"score_spread":0.31541953159572766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966286942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.751332,0.00002024463,0.15902217,0.00031803927,0.0006108609,0.0008161677,0.0000073752362,0.00015623937,0.0877169],"genre_scores_gemma":[0.9940724,0.000006895964,0.002106013,0.000075362535,0.00009129308,0.000054286924,0.000008648612,0.000016230195,0.0035688875],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961051,0.0008623823,0.0005390351,0.0005499312,0.00143089,0.0005126676],"domain_scores_gemma":[0.9969584,0.0013920957,0.0001682867,0.0008757473,0.000360361,0.00024512524],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005651754,0.00019832596,0.00032266075,0.0006974094,0.00012729094,0.00045347423,0.0012643468,0.00012172124,0.00091745646],"category_scores_gemma":[0.0055955853,0.00015602338,0.00005564732,0.00086981064,0.00015552808,0.0010498525,0.00016925987,0.0007193206,0.0056642494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014435031,0.00027789857,0.0342928,0.00002544627,0.000014397443,0.000010416449,0.017578963,0.14282376,0.00070270314,0.34510338,0.0002413623,0.45748538],"study_design_scores_gemma":[0.003543865,0.0034912026,0.07325065,0.0003675493,0.000011261017,0.000020894733,0.06064617,0.38872635,0.005190481,0.4181623,0.04473951,0.0018497626],"about_ca_topic_score_codex":0.000006495758,"about_ca_topic_score_gemma":5.162152e-7,"teacher_disagreement_score":0.4556356,"about_ca_system_score_codex":0.0000885672,"about_ca_system_score_gemma":0.00016375413,"threshold_uncertainty_score":0.9999958},"labels":[],"label_agreement":null},{"id":"W2966820259","doi":"","title":"Problem-dependent Regret Bounds for Online Learning with Feedback Graphs.","year":2019,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Computer science; Online learning; Theoretical computer science; Artificial intelligence; Machine learning; World Wide Web","score_opus":0.1217124348623598,"score_gpt":0.41820771941942625,"score_spread":0.2964952845570664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966820259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6132775,0.00019603437,0.37817386,0.0021209423,0.0007715348,0.003279109,0.00010524586,0.00017271122,0.0019030884],"genre_scores_gemma":[0.9801668,0.000040241925,0.0128747625,0.00011619413,0.00013005822,0.00012535369,0.000042344316,0.000045955465,0.0064583104],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99430704,0.00026551436,0.0012069852,0.0012050467,0.0020728724,0.000942533],"domain_scores_gemma":[0.9950705,0.0025909685,0.0003498766,0.0007972589,0.0009959402,0.0001954597],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035330437,0.00032699425,0.0005571393,0.0007320554,0.000245485,0.00044108668,0.0013466512,0.00016248878,0.00085655466],"category_scores_gemma":[0.0027257863,0.0002369631,0.00015157918,0.0021285051,0.00038099714,0.0005096626,0.00021227228,0.0007616902,0.0007842815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009571567,0.00027911048,0.003943352,0.00002259702,0.000018432396,0.000021917524,0.0011058468,0.59843564,0.000788249,0.009224301,0.00013645818,0.38506693],"study_design_scores_gemma":[0.00040604576,0.0016915739,0.00066541723,0.00017666788,0.000010117503,0.000021242677,0.011161514,0.42944795,0.007196718,0.52970296,0.01876473,0.0007550914],"about_ca_topic_score_codex":0.00034973267,"about_ca_topic_score_gemma":0.0036672016,"teacher_disagreement_score":0.52047867,"about_ca_system_score_codex":0.00024371,"about_ca_system_score_gemma":0.00024290584,"threshold_uncertainty_score":0.99999374},"labels":[],"label_agreement":null},{"id":"W2970168598","doi":"","title":"Surrogate Objectives for Batch Policy Optimization in One-step Decision Making","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Mathematical optimization; Entropy (arrow of time); Artificial intelligence; Multi-armed bandit; Constrained optimization problem; Action selection; Action (physics); Optimization problem; State (computer science); Surrogate model; Principle of maximum entropy; Machine learning; Mathematics; Algorithm; Regret; Psychology","score_opus":0.07992803755470389,"score_gpt":0.42332753069394063,"score_spread":0.34339949313923673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970168598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04015015,0.00013431734,0.95546687,0.00025284223,0.00069229864,0.0016084672,0.000025285874,0.000098161676,0.0015716346],"genre_scores_gemma":[0.98817945,0.0000064738024,0.010975207,0.000110999514,0.00014449428,0.000121842226,0.00002375631,0.000017809089,0.00041998122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995966,0.00014088661,0.0013734791,0.00034863342,0.0017084156,0.00046258175],"domain_scores_gemma":[0.9963411,0.0012083637,0.00072187994,0.0003758853,0.0012745844,0.0000781864],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002499276,0.00019114124,0.0003873786,0.0014216584,0.00023507037,0.0014410364,0.00059575646,0.00014109223,0.000033059983],"category_scores_gemma":[0.003984449,0.00015515578,0.000075036536,0.0021495286,0.00004658812,0.007755655,0.00011759712,0.00020485623,0.00019123295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012704005,0.00001570159,0.0011047606,0.00011211058,0.0000024150404,2.9229872e-7,0.00096010463,0.80060893,0.000025978756,0.00014029363,0.000097184355,0.19680521],"study_design_scores_gemma":[0.000939889,0.00008547748,0.001431157,0.0002959299,0.0000016611317,0.000010606784,0.0022531399,0.9918358,0.000070705886,0.000826301,0.0020697596,0.00017961436],"about_ca_topic_score_codex":0.000050387436,"about_ca_topic_score_gemma":0.000013552235,"teacher_disagreement_score":0.9480293,"about_ca_system_score_codex":0.00030518573,"about_ca_system_score_gemma":0.0002705393,"threshold_uncertainty_score":0.9995956},"labels":[],"label_agreement":null},{"id":"W2970245835","doi":"","title":"Learning Reliable Policies in the Bandit Setting with Application to Adaptive Clinical Trials.","year":2019,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.44409328734001935,"score_gpt":0.5419922742734516,"score_spread":0.0978989869334323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970245835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16495103,0.000009589048,0.795641,0.019598624,0.00091663765,0.0018305739,0.000024670106,0.00006491925,0.016962966],"genre_scores_gemma":[0.9956114,0.000018676612,0.0020687517,0.00073992484,0.00033061812,0.0001282749,0.000008879069,0.000014954544,0.0010785076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930583,0.0012472859,0.0018436974,0.0008766131,0.00256191,0.0004121953],"domain_scores_gemma":[0.9908229,0.0066252914,0.00062331295,0.0006279367,0.0011660195,0.00013454231],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017921032,0.00021829575,0.00050592073,0.00059253257,0.0001499768,0.0006279714,0.0016375167,0.0001038251,0.00088580983],"category_scores_gemma":[0.0139992125,0.00013145668,0.00014583422,0.0010299673,0.00019224004,0.00037060218,0.00020199608,0.00090633304,0.0046868287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011748166,0.0002853914,0.0062386203,0.0000024754613,0.000036073816,0.00002140651,0.0030870645,0.14533226,0.0011094551,0.14681987,0.00047947458,0.69541305],"study_design_scores_gemma":[0.00028606688,0.0022083588,0.017786909,0.00026339464,0.000010310436,0.000021811351,0.028094012,0.7145491,0.008568477,0.21422982,0.0133814085,0.0006003323],"about_ca_topic_score_codex":0.00023772768,"about_ca_topic_score_gemma":0.00034792253,"teacher_disagreement_score":0.8306604,"about_ca_system_score_codex":0.00013775866,"about_ca_system_score_gemma":0.0002203892,"threshold_uncertainty_score":0.99608815},"labels":[],"label_agreement":null},{"id":"W2973807518","doi":"10.1109/access.2024.3510558","title":"Constrained Restless Bandits for Dynamic Scheduling in Cyber-Physical Systems","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Science and Engineering Research Board; Indian Institute of Technology Madras","keywords":"Mathematical optimization; Computer science; Set (abstract data type); Scheduling (production processes); Bellman equation; Observable; Class (philosophy); Mathematics; Artificial intelligence","score_opus":0.18320865466153252,"score_gpt":0.5301487381280565,"score_spread":0.346940083466524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973807518","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52075,0.00069957424,0.4736222,0.0005039757,0.0027793131,0.00088290696,0.00013021627,0.00012758534,0.00050422765],"genre_scores_gemma":[0.99760354,0.000015090371,0.00048904784,0.000020611187,0.00045151665,0.00020562444,0.000008072073,0.0000333273,0.0011731755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965584,0.00015301163,0.0005924147,0.00082288514,0.0013173653,0.000555914],"domain_scores_gemma":[0.99459124,0.004383904,0.00008469858,0.0004992939,0.00029888377,0.00014195523],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019373898,0.00019151719,0.0004224478,0.0006845951,0.00012483106,0.0016916418,0.001411457,0.00010626714,0.00003262601],"category_scores_gemma":[0.0014800894,0.00014388563,0.00013130136,0.0017003957,0.00019211182,0.0012232088,0.00015250142,0.00036001235,0.00021206443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040956523,0.0004391587,0.002817649,0.00064175145,0.00016749087,0.0011091594,0.001963254,0.73379314,0.009008513,0.010467684,0.006410098,0.23277254],"study_design_scores_gemma":[0.00051766523,0.000050209434,0.0008251237,0.00018989136,0.0000064842825,0.000017446582,0.0003013412,0.96702963,0.0008796553,0.027252464,0.002708463,0.00022165249],"about_ca_topic_score_codex":0.000059823826,"about_ca_topic_score_gemma":0.00011209124,"teacher_disagreement_score":0.47685352,"about_ca_system_score_codex":0.00016919822,"about_ca_system_score_gemma":0.00025435223,"threshold_uncertainty_score":0.9993447},"labels":[],"label_agreement":null},{"id":"W2978459918","doi":"10.48550/arxiv.1910.01706","title":"Bounds for Approximate Regret-Matching Algorithms","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Mathematical optimization; Generalization; Matching (statistics); Function (biology); Algorithm; Mathematics; Machine learning; Statistics","score_opus":0.28678316791238206,"score_gpt":0.33104138160431723,"score_spread":0.044258213691935167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978459918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04600183,0.0001335781,0.9473756,0.00016878817,0.0017039645,0.0014732254,0.0003430288,0.00018952442,0.0026104432],"genre_scores_gemma":[0.9377445,0.00014409708,0.011578387,0.00008337736,0.0004206876,0.000011623332,0.00010400433,0.000098987475,0.049814343],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944332,0.00032291637,0.0006872483,0.0026978503,0.00086202176,0.0009967523],"domain_scores_gemma":[0.99266666,0.002323659,0.0007383833,0.0027901072,0.001133582,0.00034759633],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030730416,0.0005774201,0.0009866112,0.0009786901,0.00046780365,0.00064986624,0.003927005,0.0006189765,0.00026117632],"category_scores_gemma":[0.0013562875,0.0005431675,0.0006877595,0.0012597844,0.00035849484,0.0007412143,0.0032210867,0.0012518313,0.0008002241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034156733,0.0001652157,0.0011201872,0.0001843931,0.00020602916,0.0002372114,0.00051287643,0.96514314,0.000051852116,0.01491766,0.004824559,0.012295284],"study_design_scores_gemma":[0.0008338994,0.00008097158,0.00017171616,0.000072763745,0.00004234011,0.000005416761,0.0006455796,0.56229216,0.00013317428,0.4261097,0.009059309,0.00055297813],"about_ca_topic_score_codex":0.00010003025,"about_ca_topic_score_gemma":0.000031413667,"teacher_disagreement_score":0.9357972,"about_ca_system_score_codex":0.00052351557,"about_ca_system_score_gemma":0.00056482747,"threshold_uncertainty_score":0.99997777},"labels":[],"label_agreement":null},{"id":"W2982146718","doi":"10.1287/ijoo.2019.0045","title":"An Ensemble Learning Framework for Model Fitting and Evaluation in Inverse Linear Optimization","year":2021,"lang":"en","type":"preprint","venue":"INFORMS Journal on Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; University of Toronto","funders":"","keywords":"Metric (unit); Computer science; Mathematical optimization; Plan (archaeology); Inverse; Machine learning; Construct (python library); Optimization problem; Base (topology); Artificial intelligence; Mathematics; Algorithm; Engineering","score_opus":0.16963652680852584,"score_gpt":0.4728932681299927,"score_spread":0.30325674132146685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982146718","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025841791,0.000103328784,0.9722229,0.00027479336,0.0004735762,0.00092032185,0.000009366119,0.000035257268,0.00011866196],"genre_scores_gemma":[0.08898901,0.000797253,0.90914744,0.00016332851,0.000349979,0.00009469246,0.00028387067,0.00005783478,0.000116606214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941994,0.0004337167,0.0015485891,0.0007116989,0.0026554007,0.0004511987],"domain_scores_gemma":[0.9932352,0.0012136854,0.0013879003,0.0005210257,0.0033854994,0.00025672684],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009475323,0.00034149637,0.0005427508,0.0013964697,0.0004997842,0.0018303095,0.00057427416,0.00065255206,0.00015160855],"category_scores_gemma":[0.020633554,0.00029258122,0.000148574,0.00082577846,0.00006494008,0.0024876914,0.0003076597,0.002108054,0.0000036059514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014233627,0.000053525026,0.00022582004,0.000021233327,0.000015082302,0.000004552955,0.0014803183,0.957311,0.0000045693896,0.00005698502,0.000019018684,0.040665608],"study_design_scores_gemma":[0.0009978213,0.00021460747,0.00003596213,0.00033290376,0.000022617749,0.000018261582,0.0016476028,0.978701,0.000056011,0.017641379,0.000022129801,0.00030973088],"about_ca_topic_score_codex":0.0000061084847,"about_ca_topic_score_gemma":0.0000143405,"teacher_disagreement_score":0.063147224,"about_ca_system_score_codex":0.0005380347,"about_ca_system_score_gemma":0.00094457564,"threshold_uncertainty_score":0.9999526},"labels":[],"label_agreement":null},{"id":"W2985478892","doi":"10.1016/j.tcs.2019.11.015","title":"A modular analysis of adaptive (non-)convex optimization: Optimism, composite objectives, variance reduction, and variational bounds","year":2019,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta; Engineering and Physical Sciences Research Council; Alberta Machine Intelligence Institute","keywords":"Mathematical proof; Mathematical optimization; Regret; Computer science; Generalization; Convex optimization; Modular design; Mathematics; Convex analysis; Regular polygon; Algorithm; Machine learning","score_opus":0.021383389473001273,"score_gpt":0.33536394111611845,"score_spread":0.31398055164311717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985478892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036166087,0.000035885616,0.96189296,0.00027719847,0.0002987367,0.0002769089,0.000019107549,0.00002515319,0.0010079858],"genre_scores_gemma":[0.7024898,0.000005652174,0.29732955,0.000040533963,0.00005347874,0.0000050556437,0.0000034074424,0.0000061196083,0.0000663935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99498564,0.0002686433,0.00061345374,0.0011385372,0.002570581,0.00042314237],"domain_scores_gemma":[0.9959005,0.001109644,0.00025274494,0.00085700076,0.001627079,0.00025302125],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004085592,0.00018744625,0.0005546545,0.0010764938,0.00036556297,0.0004027946,0.001322886,0.00007313131,0.0006192841],"category_scores_gemma":[0.00042944477,0.00014846357,0.00011617181,0.007086887,0.0040288605,0.0010357624,0.0006927904,0.00021727924,0.000033259246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064429645,0.000055092507,0.0003100681,0.000001934219,0.00007622742,0.0000017523687,0.00051616755,0.7776806,0.0005339263,0.21871582,0.000005389641,0.0020386425],"study_design_scores_gemma":[0.00029825693,0.00020158332,0.015652781,0.000011012618,0.000046202953,0.000014176595,0.00006468487,0.9211148,0.00054987747,0.061872605,0.000012014729,0.0001620133],"about_ca_topic_score_codex":0.000008492262,"about_ca_topic_score_gemma":1.8952515e-7,"teacher_disagreement_score":0.6663237,"about_ca_system_score_codex":0.00009912078,"about_ca_system_score_gemma":0.0002766171,"threshold_uncertainty_score":0.9986816},"labels":[],"label_agreement":null},{"id":"W2993775923","doi":"10.48550/arxiv.1912.02967","title":"Alternative Function Approximation Parameterizations for Solving Games: An Analysis of $f$-Regression Counterfactual Regret Minimization","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Softmax function; Counterfactual thinking; Approximation error; Function approximation; Reinforcement learning; Perfect information; Function (biology); Mathematics; Mathematical optimization; Computer science; Applied mathematics; Mathematical economics; Artificial intelligence; Statistics; Artificial neural network","score_opus":0.24397190943936153,"score_gpt":0.33773912044899723,"score_spread":0.0937672110096357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993775923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30768895,0.000018638944,0.6906665,0.0000142041235,0.0003862372,0.0007081198,0.0004100841,0.00003965409,0.00006759676],"genre_scores_gemma":[0.9946444,0.00006767293,0.0028544015,0.000018103245,0.00007040978,0.0000082517045,0.0011555847,0.00002907444,0.0011521165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996388,0.00036628003,0.00071950135,0.0015201973,0.00068013236,0.00032584937],"domain_scores_gemma":[0.9932686,0.0015800914,0.001487118,0.0014280605,0.0020970444,0.00013910339],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012333471,0.00033766654,0.00081433874,0.0022944696,0.00021107691,0.000210766,0.0011755164,0.00048412624,0.00022887738],"category_scores_gemma":[0.0016486597,0.00030843282,0.0005229596,0.0026035102,0.00019975053,0.0011616434,0.0005511208,0.00043992166,0.000022479238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036616554,0.0001170404,0.0037426972,0.000036820617,0.0005147063,0.0000022726922,0.0005456875,0.9909829,0.00013515192,0.0016683924,0.000074411706,0.0018137817],"study_design_scores_gemma":[0.00055826106,0.00020901898,0.0033457342,0.000070944836,0.0007755336,2.769726e-7,0.0013123162,0.9640228,0.00049802597,0.028817723,0.0001021233,0.00028725574],"about_ca_topic_score_codex":0.00008456037,"about_ca_topic_score_gemma":0.00007814274,"teacher_disagreement_score":0.6878121,"about_ca_system_score_codex":0.00033240402,"about_ca_system_score_gemma":0.00022937731,"threshold_uncertainty_score":0.99993676},"labels":[],"label_agreement":null},{"id":"W2993785662","doi":"10.48550/arxiv.1912.01718","title":"Risk-Averse Action Selection Using Extreme Value Theory Estimates of the CVaR","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"CVAR; Quantile; Estimator; Extreme value theory; Expected shortfall; Generalized Pareto distribution; Selection (genetic algorithm); Variance (accounting); Mathematical optimization; Extrapolation; Econometrics; Mathematics; Computer science; Statistics; Risk management; Economics; Artificial intelligence","score_opus":0.36099966413873114,"score_gpt":0.3320410035950809,"score_spread":0.02895866054365026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993785662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4799496,0.000026384683,0.5184244,0.000009186213,0.0007424474,0.0003636036,0.000037350404,0.0000394918,0.00040755185],"genre_scores_gemma":[0.99513435,0.000099803336,0.0015370152,0.000008856776,0.00009049062,4.8795687e-7,0.0000035590667,0.000027562659,0.0030978757],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99634176,0.0010866146,0.00041035388,0.0011151232,0.00067252433,0.0003736209],"domain_scores_gemma":[0.9948492,0.0017746974,0.001073607,0.0014463051,0.0007548785,0.000101294616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024649606,0.00029978045,0.00045264888,0.00057994766,0.00037691987,0.00010429037,0.0017472779,0.00035657876,0.0003571636],"category_scores_gemma":[0.00242276,0.00023290818,0.00040615987,0.0016353801,0.0003854779,0.0005032323,0.0016543019,0.0010621044,0.00017064998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014842021,0.000053630618,0.02231749,0.00002327949,0.000077143726,0.000007980822,0.00011403717,0.9723262,0.00056342024,0.0026768355,0.00007440276,0.00161712],"study_design_scores_gemma":[0.0003079348,0.000030116084,0.008368563,0.000062020335,0.00011136114,0.000004663871,0.00052025326,0.7545904,0.0027662287,0.23286955,0.0001574835,0.00021144608],"about_ca_topic_score_codex":0.00042512463,"about_ca_topic_score_gemma":0.00006272297,"teacher_disagreement_score":0.51688737,"about_ca_system_score_codex":0.0005264959,"about_ca_system_score_gemma":0.00044255238,"threshold_uncertainty_score":0.94977194},"labels":[],"label_agreement":null},{"id":"W2994873989","doi":"10.1109/cwit.2019.8929931","title":"Dynamic spectrum access under partial observations: A restless bandit approach","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Markov decision process; Markov process; Channel (broadcasting); Mathematical optimization; Scheduling (production processes); Partially observable Markov decision process; Resource allocation; Transmitter; Heuristic; Channel allocation schemes; Markov chain; Computer network; Wireless; Mathematics; Telecommunications","score_opus":0.26519510859321027,"score_gpt":0.4729444876965696,"score_spread":0.20774937910335933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994873989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15201573,0.00008259884,0.83012736,0.0032752072,0.0006611549,0.00083303504,0.000021103982,0.00014569321,0.012838142],"genre_scores_gemma":[0.9410027,0.000018739653,0.005827871,0.0003450286,0.00010330486,0.000057868732,0.00002482735,0.000029493212,0.05259012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995245,0.0002013825,0.0006116476,0.0009112328,0.0024293724,0.00060139765],"domain_scores_gemma":[0.9970097,0.0011003071,0.00015809851,0.0012913845,0.00025786768,0.00018264836],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001701344,0.00019670543,0.0003470559,0.00039051866,0.00018892201,0.0008435369,0.0020554063,0.00011617314,0.0044687716],"category_scores_gemma":[0.000699863,0.00013624212,0.00012303593,0.0018424742,0.0001452464,0.0016036589,0.000610384,0.0003218748,0.0030090495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006511084,0.0015207444,0.11195447,0.000078717916,0.00024147557,0.00006488119,0.000900557,0.7608475,0.001475655,0.05715978,0.039681993,0.025423104],"study_design_scores_gemma":[0.0012018544,0.00010672737,0.16423121,0.000011610741,0.000007277422,0.000016848271,0.0011586475,0.65255564,0.00066365674,0.1649554,0.014623562,0.00046757582],"about_ca_topic_score_codex":0.0000765017,"about_ca_topic_score_gemma":0.00012016565,"teacher_disagreement_score":0.82429945,"about_ca_system_score_codex":0.0001422601,"about_ca_system_score_gemma":0.0001901416,"threshold_uncertainty_score":0.9977672},"labels":[],"label_agreement":null},{"id":"W2995725691","doi":"10.48550/arxiv.1912.09451","title":"An Iterative Riccati Algorithm for Online Linear Quadratic Control","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Regret; Sublinear function; Linear-quadratic regulator; Logarithm; Mathematics; Mathematical optimization; Hindsight bias; Controller (irrigation); Linear-quadratic-Gaussian control; Optimal control; Linear system; Riccati equation; Smoothing; Sequence (biology); Computer science; Discrete mathematics","score_opus":0.22565802047666222,"score_gpt":0.3500820730083962,"score_spread":0.124424052531734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995725691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030581705,0.00011070122,0.96420604,0.00013979108,0.001058212,0.0019376443,0.0016931472,0.00012107418,0.00015171044],"genre_scores_gemma":[0.9393577,0.000109369255,0.04402362,0.00023432627,0.0007282944,0.000013053825,0.000450142,0.00008773939,0.014995766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947598,0.0007012526,0.0007227077,0.0023760123,0.00069448946,0.0007457662],"domain_scores_gemma":[0.9912169,0.0029975942,0.0007117286,0.0024785358,0.0021625122,0.00043271788],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017203917,0.00056442793,0.0010684213,0.0008722047,0.0003106708,0.00034535333,0.0031771646,0.0005183334,0.00026384654],"category_scores_gemma":[0.0012847047,0.00051487295,0.0004907564,0.0011504679,0.0003332137,0.00086940464,0.0007770507,0.001058829,0.00050876045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025584613,0.0005622343,0.00081033574,0.000041427003,0.00020180567,0.00015055425,0.00034693658,0.9566661,0.000031601736,0.0013011325,0.0008763406,0.038755674],"study_design_scores_gemma":[0.0020986958,0.0004006269,0.00051587046,0.00004528333,0.00007596416,0.0000020756033,0.0006241273,0.9390574,0.0000630157,0.052912902,0.0036505829,0.00055342354],"about_ca_topic_score_codex":0.00007387415,"about_ca_topic_score_gemma":0.00009314954,"teacher_disagreement_score":0.9201824,"about_ca_system_score_codex":0.0003628729,"about_ca_system_score_gemma":0.0006673119,"threshold_uncertainty_score":0.9997303},"labels":[],"label_agreement":null},{"id":"W2997720193","doi":"10.1609/aaai.v34i04.6116","title":"Efficient Projection-Free Online Methods with Stochastic Recursive Gradient","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Regret; Logarithm; Projection (relational algebra); Mathematical optimization; Computer science; Estimator; Regular polygon; Convex optimization; Algorithm; Mathematics; Machine learning","score_opus":0.3080010328745577,"score_gpt":0.46401449363521663,"score_spread":0.15601346076065892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997720193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17551073,0.00005622128,0.7937316,0.025028655,0.00062420755,0.0020883814,0.000090753376,0.00013834627,0.0027311493],"genre_scores_gemma":[0.96672034,0.000006644138,0.032449704,0.0002701282,0.0001757899,0.000054404274,8.6565603e-7,0.00002804875,0.0002940756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950144,0.00009815078,0.00095662,0.0009893375,0.002415556,0.00052592746],"domain_scores_gemma":[0.99441415,0.0009850941,0.00073506,0.00054573285,0.0030323057,0.00028762937],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017925984,0.00031398423,0.00049817073,0.0002763185,0.00032007266,0.00027500038,0.0031707427,0.00009347224,0.00024334437],"category_scores_gemma":[0.017167436,0.0001817467,0.00016230154,0.0028182974,0.0008412708,0.00018011683,0.0006937419,0.00066524814,0.00013276975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034421203,0.0013792845,0.00016860898,0.00009254401,0.0001295858,0.0000064017822,0.0160391,0.094659306,0.031865418,0.27051637,0.0016802677,0.58002096],"study_design_scores_gemma":[0.0001253846,0.0015066745,0.00017281638,0.00020181085,0.000032140717,0.000012800653,0.011170292,0.5936064,0.17277318,0.21976218,0.00024518854,0.00039112612],"about_ca_topic_score_codex":0.00002779113,"about_ca_topic_score_gemma":0.000020339292,"teacher_disagreement_score":0.79120964,"about_ca_system_score_codex":0.00009238192,"about_ca_system_score_gemma":0.00024114522,"threshold_uncertainty_score":0.9911114},"labels":[],"label_agreement":null},{"id":"W2997790181","doi":"10.1609/aaai.v34i04.5821","title":"Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"Division of Electrical, Communications and Cyber Systems; National Science Foundation","keywords":"Regret; Sublinear function; Probabilistic logic; Attack model; Computer science; Bounded function; Expected value; Algorithm; Adversary; Mathematical optimization; Mathematics; Discrete mathematics; Artificial intelligence; Machine learning; Computer security; Statistics","score_opus":0.4478936109603608,"score_gpt":0.4201507851199051,"score_spread":0.027742825840455676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997790181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09308951,0.000069899186,0.85121626,0.039714374,0.0024470538,0.0035339654,0.00014882398,0.000319023,0.009461112],"genre_scores_gemma":[0.9963988,0.0000083577615,0.0019401257,0.00040937957,0.00046304258,0.00004746302,0.0000017718356,0.00003664723,0.0006943809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932614,0.000079290476,0.0014040279,0.0012645954,0.0032479595,0.00074272935],"domain_scores_gemma":[0.9946414,0.0011215553,0.0007771945,0.000520891,0.002527823,0.00041112152],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016902316,0.00042500775,0.00066283945,0.00024230653,0.0004461524,0.000673947,0.0036119923,0.00019033819,0.0013521131],"category_scores_gemma":[0.013773177,0.00028781875,0.00028186146,0.0023130532,0.0012301783,0.0006436964,0.00080375216,0.00081844046,0.001071697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029020074,0.0009754285,0.00016390703,0.0001519095,0.00018298064,0.000009917344,0.0076117557,0.37013766,0.019619571,0.43383425,0.006590581,0.15782005],"study_design_scores_gemma":[0.00016210169,0.0006208702,0.00014871228,0.00012456972,0.00003567132,0.000007014631,0.0038535995,0.5632754,0.03220922,0.39874128,0.00034406214,0.00047750672],"about_ca_topic_score_codex":0.00002751723,"about_ca_topic_score_gemma":0.000018828312,"teacher_disagreement_score":0.90330935,"about_ca_system_score_codex":0.0001503396,"about_ca_system_score_gemma":0.0003875942,"threshold_uncertainty_score":0.9999574},"labels":[],"label_agreement":null},{"id":"W2998546572","doi":"10.48550/arxiv.2009.09153","title":"Hidden Incentives for Auto-Induced Distributional Shift","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Incentive; Leverage (statistics); Computer science; Perception; Artificial intelligence; Machine learning; Paradigm shift; Economics; Microeconomics; Psychology","score_opus":0.3450151864016881,"score_gpt":0.33675152972918004,"score_spread":0.008263656672508057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998546572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13837363,0.00004220195,0.8561112,0.0015603107,0.0008308962,0.0009734413,0.0013317146,0.00016552873,0.00061107374],"genre_scores_gemma":[0.99607366,0.000026081518,0.0011270277,0.00005861491,0.00034889602,0.0000069481107,0.00023822927,0.000030078969,0.0020904879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99577403,0.00030458308,0.0004960524,0.002076696,0.0007251862,0.00062346127],"domain_scores_gemma":[0.99532455,0.0018628828,0.000463018,0.0011357658,0.0007852927,0.00042850405],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010790731,0.00039638727,0.0006351746,0.00039558823,0.00039254603,0.00031114032,0.0029408352,0.00039525848,0.0004176858],"category_scores_gemma":[0.0029990072,0.00039173086,0.0005366731,0.0012116478,0.000312903,0.00047991055,0.0030282405,0.00091902993,0.0005636536],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004701208,0.0015560501,0.02899103,0.00048122244,0.0017578515,0.0026429114,0.0023464663,0.13711336,0.001644413,0.73464936,0.041541204,0.042574935],"study_design_scores_gemma":[0.0011643077,0.00012724767,0.013120955,0.00004293293,0.00005556016,0.0000015817183,0.0003620548,0.20453341,0.0004979696,0.76984376,0.009651302,0.00059892575],"about_ca_topic_score_codex":0.000043639717,"about_ca_topic_score_gemma":0.000031310887,"teacher_disagreement_score":0.8577,"about_ca_system_score_codex":0.00049100985,"about_ca_system_score_gemma":0.0007121599,"threshold_uncertainty_score":0.99985343},"labels":[],"label_agreement":null},{"id":"W3000867405","doi":"10.1007/978-3-030-33950-0_19","title":"Policy Search on Aggregated State Space for Active Sampling","year":2020,"lang":"en","type":"book-chapter","venue":"Springer proceedings in advanced robotics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Sampling (signal processing); Measure (data warehouse); Adaptive sampling; Computer science; Scalar (mathematics); Space (punctuation); Field (mathematics); State space; Mathematical optimization; Algorithm; Mathematics; Data mining; Statistics; Geometry; Computer vision; Pure mathematics","score_opus":0.15193684302990682,"score_gpt":0.42441289845431784,"score_spread":0.272476055424411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000867405","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009982096,0.0010615458,0.6000721,0.03671498,0.003137867,0.016204726,0.0014337519,0.0013254972,0.33905134],"genre_scores_gemma":[0.010275639,0.0022920214,0.43536517,0.001973849,0.002238877,0.00036419113,0.00009021856,0.001315982,0.54608405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99102557,0.000021834665,0.0014565595,0.0024972411,0.0035570664,0.001441711],"domain_scores_gemma":[0.9933923,0.002158676,0.0009267534,0.0006902717,0.0022578533,0.0005741846],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015491109,0.0009817171,0.0014714494,0.0023191315,0.00033973937,0.0004698473,0.0020299375,0.00048420508,0.000058633887],"category_scores_gemma":[0.009181887,0.00090922246,0.0003878234,0.0011930758,0.00042255392,0.0007158704,0.0009771751,0.002611544,0.00037955464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002852412,0.00014441583,0.00006207638,0.00033922936,0.00020256262,0.00009894823,0.0017055266,0.37408802,0.0014772638,0.2735004,0.0012253921,0.34430373],"study_design_scores_gemma":[0.0030004277,0.0012434139,0.00011858618,0.0014955058,0.000030908326,0.000016133066,0.000572086,0.01694662,0.007905106,0.778209,0.18840472,0.0020575034],"about_ca_topic_score_codex":0.0000070744086,"about_ca_topic_score_gemma":0.000013646109,"teacher_disagreement_score":0.5047085,"about_ca_system_score_codex":0.0013071228,"about_ca_system_score_gemma":0.0006569387,"threshold_uncertainty_score":0.99968946},"labels":[],"label_agreement":null},{"id":"W3004262408","doi":"10.1109/lcsys.2020.2989110","title":"Dynamic and Distributed Online Convex Optimization for Demand Response of Commercial Buildings","year":2020,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency - Energy","keywords":"Regret; Demand response; Convex optimization; Upper and lower bounds; Time horizon; Regular polygon; Dual (grammatical number)","score_opus":0.05587819967213528,"score_gpt":0.3638840339324756,"score_spread":0.30800583426034034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004262408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25843295,0.000154346,0.7268608,0.012458161,0.00025801666,0.00080970867,0.0009995142,0.000026089883,4.0044486e-7],"genre_scores_gemma":[0.9962457,0.0000057597363,0.002362485,0.0011251135,0.00013943961,0.000050081424,0.000033265133,0.000020723519,0.000017421127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970172,0.0005546956,0.0008072783,0.00046765825,0.0008443518,0.00030880177],"domain_scores_gemma":[0.99473745,0.003936645,0.00040620298,0.00027636706,0.00045116965,0.00019218227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020562513,0.0001682166,0.0006243955,0.00016891529,0.00012893257,0.00014719434,0.00043995123,0.000087263325,0.000009260645],"category_scores_gemma":[0.004307943,0.00013718859,0.000098372395,0.00044173413,0.00020974474,0.00025328159,0.000041669104,0.0001345877,0.000004187582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003348322,0.00002910379,0.0008104184,0.000051495164,0.00005785397,0.000011366628,0.00024406021,0.9163107,0.073693454,0.000008778148,0.0045778146,0.00085661904],"study_design_scores_gemma":[0.003834775,0.00021302376,0.0017594505,0.000029575565,0.00002196726,0.00000665951,0.00021147076,0.9915283,0.00021458683,0.0000173198,0.002017,0.00014591884],"about_ca_topic_score_codex":0.00001761102,"about_ca_topic_score_gemma":0.0000036704578,"teacher_disagreement_score":0.73781276,"about_ca_system_score_codex":0.000065280365,"about_ca_system_score_gemma":0.00004960402,"threshold_uncertainty_score":0.5594388},"labels":[],"label_agreement":null},{"id":"W3005661940","doi":"10.1609/aaai.v35i8.16901","title":"Regret Bounds for Batched Bandits","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Office of Naval Research; Institut de Valorisation des Données; Canada First Research Excellence Fund; National Science Foundation","keywords":"Regret; Logarithm; Mathematical optimization; Simple (philosophy); Computer science; Multi-armed bandit; Mathematics; Algorithm; Machine learning","score_opus":0.349858033997507,"score_gpt":0.4633447509370407,"score_spread":0.11348671693953372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005661940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5126265,0.00047160682,0.33356667,0.0668943,0.0061820117,0.004601665,0.00040121327,0.0003471127,0.07490888],"genre_scores_gemma":[0.98846763,0.000040711224,0.003575751,0.00020399505,0.00020609226,0.00007118012,0.0000020092418,0.000022930542,0.007409673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99555326,0.000043139888,0.0010089343,0.000864114,0.0019774763,0.0005530899],"domain_scores_gemma":[0.99242824,0.001290812,0.000530731,0.000559453,0.0050273496,0.00016339506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002345155,0.0002457535,0.00046403927,0.00020765544,0.00039275436,0.0006097171,0.002219153,0.00013989968,0.0008648851],"category_scores_gemma":[0.017821671,0.00016440346,0.0002832372,0.0016564315,0.00055834407,0.00045035323,0.0004687545,0.00037273808,0.00024704228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057834515,0.00040058186,0.00056281773,0.0000616773,0.000053056036,0.000003949553,0.0018593792,0.00027218423,0.10824461,0.5520921,0.007949475,0.32792184],"study_design_scores_gemma":[0.000040955343,0.000122062236,0.0001418722,0.00006603694,0.000007583715,0.000005285976,0.0017012287,0.012444984,0.5155847,0.46692565,0.0028156023,0.00014401945],"about_ca_topic_score_codex":0.00000960653,"about_ca_topic_score_gemma":0.000029407849,"teacher_disagreement_score":0.47584113,"about_ca_system_score_codex":0.00007430318,"about_ca_system_score_gemma":0.00037184835,"threshold_uncertainty_score":0.99045163},"labels":[],"label_agreement":null},{"id":"W3007722162","doi":"10.1109/tsp.2021.3089822","title":"Safe Linear Thompson Sampling With Side Information","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Signal Processing","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Office of the President, University of California","keywords":"Frequentist inference; Regret; Thompson sampling; Set (abstract data type); Reliability (semiconductor); Linear programming; Mathematics; Computer science; Algorithm; Mathematical optimization; Sampling (signal processing); Combinatorics; Bayesian probability; Statistics; Bayesian inference","score_opus":0.14129229971825966,"score_gpt":0.41763110013686366,"score_spread":0.27633880041860404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007722162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052666105,0.00018544658,0.9919874,0.00041388843,0.00044581477,0.0005049622,0.00007977417,0.0001720861,0.0009440063],"genre_scores_gemma":[0.91700923,0.000042547497,0.08169092,0.00020187446,0.00021543898,0.000119826625,0.000036066765,0.000054117896,0.00062996364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99314845,0.00024494337,0.0012253663,0.0010014103,0.0037654229,0.0006144333],"domain_scores_gemma":[0.9952439,0.000998915,0.00065858883,0.0008145927,0.002020287,0.00026369555],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016841472,0.000517416,0.0007027382,0.0010839086,0.00086167344,0.0020708058,0.0009979906,0.00042554157,0.0006525006],"category_scores_gemma":[0.00014037036,0.0004020096,0.00026336164,0.0015925091,0.00022397947,0.002514508,0.000027096077,0.0024371939,0.00022360033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013873851,0.00006062032,0.0000035616104,0.00008122515,0.000026437336,0.000012531832,0.0007439232,0.5628438,0.00016228513,5.7469987e-7,0.00000972403,0.43591657],"study_design_scores_gemma":[0.0015857145,0.00042357176,0.00020278107,0.0025135505,0.00015326207,0.0001467133,0.006140043,0.91642714,0.06202101,0.0032058584,0.0054838806,0.0016965029],"about_ca_topic_score_codex":0.000040585215,"about_ca_topic_score_gemma":0.00007476027,"teacher_disagreement_score":0.9117426,"about_ca_system_score_codex":0.00030841044,"about_ca_system_score_gemma":0.0014360263,"threshold_uncertainty_score":0.9998642},"labels":[],"label_agreement":null},{"id":"W3008672633","doi":"10.4171/msl/38","title":"Optimal anytime regret with two experts","year":2023,"lang":"en","type":"article","venue":"Mathematical Statistics and Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Minimax; Time horizon; Constant (computer programming); Mathematical optimization; Computer science; Horizon; Mathematics; Machine learning","score_opus":0.09688300321347229,"score_gpt":0.43732907788875097,"score_spread":0.34044607467527865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008672633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07777894,0.000027500166,0.91983855,0.00027886248,0.000025543999,0.00013471636,0.000020696098,0.00010194657,0.0017932225],"genre_scores_gemma":[0.47848192,0.000024092775,0.4882969,0.00006205225,0.00013502924,0.00004490003,0.00002256206,0.00006290474,0.03286966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973917,0.00017672246,0.0003347673,0.0003809112,0.0013128225,0.00040309428],"domain_scores_gemma":[0.9946053,0.0046906997,0.00008998544,0.00023214187,0.00018021399,0.0002016293],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018837369,0.00013354814,0.0002816176,0.00016572395,0.00035523195,0.0003260845,0.00022672392,0.000036288307,0.0011855006],"category_scores_gemma":[0.0065831537,0.00008253749,0.000021317783,0.0006355649,0.0002300216,0.000084280146,0.0001868737,0.00030431908,0.0008940107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027730622,0.00022104828,0.0035534932,0.0001577559,0.00012171393,0.0019456537,0.013689358,0.11746039,0.00038942372,0.1261144,0.03354051,0.70252895],"study_design_scores_gemma":[0.00057942374,0.00028469166,0.0011268395,0.00004126255,0.0000074931863,0.00005544981,0.0026697798,0.8703772,0.00003934944,0.112337515,0.012257084,0.0002239238],"about_ca_topic_score_codex":0.0000045061756,"about_ca_topic_score_gemma":0.0000021764238,"teacher_disagreement_score":0.7529168,"about_ca_system_score_codex":0.00001633088,"about_ca_system_score_gemma":0.000029427252,"threshold_uncertainty_score":0.9998839},"labels":[],"label_agreement":null},{"id":"W3009214291","doi":"10.48550/arxiv.2003.03456","title":"A Farewell to Arms: Sequential Reward Maximization on a Budget with a Giving Up Option","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Maximization; Economics; Utility maximization; Microeconomics; Keynesian economics; Mathematical economics","score_opus":0.29663554765176436,"score_gpt":0.31414571951151904,"score_spread":0.017510171859754675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009214291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14898954,0.000008898995,0.84767526,0.0008204603,0.00052081153,0.0008699494,0.00009752599,0.00017623739,0.0008413058],"genre_scores_gemma":[0.9893231,0.000045227724,0.0037695153,0.00023382371,0.00022243393,0.0000057518478,0.00004932074,0.00005351035,0.00629731],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952062,0.00043238042,0.00044162382,0.0023147657,0.0010385554,0.00056649314],"domain_scores_gemma":[0.99634653,0.00047445833,0.00043393628,0.0014108189,0.0008250284,0.00050925394],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008914139,0.00045336792,0.00058453344,0.0010601956,0.00025439626,0.00043307556,0.0018844706,0.00031003993,0.00033979717],"category_scores_gemma":[0.0013436944,0.00041400868,0.00022678908,0.002490275,0.00016616812,0.0004652335,0.001760093,0.0010009625,0.0012414154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010553245,0.00007030951,0.00068752404,0.000033694883,0.000068451045,0.00054400234,0.0008593781,0.9913223,0.00009425641,0.002027718,0.00089700567,0.002340078],"study_design_scores_gemma":[0.0027564806,0.0013100131,0.002689236,0.00050320395,0.00013466713,0.000022413651,0.0028886646,0.84503126,0.0013473803,0.12856129,0.012989191,0.0017661811],"about_ca_topic_score_codex":0.000116388655,"about_ca_topic_score_gemma":0.00011883577,"teacher_disagreement_score":0.84390575,"about_ca_system_score_codex":0.0006428265,"about_ca_system_score_gemma":0.00041197028,"threshold_uncertainty_score":0.9998312},"labels":[],"label_agreement":null},{"id":"W3012851896","doi":"","title":"Convergence of Gradient Methods on Bilinear Zero-Sum Games","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convergence (economics); Bilinear interpolation; Zero (linguistics); Applied mathematics; Adversarial system; Computer science; Mathematical optimization; Generative grammar; Zero-sum game; Mathematics; Algorithm; Artificial intelligence; Nash equilibrium","score_opus":0.35221709293036835,"score_gpt":0.5526990798639185,"score_spread":0.20048198693355018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012851896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1087376,0.000042400123,0.80924517,0.029689062,0.0014751112,0.00059804885,0.00010713806,0.00017909889,0.049926348],"genre_scores_gemma":[0.9831194,0.000053551616,0.011219879,0.00027084802,0.000120600766,0.000033195407,0.000026384756,0.000016223594,0.005139867],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99551946,0.0006446224,0.00072515686,0.0007358527,0.002138214,0.0002367073],"domain_scores_gemma":[0.9944951,0.0030653337,0.00041300408,0.00042449436,0.0013945701,0.00020749144],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011506117,0.0001668606,0.0002910095,0.00040313945,0.00015221545,0.00017286441,0.0011769912,0.0000617754,0.0039604004],"category_scores_gemma":[0.019843373,0.00013803766,0.00015813143,0.00080061407,0.00027245187,0.0002947562,0.00022130583,0.0005466045,0.0008289014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011137006,0.0006898414,0.04408732,0.000023952163,0.00035222978,0.00008701502,0.013940642,0.38224906,0.04386877,0.19790706,0.011677864,0.30400255],"study_design_scores_gemma":[0.0011555201,0.0011121987,0.020764176,0.0000832807,0.000015499798,0.000008549847,0.0053947982,0.8362018,0.03966288,0.05318099,0.041988473,0.00043182715],"about_ca_topic_score_codex":0.000041060197,"about_ca_topic_score_gemma":0.000003230278,"teacher_disagreement_score":0.87438184,"about_ca_system_score_codex":0.000053491956,"about_ca_system_score_gemma":0.00014695484,"threshold_uncertainty_score":0.9999491},"labels":[],"label_agreement":null},{"id":"W3012922890","doi":"10.1007/s10614-021-10119-4","title":"Reinforcement Learning in Economics and Finance","year":2021,"lang":"en","type":"preprint","venue":"Computational Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; AXA Research Fund","keywords":"Reinforcement learning; Action (physics); Computer science; Set (abstract data type); Artificial intelligence; Time horizon; Q-learning; Behavioral economics; Order (exchange); Reinforcement; Process (computing); Term (time); Temporal difference learning; Economics; Microeconomics; Psychology; Finance; Social psychology","score_opus":0.08548769842633776,"score_gpt":0.3792800501201351,"score_spread":0.29379235169379736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012922890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88599914,0.00052102766,0.11048073,0.0010487366,0.00061742665,0.0003189278,0.00002249926,0.000019321093,0.00097220525],"genre_scores_gemma":[0.9707885,0.004463106,0.022886276,0.00018550218,0.00014872261,0.000044879973,0.00020861662,0.000028030758,0.0012463606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974141,0.000108148284,0.0010008883,0.0009634701,0.00022776349,0.00028561713],"domain_scores_gemma":[0.99743277,0.0013946969,0.0004697371,0.00038283176,0.000249653,0.00007033753],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013032719,0.00022698041,0.00052299304,0.00042655415,0.00011193677,0.0006644448,0.00056822225,0.00018496517,0.00006807801],"category_scores_gemma":[0.00070944795,0.00025714573,0.00010094045,0.00014021166,0.00013672837,0.00034201134,0.0017143422,0.000718164,0.000054904493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000104369465,0.000011955145,0.0007932757,0.0000054592215,0.000012256757,0.0000063972293,0.00022240536,0.93298566,6.7835984e-8,0.0019676767,0.000039394574,0.06394499],"study_design_scores_gemma":[0.00032075073,0.000017338622,0.008307798,0.000021073149,0.000001677753,0.000007691515,0.00019369979,0.84516704,0.0000056992258,0.13775092,0.007994148,0.00021214006],"about_ca_topic_score_codex":0.000021925649,"about_ca_topic_score_gemma":0.00009963075,"teacher_disagreement_score":0.13578324,"about_ca_system_score_codex":0.00039908636,"about_ca_system_score_gemma":0.0008723559,"threshold_uncertainty_score":0.9999881},"labels":[],"label_agreement":null},{"id":"W3017369915","doi":"10.1287/moor.2019.1019","title":"Variance Regularization in Sequential Bayesian Optimization","year":2020,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regularization (linguistics); Mathematical optimization; Bayesian probability; A priori and a posteriori; Mathematics; Optimization problem; Computer science; Dynamic programming; Algorithm; Artificial intelligence","score_opus":0.29304720584955735,"score_gpt":0.49850097107321184,"score_spread":0.2054537652236545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017369915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028901733,0.00003533982,0.98972774,0.0039943815,0.000036142337,0.0006569063,0.000019333602,0.000019970596,0.002620031],"genre_scores_gemma":[0.60325354,0.00003669923,0.39360923,0.000043343745,0.00011526753,0.00008451822,0.000029764471,0.000031668656,0.0027959943],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994564,0.00058365276,0.0009770999,0.00045645787,0.0030577122,0.00036110837],"domain_scores_gemma":[0.99643344,0.00092512585,0.00007139879,0.0006070542,0.0018055991,0.00015736427],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051408615,0.00010831,0.00029895696,0.0007221229,0.0002331281,0.0003510297,0.000974053,0.00009874845,0.0011849472],"category_scores_gemma":[0.017060885,0.00009268273,0.000052412066,0.0041681817,0.0002505929,0.00071516307,0.00031300736,0.00038730336,0.00015486541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016635444,0.00014091945,0.000053617263,0.000028873548,0.0000056977437,0.0000071204367,0.0024351154,0.97801256,0.0023164891,0.015150704,0.00032257184,0.0015096712],"study_design_scores_gemma":[0.00033603623,0.00008534294,0.000044014032,0.000025715352,0.0000014131997,0.000002198839,0.0010270695,0.971967,0.0040875454,0.022181831,0.00015873926,0.00008311106],"about_ca_topic_score_codex":0.000021715712,"about_ca_topic_score_gemma":0.00004822636,"teacher_disagreement_score":0.6003634,"about_ca_system_score_codex":0.00008845932,"about_ca_system_score_gemma":0.00032844816,"threshold_uncertainty_score":0.9997281},"labels":[],"label_agreement":null},{"id":"W3023384417","doi":"10.1109/isit45174.2021.9518176","title":"Regret Bounds for Safe Gaussian Process Bandit Optimization","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Mathematical optimization; Bayesian optimization; Computer science; Stochastic game; Gaussian process; Set (abstract data type); Constraint (computer-aided design); Function (biology); Bayesian probability; Gaussian; Mathematics; Artificial intelligence; Machine learning; Mathematical economics","score_opus":0.1769952684360234,"score_gpt":0.4986446823155516,"score_spread":0.32164941387952817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023384417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042055617,0.0003328403,0.9831676,0.0021842574,0.0012798947,0.0013165176,0.000140066,0.000109697256,0.011048585],"genre_scores_gemma":[0.16726066,0.0003807405,0.6722862,0.000575239,0.0020513562,0.0017586548,0.001848242,0.00022817249,0.15361069],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929965,0.00021322469,0.0011241842,0.0018316177,0.0031758777,0.0006586049],"domain_scores_gemma":[0.9933614,0.0013531499,0.00051895576,0.0017155795,0.002767313,0.00028357125],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002959683,0.00040977637,0.00078760454,0.0006197528,0.0003652351,0.0022068373,0.002036865,0.0005453622,0.0059527075],"category_scores_gemma":[0.008143953,0.00030574136,0.00035082534,0.00082598947,0.0001974221,0.00061219226,0.0012018643,0.00072710164,0.00008432875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001071137,0.000112465284,0.00014860646,0.0001415633,0.00006428896,0.000027908567,0.00071357423,0.95031035,0.0000071504573,0.00018141483,0.014612051,0.03357349],"study_design_scores_gemma":[0.0008998465,0.00012154232,0.00019856199,0.0001581948,0.000029744393,0.000017941085,0.002265699,0.9029674,0.0014600032,0.07189064,0.019218396,0.0007720439],"about_ca_topic_score_codex":0.000024726773,"about_ca_topic_score_gemma":0.000108971886,"teacher_disagreement_score":0.31088135,"about_ca_system_score_codex":0.00021500299,"about_ca_system_score_gemma":0.0012954267,"threshold_uncertainty_score":0.99993944},"labels":[],"label_agreement":null},{"id":"W3028421523","doi":"10.1016/j.jeconom.2020.04.025","title":"The fast iterated bootstrap","year":2020,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Iterated function; Series (stratigraphy); Mathematics; Algorithm; Applied mathematics; Computer science","score_opus":0.602328803079659,"score_gpt":0.4419714958789592,"score_spread":0.1603573072006998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028421523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29922843,0.012424486,0.58720595,0.08017808,0.004506314,0.0005394333,0.00008261052,0.000045178505,0.015789516],"genre_scores_gemma":[0.9958855,0.00043052476,0.0014508546,0.0005013,0.00065973465,7.3617906e-7,3.0677108e-7,0.000011616822,0.001059444],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741673,0.00010878238,0.0010032767,0.00015747036,0.0010763047,0.00023744456],"domain_scores_gemma":[0.99424237,0.0035252979,0.00072806294,0.0002214481,0.0009650161,0.00031779008],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031315892,0.00008194199,0.0002623505,0.00067031523,0.00017971735,0.00066993246,0.0013249082,0.000040466562,0.00039960607],"category_scores_gemma":[0.019360043,0.00004412658,0.00016720154,0.004236382,0.00009608184,0.00062128436,0.00011659102,0.00040833058,0.00030664707],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025814114,0.00008690228,0.012655658,0.000004971018,0.00012323246,0.00020130683,0.00080509373,0.013088345,0.00014495074,0.000589592,0.09143059,0.88061124],"study_design_scores_gemma":[0.0009943097,0.0008035383,0.015208218,0.000005993928,0.000009046597,0.00010134354,0.0017983856,0.023421593,0.00067747285,0.012477446,0.9443283,0.00017432263],"about_ca_topic_score_codex":4.052699e-7,"about_ca_topic_score_gemma":8.8543675e-7,"teacher_disagreement_score":0.8804369,"about_ca_system_score_codex":0.000060768165,"about_ca_system_score_gemma":0.00014454586,"threshold_uncertainty_score":0.9889003},"labels":[],"label_agreement":null},{"id":"W3029510736","doi":"10.1016/j.artint.2020.103328","title":"On the equivalence of optimal recommendation sets and myopically optimal query sets","year":2020,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Luonnontieteiden ja Tekniikan Tutkimuksen Toimikunta; Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Computer science; Recommender system; Preference elicitation; Set (abstract data type); Preference; Equivalence (formal languages); Expected utility hypothesis; Information retrieval; Data mining; Machine learning; Mathematics","score_opus":0.33583112151467903,"score_gpt":0.46472001396090457,"score_spread":0.12888889244622553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029510736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40969995,0.0000427435,0.5689922,0.020198343,0.00018333807,0.00034501517,0.0000400425,0.00003422457,0.00046414172],"genre_scores_gemma":[0.993043,0.00004377467,0.006037041,0.0007329649,0.00007050762,0.000013563843,0.000003361547,0.000011477938,0.000044323482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692506,0.0003036309,0.00075714133,0.0005903122,0.0010954886,0.00032837855],"domain_scores_gemma":[0.9946714,0.004159301,0.00022324677,0.00039161573,0.00037344854,0.00018096482],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017121104,0.00015825605,0.00024835742,0.000105807805,0.00021483275,0.0001817271,0.0008423064,0.00007297275,0.0013841701],"category_scores_gemma":[0.009104935,0.000104066836,0.00007496884,0.00081276224,0.0004798582,0.00035042543,0.00035595926,0.00034165027,0.0004835723],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047484227,0.0001201062,0.00017463168,0.000011760657,0.000020604142,0.000016549497,0.0029504178,0.026071278,0.0045227315,0.029270599,0.001982198,0.9343843],"study_design_scores_gemma":[0.000067833855,0.001429523,0.0008564204,0.00004542069,0.000010283688,0.000009531405,0.00475558,0.7164165,0.13528636,0.13856582,0.002196934,0.00035982873],"about_ca_topic_score_codex":0.000017844784,"about_ca_topic_score_gemma":0.000009305266,"teacher_disagreement_score":0.93402445,"about_ca_system_score_codex":0.000024614283,"about_ca_system_score_gemma":0.00007566471,"threshold_uncertainty_score":0.9995287},"labels":[],"label_agreement":null},{"id":"W3033089188","doi":"10.48550/arxiv.2006.02585","title":"Online mirror descent and dual averaging: keeping pace in the dynamic case","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pace; Dual (grammatical number); Descent (aeronautics); Stochastic gradient descent; Computer science; Control theory (sociology); Artificial intelligence; Geodesy; Aerospace engineering; Engineering; Geography; Art","score_opus":0.31241003091884384,"score_gpt":0.3382989221110649,"score_spread":0.025888891192221042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033089188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.915315,0.00015236744,0.0817663,0.001689316,0.00022245932,0.0005552041,0.00010593694,0.00004961033,0.00014382189],"genre_scores_gemma":[0.9979123,0.00022636389,0.0010136843,0.0002021039,0.00003977959,0.0000011475306,0.000019974023,0.00002076934,0.00056388037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650604,0.0006649466,0.00038994438,0.0014673404,0.0005011971,0.00047055932],"domain_scores_gemma":[0.9968219,0.0014304091,0.00025520608,0.0010513414,0.00021494464,0.0002262261],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014082977,0.00031481887,0.0004507557,0.00051747274,0.00025204956,0.0002692153,0.0012902898,0.00020363291,0.000061691004],"category_scores_gemma":[0.0010981814,0.00025745408,0.0001513125,0.0014018428,0.00031818333,0.00027568854,0.002256258,0.0014515828,0.000070645096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010910942,0.0017152049,0.034846183,0.00040562515,0.00037680558,0.42111182,0.019065375,0.46433637,0.00029823734,0.007642436,0.0012089561,0.04790188],"study_design_scores_gemma":[0.0010019777,0.00007635602,0.013745056,0.000091676266,0.00004215076,0.0005250238,0.0074816723,0.9220318,0.00001354341,0.05320464,0.0012898545,0.000496239],"about_ca_topic_score_codex":0.0004889073,"about_ca_topic_score_gemma":0.0022193776,"teacher_disagreement_score":0.45769542,"about_ca_system_score_codex":0.0002834642,"about_ca_system_score_gemma":0.0002234999,"threshold_uncertainty_score":0.9999878},"labels":[],"label_agreement":null},{"id":"W3035741541","doi":"","title":"Fiduciary Bandits","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fiduciary; Recommender system; Computer science; Incentive; Ask price; Constraint (computer-aided design); Action (physics); Face (sociological concept); Ex-ante; Operations research; Mathematical optimization; Risk analysis (engineering); Economics; Microeconomics; Business; Machine learning; Engineering; Mathematics; Finance; Law","score_opus":0.30271457978874516,"score_gpt":0.47533798022670787,"score_spread":0.1726234004379627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035741541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060510565,0.00021937909,0.3856631,0.17820041,0.0023562284,0.00060145924,0.00016943917,0.00064232474,0.3716371],"genre_scores_gemma":[0.9906839,0.000031260042,0.00085371453,0.0013217247,0.00044450752,0.000008852472,0.00003451917,0.000016798303,0.0066047325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620414,0.0002518377,0.0004148724,0.0006018264,0.0022717125,0.00025563163],"domain_scores_gemma":[0.9980932,0.0007411125,0.00018297973,0.00021215218,0.00055583514,0.00021471792],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00084084907,0.00016071423,0.00021294394,0.00023495247,0.00016972036,0.00039181914,0.0013282053,0.00005733477,0.012677291],"category_scores_gemma":[0.00848818,0.00012609252,0.000095529394,0.000411148,0.00007612382,0.00036544917,0.00029892425,0.0008323403,0.004304257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011049977,0.00022169462,0.059213206,0.000011366907,0.00017588183,0.0004806947,0.0033766888,0.10910391,0.0068074856,0.074355066,0.016175397,0.7289736],"study_design_scores_gemma":[0.0006390392,0.00029052995,0.0052172435,0.000020096762,0.0000024477918,0.000009867872,0.0003484272,0.81740594,0.0006770996,0.017251084,0.1578965,0.00024173321],"about_ca_topic_score_codex":0.000022697113,"about_ca_topic_score_gemma":0.000008809679,"teacher_disagreement_score":0.93017334,"about_ca_system_score_codex":0.000047534184,"about_ca_system_score_gemma":0.00008291982,"threshold_uncertainty_score":0.99986374},"labels":[],"label_agreement":null},{"id":"W3037507370","doi":"10.65109/hjfz7394","title":"Alternative Function Approximation Parameterizations for Solving Games: An Analysis of ƒ-Regression Counterfactual Regret Minimization","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Softmax function; Counterfactual thinking; Approximation error; Function approximation; Reinforcement learning; Perfect information; Approximation algorithm; Mathematical optimization; Computer science; Function (biology); Mathematics; Applied mathematics; Mathematical economics; Artificial intelligence; Artificial neural network; Machine learning","score_opus":0.19774246992382122,"score_gpt":0.44301282600521824,"score_spread":0.24527035608139702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037507370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07203786,0.000016867547,0.9267403,0.000351497,0.00010481694,0.00046500136,0.00013928012,0.000049251874,0.00009513975],"genre_scores_gemma":[0.96919787,0.000009762889,0.0298926,0.00017387983,0.00008465558,0.000050828403,0.00039531238,0.0000154844,0.0001796363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968563,0.00016545397,0.0007781563,0.00062536506,0.0013646347,0.00021011532],"domain_scores_gemma":[0.99630094,0.0013132835,0.00053348346,0.0003952419,0.0013057232,0.00015131145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008279207,0.00015377844,0.00042779036,0.00071317446,0.00016810294,0.00018657644,0.00044171684,0.000114657945,0.00064953195],"category_scores_gemma":[0.0048861066,0.00010925946,0.00020544649,0.0027635428,0.00009919393,0.0013326096,0.00008081588,0.00011591193,0.000013928366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008800055,0.00021593977,0.0039353003,0.000027452617,0.0006201503,8.834721e-7,0.0064788847,0.8955401,0.0100225955,0.0019620222,0.0011190583,0.07919757],"study_design_scores_gemma":[0.00040909718,0.000399708,0.0022276845,0.000008055945,0.0001714402,2.0496897e-7,0.002567073,0.9831156,0.0072797346,0.0033273655,0.0003734612,0.00012057972],"about_ca_topic_score_codex":0.000019413157,"about_ca_topic_score_gemma":0.000026450021,"teacher_disagreement_score":0.89716,"about_ca_system_score_codex":0.0000542094,"about_ca_system_score_gemma":0.000061803774,"threshold_uncertainty_score":0.71119195},"labels":[],"label_agreement":null},{"id":"W3041060701","doi":"10.48550/arxiv.2007.05477","title":"Exponential Convergence of Gradient Methods in Concave Network Zero-sum Games","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Zero-sum game; Zero (linguistics); Lipschitz continuity; Generalization; Convergence (economics); Mathematics; Nash equilibrium; Regular polygon; Fictitious play; Applied mathematics; Mathematical optimization; Mathematical economics; Pure mathematics; Mathematical analysis","score_opus":0.3396832296260758,"score_gpt":0.3713927499233881,"score_spread":0.03170952029731233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041060701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11348493,0.00027702047,0.8831278,0.00011537136,0.0014900458,0.0005618619,0.00005607194,0.000054254342,0.00083265256],"genre_scores_gemma":[0.98270684,0.00040345488,0.015136461,0.000043787793,0.00014899705,0.0000027704175,0.00001492722,0.000029220224,0.0015135346],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994219,0.0015400351,0.0009352211,0.0019115271,0.00068871444,0.000705514],"domain_scores_gemma":[0.99450356,0.0022775072,0.0008131146,0.0014548161,0.00058352784,0.00036746662],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029585992,0.00040971563,0.001092569,0.0006231275,0.00010820773,0.00008359731,0.0028621564,0.00038336075,0.0006577493],"category_scores_gemma":[0.0019077521,0.00041448834,0.00044428295,0.0026000158,0.0006705833,0.00030794166,0.003606486,0.0011971268,0.00015798134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044659595,0.00014102928,0.015409019,0.00006926383,0.00014150538,0.0008043414,0.00074512925,0.960202,0.00039827888,0.012648857,0.0026499801,0.006344029],"study_design_scores_gemma":[0.0011601327,0.00016077538,0.009594063,0.00013894503,0.000060560156,0.0000036577,0.0008969449,0.5047227,0.0020747893,0.47711486,0.003411478,0.0006611012],"about_ca_topic_score_codex":0.00023472504,"about_ca_topic_score_gemma":0.00009971948,"teacher_disagreement_score":0.8692219,"about_ca_system_score_codex":0.00027692114,"about_ca_system_score_gemma":0.0004103924,"threshold_uncertainty_score":0.9998307},"labels":[],"label_agreement":null},{"id":"W3043040027","doi":"10.48550/arxiv.2007.06699","title":"Fair Algorithms for Multi-Agent Multi-Armed Bandits","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Sublinear function; Multi-armed bandit; Computer science; Nash equilibrium; Mathematical optimization; Mathematical economics; Social Welfare; Artificial intelligence; Algorithm; Mathematics; Machine learning; Law; Discrete mathematics; Political science","score_opus":0.5827502268841479,"score_gpt":0.3803343093108259,"score_spread":0.202415917573322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043040027","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009896663,0.00014815951,0.98452556,0.00038468337,0.001737654,0.002052447,0.0008067934,0.00029183418,0.0001561817],"genre_scores_gemma":[0.9149038,0.00028618774,0.06104882,0.00022534408,0.00059263245,0.000032427084,0.00018831024,0.00013655063,0.022585927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932382,0.00046317524,0.00086313806,0.003426114,0.0009203431,0.0010890063],"domain_scores_gemma":[0.9933376,0.0016285368,0.0007265998,0.0020442926,0.0013957381,0.00086728216],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001672729,0.00074460445,0.0011342767,0.0008643302,0.00051003805,0.00039518255,0.0042278143,0.0006638408,0.00039393795],"category_scores_gemma":[0.0037777838,0.0007204695,0.0009074977,0.001667829,0.00046215375,0.00053471455,0.0037398592,0.0013795363,0.0012556642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011696572,0.001641882,0.005257623,0.00037028457,0.0010093697,0.002791736,0.0019839746,0.92515904,0.0004145593,0.003861289,0.02172221,0.03461836],"study_design_scores_gemma":[0.0034074152,0.00014729469,0.002344492,0.000056271198,0.00008894313,0.0000041256476,0.0007850207,0.9532309,0.0004943488,0.022546735,0.016030725,0.0008636887],"about_ca_topic_score_codex":0.0000990228,"about_ca_topic_score_gemma":0.00013151081,"teacher_disagreement_score":0.92347676,"about_ca_system_score_codex":0.00061094505,"about_ca_system_score_gemma":0.0006151597,"threshold_uncertainty_score":0.99952465},"labels":[],"label_agreement":null},{"id":"W3043739328","doi":"10.65109/laqv4730","title":"The Effect of Strategic Noise in Linear Regression","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nash equilibrium; Computer science; Bounded function; Regularization (linguistics); Outcome (game theory); Focus (optics); Mathematical economics; Mathematical optimization; Algorithm; Artificial intelligence; Mathematics","score_opus":0.21707434903919445,"score_gpt":0.49515051276018374,"score_spread":0.2780761637209893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043739328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86683726,0.0046952693,0.06103702,0.012997899,0.0055458713,0.006350375,0.00014983285,0.00025705763,0.04212943],"genre_scores_gemma":[0.99400836,0.0002411467,0.0016023903,0.000016796495,0.00019015868,0.000066917564,0.000008648264,0.000024103256,0.0038414702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99412286,0.0010639937,0.0009526447,0.0008102414,0.0027094958,0.0003407826],"domain_scores_gemma":[0.9903832,0.007497916,0.00039284895,0.0013279873,0.00026614626,0.00013190496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005341842,0.00025476082,0.000658526,0.00026626987,0.000095100484,0.00018742179,0.0023704593,0.0002488246,0.00024350609],"category_scores_gemma":[0.0066996575,0.00010730791,0.00021929573,0.00089198194,0.0002551698,0.00008694312,0.0023284645,0.0013021693,0.00027591115],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056459894,0.0002603795,0.027123429,0.0007755881,0.0002020557,0.00077090017,0.0016958693,0.1817274,0.007875704,0.0021575992,0.024817515,0.7469476],"study_design_scores_gemma":[0.0023999298,0.0014961509,0.0068836208,0.00060841837,0.000019947367,0.0000068468253,0.0013024518,0.5373761,0.054376405,0.38847247,0.0063097556,0.0007479044],"about_ca_topic_score_codex":0.00009479389,"about_ca_topic_score_gemma":0.00009426647,"teacher_disagreement_score":0.74619967,"about_ca_system_score_codex":0.00006929041,"about_ca_system_score_gemma":0.0002526839,"threshold_uncertainty_score":0.80206},"labels":[],"label_agreement":null},{"id":"W3043761458","doi":"","title":"Beyond Prioritized Replay: Sampling States in Model-Based RL via Simulated Priorities","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Sampling (signal processing); Key (lock); Benchmark (surveying); Equivalence (formal languages); Sample (material); Ideal (ethics); Mathematical optimization; Sampling bias; Sample size determination; Mathematics; Statistics; Telecommunications","score_opus":0.21948416268667387,"score_gpt":0.32630614007900377,"score_spread":0.1068219773923299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043761458","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46088365,0.00019009974,0.537587,0.00007154291,0.0003175289,0.00048889284,0.00008984642,0.00012362903,0.00024781987],"genre_scores_gemma":[0.98883903,0.00022151663,0.0079429215,0.00010285274,0.0000765992,0.000002653579,0.00014741416,0.000067633875,0.0025993653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934272,0.0006972214,0.0010457833,0.002789099,0.0010392653,0.0010014123],"domain_scores_gemma":[0.9920746,0.0030247497,0.0005649668,0.0024256657,0.0015328593,0.000377121],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024224157,0.00063374534,0.0012135884,0.0016444259,0.00031106433,0.0006161941,0.0023354786,0.0006604522,0.0003231331],"category_scores_gemma":[0.0021018346,0.00068647286,0.00046266153,0.0027584026,0.00046587051,0.00074874103,0.002323248,0.0018536049,0.00008176857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027790607,0.00012237272,0.003966434,0.00005672121,0.000045626726,0.00092545804,0.0003842675,0.99241436,0.00008970419,0.0003489099,0.00003827983,0.0013299657],"study_design_scores_gemma":[0.0014664521,0.000036377693,0.0005640098,0.00015148707,0.000028578943,0.0000024148085,0.00072510866,0.8177481,0.0003901781,0.17819603,0.00010557081,0.00058567105],"about_ca_topic_score_codex":0.00040727577,"about_ca_topic_score_gemma":0.00054622116,"teacher_disagreement_score":0.5296441,"about_ca_system_score_codex":0.0008747295,"about_ca_system_score_gemma":0.001465468,"threshold_uncertainty_score":0.9995586},"labels":[],"label_agreement":null},{"id":"W3046075819","doi":"10.5539/ijsp.v9n5p40","title":"Estimating Smooth and Convex Functions","year":2020,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Differentiable function; Estimator; Convex function; Regular polygon; Function (biology); Combinatorics; Applied mathematics; Convex combination; Convex optimization; Mathematical optimization; Mathematical analysis; Statistics","score_opus":0.11626796317296399,"score_gpt":0.42407798410454783,"score_spread":0.3078100209315838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046075819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052857734,0.00010829731,0.9414579,0.004772313,0.00040486956,0.00006492547,0.00021651597,0.0000039648894,0.000113447815],"genre_scores_gemma":[0.7694715,0.000026046595,0.22994904,0.0002125388,0.00028602115,0.0000010436114,0.0000025980864,0.000004423663,0.000046783116],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980366,0.000083928404,0.00055711623,0.00017285986,0.0010617481,0.00008771882],"domain_scores_gemma":[0.9965065,0.0014163523,0.0003020439,0.000069806396,0.0015245257,0.0001807548],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012536516,0.00006534,0.00017190697,0.00007524106,0.00006956814,0.0002349073,0.0002744075,0.000023452818,0.00021446605],"category_scores_gemma":[0.010013026,0.00004714605,0.000026302803,0.00010954134,0.0002005265,0.00025509106,0.00013228488,0.0002006917,0.000007916704],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038909665,0.00010601163,0.049748164,0.000029564306,0.00012084002,0.00013136715,0.0015724665,0.005033501,0.00022523299,0.008372271,0.008082295,0.9261892],"study_design_scores_gemma":[0.0010003546,0.0004444328,0.06283859,0.00002454907,0.000015828524,0.00013996391,0.00034012884,0.24001367,0.000049218917,0.67680615,0.018188378,0.00013874794],"about_ca_topic_score_codex":0.0000064966375,"about_ca_topic_score_gemma":0.000004374672,"teacher_disagreement_score":0.9260504,"about_ca_system_score_codex":0.0000271972,"about_ca_system_score_gemma":0.00008916654,"threshold_uncertainty_score":0.99832606},"labels":[],"label_agreement":null},{"id":"W3046729600","doi":"","title":"Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent","year":2020,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Regret; Gradient descent; Bounded function; Descent (aeronautics); Mathematical optimization; Computer science; Property (philosophy); Mathematics; Applied mathematics; Artificial intelligence; Mathematical analysis; Engineering; Machine learning","score_opus":0.12255929215823734,"score_gpt":0.37242527432546296,"score_spread":0.2498659821672256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046729600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29104814,0.00020223792,0.70094204,0.0032328703,0.00016337582,0.00047350486,0.000010070558,0.00022117698,0.0037065998],"genre_scores_gemma":[0.99340713,0.0000828188,0.0043368465,0.00035383727,0.00010847446,0.00001623166,0.000003187953,0.00003278395,0.001658682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598116,0.00078627164,0.0004193707,0.00087406515,0.0014303306,0.0005088309],"domain_scores_gemma":[0.9938733,0.004654675,0.0003015758,0.00042351516,0.00035193187,0.00039501954],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018585805,0.00026693227,0.0003802536,0.00014103313,0.0003727873,0.00039693603,0.0007438383,0.00007304096,0.0007353574],"category_scores_gemma":[0.010422448,0.0001854845,0.00006096055,0.00046313295,0.00040279803,0.00026273102,0.0003203344,0.00081938657,0.00030507895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001941601,0.0001154919,0.024885422,0.0000413012,0.00008392719,0.00025232031,0.0062602623,0.017319059,0.0019015326,0.013196773,0.00038051757,0.93362176],"study_design_scores_gemma":[0.0065039345,0.005742114,0.05327256,0.000967431,0.000065467066,0.00008653921,0.020548046,0.77997667,0.0062157097,0.09442037,0.030050732,0.002150409],"about_ca_topic_score_codex":0.0000077037475,"about_ca_topic_score_gemma":0.0000063500884,"teacher_disagreement_score":0.9314714,"about_ca_system_score_codex":0.00004765789,"about_ca_system_score_gemma":0.000094584975,"threshold_uncertainty_score":0.9979132},"labels":[],"label_agreement":null},{"id":"W3082716386","doi":"10.48550/arxiv.2008.13773","title":"Beyond variance reduction: Understanding the true impact of baselines on policy optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reduction (mathematics); Variance reduction; Variance (accounting); Econometrics; Economics; Computer science; Environmental science; Mathematics","score_opus":0.33460323019835514,"score_gpt":0.35245186452443816,"score_spread":0.017848634326083024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082716386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064943903,0.00003337699,0.9888022,0.0012504255,0.00040870125,0.00042259853,0.00013083583,0.000054038945,0.0024034393],"genre_scores_gemma":[0.99685603,0.00022449008,0.00103521,0.000038419188,0.00048133385,9.770741e-7,0.000021884987,0.000025431696,0.0013162108],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970043,0.00049006526,0.0004493984,0.0011074943,0.0006107429,0.00033801576],"domain_scores_gemma":[0.9963268,0.000988684,0.0006282122,0.0013271159,0.00053540914,0.00019375581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011272618,0.00030349768,0.00046130197,0.0007345846,0.00031733408,0.00016784556,0.0017322964,0.00022892305,0.0003519463],"category_scores_gemma":[0.0022548595,0.0002219631,0.00041450947,0.0031089876,0.0004244723,0.0003630004,0.0008768512,0.00074066897,0.000059352446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022684521,0.00004153176,0.00013364266,0.000009995124,0.00007823712,0.000031465705,0.00024141608,0.9764067,0.000023136614,0.021806555,0.0006471776,0.00035332103],"study_design_scores_gemma":[0.00035226342,0.00013476287,0.0002228799,0.00003859147,0.000027987091,0.0000047669937,0.0009604284,0.77407116,0.0000893562,0.22385208,0.000049092214,0.00019665138],"about_ca_topic_score_codex":0.00018238022,"about_ca_topic_score_gemma":0.000005172486,"teacher_disagreement_score":0.99036163,"about_ca_system_score_codex":0.0010176378,"about_ca_system_score_gemma":0.0008451728,"threshold_uncertainty_score":0.9051392},"labels":[],"label_agreement":null},{"id":"W3084085014","doi":"","title":"Bandit Online Learning of Nash Equilibria in Monotone Games","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nash equilibrium; Monotonic function; Monotone polygon; Regular polygon; Mathematical optimization; Action (physics); Extension (predicate logic); Mathematical economics; Function (biology); Mathematics; Zero (linguistics); Best response; Computer science; Zero-sum game","score_opus":0.2829365411725819,"score_gpt":0.32831893201346246,"score_spread":0.04538239084088058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084085014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87482536,0.00014337915,0.123091266,0.00020380602,0.0002590029,0.0003883926,0.00009630588,0.00007763375,0.0009148703],"genre_scores_gemma":[0.9937565,0.00029160423,0.00068623124,0.00002103048,0.00011482419,8.9286107e-7,0.000046828227,0.000032690758,0.005049442],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958888,0.0005729373,0.0007332119,0.0016131344,0.00068660825,0.0005052511],"domain_scores_gemma":[0.9961521,0.0013889215,0.0006395408,0.0010944041,0.00046043796,0.0002645954],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011994514,0.0003484053,0.00092064554,0.0010459215,0.00007719279,0.00009428375,0.0024216953,0.00035575934,0.0005487799],"category_scores_gemma":[0.0031932876,0.00035576467,0.00032049592,0.0023273092,0.00036603288,0.0003977472,0.0036045723,0.0017316674,0.00020953339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000390633,0.00022392873,0.037461527,0.00007212615,0.00007795692,0.00086549134,0.000616703,0.95241624,0.0007677011,0.0019289746,0.00040176048,0.004776976],"study_design_scores_gemma":[0.001201799,0.00016419742,0.020107085,0.00014769787,0.000027854245,0.0000025259908,0.0015388108,0.8588946,0.00056088815,0.114763275,0.0021099427,0.0004813614],"about_ca_topic_score_codex":0.00021078932,"about_ca_topic_score_gemma":0.00013466606,"teacher_disagreement_score":0.12240504,"about_ca_system_score_codex":0.000235215,"about_ca_system_score_gemma":0.00033698694,"threshold_uncertainty_score":0.99988943},"labels":[],"label_agreement":null},{"id":"W3085631657","doi":"10.1287/opre.2022.2380","title":"Learning Product Rankings Robust to Fake Users","year":2022,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Leverage (statistics); Computer science; Product (mathematics); Ranking (information retrieval); Analytics; Status quo; Data science; Learning to rank; Machine learning; Artificial intelligence; Mathematics; Economics","score_opus":0.36256294639491365,"score_gpt":0.5291875609008896,"score_spread":0.16662461450597593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085631657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8243497,0.00039163182,0.099814706,0.050235946,0.0010504725,0.004988674,0.00012148791,0.00029477756,0.0187526],"genre_scores_gemma":[0.84749126,0.000013387055,0.00847573,0.00013522436,0.0002714891,0.0009768524,0.000026445281,0.000040671563,0.14256896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9869181,0.0025374547,0.0005360714,0.0011081891,0.00794044,0.0009597289],"domain_scores_gemma":[0.99489677,0.0014732652,0.00002580398,0.0011073276,0.0021672312,0.00032957495],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.018579418,0.00013893787,0.00023495358,0.0018802424,0.0054308902,0.001225635,0.0021179472,0.000031529773,0.0098890355],"category_scores_gemma":[0.02046392,0.00012041699,0.00007880164,0.007952555,0.0002196839,0.0006137092,0.0021588106,0.0018519087,0.0027535863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049947237,0.000080978876,0.00073800713,0.0000014428564,0.000007895924,0.000027207503,0.0019911858,0.9304064,0.0027730514,0.00043537744,0.022660982,0.04082753],"study_design_scores_gemma":[0.0006176202,0.00082400074,0.00263566,0.0000072010544,0.0000022073905,0.000041181414,0.015239988,0.17545182,0.0023482656,0.0011818085,0.8012902,0.00036000853],"about_ca_topic_score_codex":0.00031431872,"about_ca_topic_score_gemma":0.0003622347,"teacher_disagreement_score":0.77862924,"about_ca_system_score_codex":0.0004677001,"about_ca_system_score_gemma":0.00064781157,"threshold_uncertainty_score":0.9998112},"labels":[],"label_agreement":null},{"id":"W3085735333","doi":"10.48550/arxiv.2009.06799","title":"The Importance of Pessimism in Fixed-Dataset Policy Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Pessimism; Core (optical fiber); Computer science; Value (mathematics); Order (exchange); Mathematical optimization; Artificial intelligence; Econometrics; Economics; Machine learning; Mathematics","score_opus":0.2439048591061609,"score_gpt":0.3377463759698552,"score_spread":0.0938415168636943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085735333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025421614,0.00025369428,0.966964,0.0026102115,0.000364754,0.00080959185,0.0020392567,0.000054721746,0.0014821546],"genre_scores_gemma":[0.99657863,0.00084184087,0.0010274404,0.00010200204,0.00011954682,0.0000018574173,0.000274765,0.000021443739,0.0010324942],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970718,0.00038059187,0.00058612507,0.0010450624,0.00053880946,0.00037758678],"domain_scores_gemma":[0.99597645,0.0013315207,0.000636453,0.001519197,0.00036805792,0.00016835103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013358091,0.00023085158,0.00042671507,0.0005222058,0.00016877694,0.00012543393,0.002780929,0.00021405087,0.00014124897],"category_scores_gemma":[0.0037709689,0.00018508754,0.00014741314,0.0024382614,0.00039524143,0.00031987,0.002293832,0.0007396169,0.00006465655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008847005,0.000031037405,0.0041653686,0.00001221951,0.000017075346,0.00012655357,0.00007372678,0.9885399,0.000004813996,0.003167623,0.0029411635,0.0008320907],"study_design_scores_gemma":[0.0005474791,0.000039537386,0.0032813775,0.000038193215,0.000013005929,0.0000015675731,0.00044040687,0.8942457,0.00012541523,0.09705177,0.0039475164,0.00026805318],"about_ca_topic_score_codex":0.00019023278,"about_ca_topic_score_gemma":0.00027341378,"teacher_disagreement_score":0.971157,"about_ca_system_score_codex":0.00025344355,"about_ca_system_score_gemma":0.000650418,"threshold_uncertainty_score":0.7547651},"labels":[],"label_agreement":null},{"id":"W3087995939","doi":"10.1109/access.2020.3026237","title":"Scalable Delay-Sensitive Polling of Sensors","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Polling; Computer science; Scalability; Context (archaeology); Real-time computing; Wireless sensor network; Bandwidth (computing); Distributed computing; Computer network","score_opus":0.22623193526839752,"score_gpt":0.4665477995047696,"score_spread":0.24031586423637208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087995939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6881099,0.00009079603,0.30657643,0.0020072185,0.0003764646,0.0002586231,0.000053609638,0.000058531004,0.0024684786],"genre_scores_gemma":[0.99722004,0.000017113727,0.0017714897,0.0003435322,0.00022642678,0.000003559142,0.0000010974971,0.000016171916,0.00040059388],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967838,0.00016362999,0.0005242132,0.0005014997,0.0016824675,0.00034438667],"domain_scores_gemma":[0.9970771,0.0013370343,0.00020939282,0.00039640235,0.0007518139,0.00022822441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008342031,0.0001250943,0.00034785215,0.00019356099,0.00011058685,0.00021178547,0.001182942,0.00006667175,0.00031657686],"category_scores_gemma":[0.002228618,0.00009657992,0.000101401114,0.0017594198,0.0001808299,0.0008688076,0.00026243515,0.00022019536,0.0004595571],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016045958,0.0004076107,0.037822038,0.0001261931,0.00031524224,0.0014549445,0.009485265,0.5038588,0.083896145,0.00089240586,0.07119795,0.2889388],"study_design_scores_gemma":[0.00093909854,0.0001832567,0.0041563567,0.000033714485,0.000014371315,0.00001996748,0.0013284634,0.15891865,0.81868523,0.008984256,0.0063390536,0.00039758647],"about_ca_topic_score_codex":0.00006545214,"about_ca_topic_score_gemma":0.000009310006,"teacher_disagreement_score":0.7347891,"about_ca_system_score_codex":0.000030854066,"about_ca_system_score_gemma":0.00009864106,"threshold_uncertainty_score":0.59068304},"labels":[],"label_agreement":null},{"id":"W3096455539","doi":"10.1111/poms.13296","title":"Optimal Bayesian Demand Learning over Short Horizons","year":2020,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Bayesian probability; Asymptotically optimal algorithm; Dynamic pricing; Revenue; Economics; Optimal stopping; Bayesian inference; Mathematical optimization; Computer science; Mathematical economics; Microeconomics; Mathematics; Finance; Artificial intelligence","score_opus":0.07210873665177904,"score_gpt":0.3837089765238756,"score_spread":0.31160023987209656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096455539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040021054,0.00018996408,0.93232137,0.023175409,0.00033585564,0.00071811845,0.0000029926048,0.00012023047,0.003114977],"genre_scores_gemma":[0.9657929,0.00024048677,0.019557318,0.00022479282,0.00038141923,0.000062655046,0.0000083348905,0.000013427049,0.013718664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799573,0.000121842684,0.00030192386,0.00063041155,0.0007573987,0.00019267833],"domain_scores_gemma":[0.9993919,0.000036192057,0.000023803235,0.00024338695,0.00015574679,0.00014894051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008225965,0.00010797,0.00013238823,0.00018362504,0.00058554113,0.00044787457,0.00020170948,0.000025570862,0.0004770905],"category_scores_gemma":[0.0008984808,0.00008802363,0.000034378918,0.0007347851,0.00008054593,0.00057788915,0.00022693876,0.00018213927,0.00013847342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051905972,0.00008895678,0.0025580253,0.000020914888,0.000070726426,0.000019916723,0.0015571031,0.81355274,0.00051331724,0.0031771648,0.018572967,0.15981628],"study_design_scores_gemma":[0.00044088496,0.00027244716,0.0105862655,0.000015520827,0.000041878782,0.000014468775,0.0054927776,0.607793,0.001483631,0.00062349654,0.37280846,0.00042718122],"about_ca_topic_score_codex":0.0000027640353,"about_ca_topic_score_gemma":0.00001573508,"teacher_disagreement_score":0.92577183,"about_ca_system_score_codex":0.000026429843,"about_ca_system_score_gemma":0.000014232226,"threshold_uncertainty_score":0.52238065},"labels":[],"label_agreement":null},{"id":"W3098528340","doi":"","title":"Differentiable Meta-Learning of Bandit Policies.","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Differentiable function; Meta learning (computer science); Computer science; Artificial intelligence; Mathematics; Economics","score_opus":0.23017559285573402,"score_gpt":0.4086101303330043,"score_spread":0.17843453747727028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098528340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15846716,0.002903038,0.8177622,0.0050969147,0.0009163996,0.0016166351,0.0001010901,0.0006649833,0.012471562],"genre_scores_gemma":[0.9986326,0.000005126721,0.0001966844,0.00019728784,0.00010545941,0.00002776804,0.000014183431,0.0000091649545,0.0008117356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960571,0.00017324973,0.0012435801,0.00019677069,0.0020320562,0.000297254],"domain_scores_gemma":[0.9975045,0.0003063678,0.00087338395,0.00021407865,0.00093067763,0.00017099458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009582213,0.00016097094,0.0005319765,0.00029272021,0.00024111572,0.000807128,0.0006266476,0.0000719775,0.00020309228],"category_scores_gemma":[0.0024657983,0.00010579439,0.00013877806,0.0013181594,0.000091067355,0.0038500775,0.00014406073,0.00028078788,0.00022612768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021637873,0.00006583078,0.0049295328,0.0015226007,0.00036337817,0.0000046060454,0.024643382,0.7862515,0.0023875784,0.0014357079,0.01888719,0.15929233],"study_design_scores_gemma":[0.00039320329,0.00012901788,0.0006521727,0.000024345798,0.00004980342,0.000011603734,0.0035320716,0.93331844,0.0019927232,0.00017213174,0.05954936,0.00017514195],"about_ca_topic_score_codex":0.000043045256,"about_ca_topic_score_gemma":4.654057e-7,"teacher_disagreement_score":0.84016544,"about_ca_system_score_codex":0.000029079754,"about_ca_system_score_gemma":0.0000825762,"threshold_uncertainty_score":0.77831537},"labels":[],"label_agreement":null},{"id":"W3101144313","doi":"","title":"Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Markov decision process; Bounding overwatch; Inverse; Combinatorics; Adversarial system; Hessian matrix; Mathematics; Markov chain; Robustness (evolution); Computer science; Diagonal; Discrete mathematics; Markov process; Mathematical optimization; Artificial intelligence; Applied mathematics; Statistics","score_opus":0.05573393714338376,"score_gpt":0.3323731971055618,"score_spread":0.27663925996217803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101144313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056859635,0.00019028688,0.9401946,0.001385253,0.00018991818,0.000573693,0.000012766678,0.0002158414,0.0003780277],"genre_scores_gemma":[0.9991298,0.000002075646,0.0002960372,0.00021558584,0.00020093592,0.000021988082,0.000020768544,0.000011790994,0.0001010631],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99700737,0.00015083875,0.000714143,0.00027779175,0.0015568818,0.0002929909],"domain_scores_gemma":[0.9981296,0.00044521948,0.00040425966,0.0001226448,0.0006789387,0.00021933828],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006617566,0.00017722673,0.00028851916,0.00021703275,0.00046384468,0.0014177728,0.00025985762,0.000083055646,0.00002285542],"category_scores_gemma":[0.0016177526,0.00012422728,0.00003076376,0.0008631811,0.00013303725,0.004224517,0.000045579574,0.00037685287,0.00013124084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023770369,0.0000052685164,0.000032531687,0.00011235886,0.000005266985,0.000007305312,0.0086055305,0.87932646,0.000066278946,0.000023137958,0.00010333931,0.1114748],"study_design_scores_gemma":[0.00083877135,0.0003253031,0.000043834098,0.00006481864,0.0000078579915,0.000101698664,0.005735172,0.98721343,0.00002349407,0.000040485935,0.005439867,0.00016528381],"about_ca_topic_score_codex":0.00001947358,"about_ca_topic_score_gemma":0.0000018087183,"teacher_disagreement_score":0.9422701,"about_ca_system_score_codex":0.000044206805,"about_ca_system_score_gemma":0.000106966385,"threshold_uncertainty_score":0.9996188},"labels":[],"label_agreement":null},{"id":"W3101613519","doi":"","title":"Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Markov decision process; Estimator; Upper and lower bounds; Computer science; Adversarial system; Mathematical optimization; Simple (philosophy); Schedule; Mathematics; Markov process; Artificial intelligence; Machine learning; Statistics","score_opus":0.49969183307741133,"score_gpt":0.32662246015581875,"score_spread":0.17306937292159258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101613519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52458197,0.000068500034,0.4694996,0.0019945293,0.0008187478,0.0011620626,0.0011674418,0.00016672851,0.000540451],"genre_scores_gemma":[0.99473184,0.000043276374,0.0021197784,0.00020904612,0.00036532313,0.0000014883332,0.000075092605,0.000021110885,0.002433041],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964843,0.00024311017,0.00038316278,0.001791346,0.0005937628,0.000504312],"domain_scores_gemma":[0.9954483,0.001765795,0.00021952318,0.0014794086,0.000595301,0.0004916547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001790659,0.00024504002,0.0004297595,0.00017249277,0.000382919,0.00023296817,0.002075097,0.00015050487,0.00043252905],"category_scores_gemma":[0.005999921,0.00021900806,0.0001041269,0.0009469407,0.00049104646,0.0013766052,0.0014753919,0.00029883286,0.00037561732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030241478,0.002124143,0.15233266,0.00066760526,0.0016019618,0.0038354548,0.007445528,0.32650432,0.0020928902,0.11031127,0.29626667,0.06657602],"study_design_scores_gemma":[0.008123971,0.00093882205,0.009787599,0.000020126881,0.00013645276,0.000010807089,0.0011946996,0.77010965,0.0005519349,0.1308418,0.07729671,0.000987446],"about_ca_topic_score_codex":0.00010835049,"about_ca_topic_score_gemma":0.000100843565,"teacher_disagreement_score":0.4701499,"about_ca_system_score_codex":0.00012880491,"about_ca_system_score_gemma":0.0002108631,"threshold_uncertainty_score":0.89308894},"labels":[],"label_agreement":null},{"id":"W3102232031","doi":"","title":"Adaptive Search Algorithms for Discrete Stochastic Optimization: A Smooth Best-Response Approach","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"Army Research Office; Canada Research Chairs","keywords":"Convergence (economics); Mathematical optimization; Set (abstract data type); Local optimum; Computer science; Random search; Stochastic optimization; Sampling (signal processing); Algorithm; Finite set; Scheme (mathematics); Mathematics","score_opus":0.20159379791926774,"score_gpt":0.4412203572855472,"score_spread":0.23962655936627947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102232031","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024165645,0.000058550708,0.9944932,0.0018913969,0.00014304287,0.0019065237,0.00022276126,0.00009356699,0.0009493396],"genre_scores_gemma":[0.14189196,0.000011078069,0.77684647,0.00010929922,0.0004087698,0.0011284978,0.000012063072,0.00009170392,0.07950018],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937836,0.0005685629,0.0007040494,0.0012031998,0.0028331447,0.0009074495],"domain_scores_gemma":[0.987415,0.0094946055,0.00014351128,0.0010650526,0.0014637661,0.00041802315],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005356803,0.00029738856,0.00045979398,0.0006198692,0.00040226235,0.0003073839,0.0014421407,0.00014425664,0.0011847271],"category_scores_gemma":[0.0077337148,0.0001575651,0.00021284059,0.0012786612,0.00053393736,0.00092052645,0.0004223527,0.00017722155,0.0004940223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056340815,0.00030318994,0.00002834956,0.000006509646,0.00007025193,0.000013603773,0.00057660165,0.68715096,0.00035402447,0.0015235496,0.0036481428,0.3006907],"study_design_scores_gemma":[0.002325294,0.00091623183,0.000098195094,0.000027802549,0.0000096073245,0.000016637028,0.0017455211,0.9855549,0.00044143046,0.006135134,0.002347533,0.0003817401],"about_ca_topic_score_codex":0.000013888255,"about_ca_topic_score_gemma":0.0000037477162,"teacher_disagreement_score":0.30030897,"about_ca_system_score_codex":0.00020270218,"about_ca_system_score_gemma":0.0003965241,"threshold_uncertainty_score":0.9997283},"labels":[],"label_agreement":null},{"id":"W3102774599","doi":"","title":"Online algorithm for unsupervised sequential selection with contextual information","year":2020,"lang":"en","type":"article","venue":"OpenBU (Boston University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regret; Context (archaeology); Artificial intelligence; Selection (genetic algorithm); Unsupervised learning; Machine learning; Mathematical optimization; Algorithm; Mathematics","score_opus":0.11547673814735646,"score_gpt":0.3492813364494446,"score_spread":0.23380459830208813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102774599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012968207,0.0000055779515,0.98207015,0.0016700081,0.000097722375,0.00084636477,0.00031940508,0.0000843566,0.0019381862],"genre_scores_gemma":[0.5573368,0.00008703339,0.3918769,0.0042571155,0.0014733388,0.000025090823,0.0017120301,0.00013479963,0.043096848],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979124,0.000117408905,0.0002829707,0.00039320538,0.00097404484,0.0003199366],"domain_scores_gemma":[0.9980056,0.00030855768,0.00017084414,0.00020514015,0.0010512191,0.00025863605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003599782,0.00016099874,0.00026317898,0.00042519855,0.00034960097,0.00023120827,0.0007377756,0.00009116485,0.00042007718],"category_scores_gemma":[0.00042902125,0.00013665736,0.00009025106,0.0018959244,0.00012900568,0.002818054,0.00018613311,0.00018773123,0.00015965257],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00256987,0.00023407515,0.00058460946,0.0000238195,0.00015421037,0.000075755415,0.0026173552,0.008900212,0.00090553926,0.0017136155,0.014618531,0.96760243],"study_design_scores_gemma":[0.004496676,0.0011311474,0.00033105776,0.000010462631,0.000029112649,0.0000116569045,0.0061471383,0.24284646,0.0022923802,0.00015051874,0.74224347,0.00030992064],"about_ca_topic_score_codex":0.000047631354,"about_ca_topic_score_gemma":0.00012676834,"teacher_disagreement_score":0.9672925,"about_ca_system_score_codex":0.00015449218,"about_ca_system_score_gemma":0.00029398425,"threshold_uncertainty_score":0.5572725},"labels":[],"label_agreement":null},{"id":"W3105983076","doi":"","title":"Comparator-adaptive Convex Bandits","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Comparator; Regret; Norm (philosophy); Mathematical optimization; Lipschitz continuity; Regular polygon; Convex optimization; Convex function; Estimator; Computer science; Oracle; Mathematics; Algorithm; Machine learning; Engineering; Statistics","score_opus":0.4560665325218811,"score_gpt":0.30483801282542755,"score_spread":0.15122851969645357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105983076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26694858,0.000068006775,0.72209007,0.0007409425,0.00023139479,0.00031629202,0.000047945814,0.00016688072,0.009389916],"genre_scores_gemma":[0.9962604,0.000015982589,0.00026365172,0.0003889135,0.00012417883,3.3790602e-7,0.000002629906,0.000013349759,0.002930564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771184,0.00024116706,0.0002587442,0.0009099736,0.0004695966,0.00040867433],"domain_scores_gemma":[0.9975525,0.0008415358,0.00014879159,0.0005188882,0.00043798238,0.0005003021],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00047609556,0.00018049931,0.0003475721,0.00018598809,0.00023001285,0.00010116755,0.0012769996,0.00008629189,0.0014012103],"category_scores_gemma":[0.00075677846,0.00016547102,0.00013881607,0.0021911727,0.0003142969,0.00067651307,0.00037955222,0.00031581943,0.005205475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025125165,0.0004473168,0.05834807,0.000024185836,0.00033503553,0.004774243,0.0032297792,0.6070836,0.0012304506,0.17973597,0.13274764,0.009531198],"study_design_scores_gemma":[0.0020980865,0.00044635576,0.0067230533,0.000009769405,0.00002473764,0.000008904307,0.002896757,0.8937051,0.0016684611,0.0484112,0.043448936,0.00055862835],"about_ca_topic_score_codex":0.000015068485,"about_ca_topic_score_gemma":0.000013359645,"teacher_disagreement_score":0.7293118,"about_ca_system_score_codex":0.00008667508,"about_ca_system_score_gemma":0.00011856769,"threshold_uncertainty_score":0.99951166},"labels":[],"label_agreement":null},{"id":"W3106590465","doi":"10.1109/tcyb.2022.3164399","title":"Scalable Transfer Evolutionary Optimization: Coping With Big Task Instances","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Science and Engineering Research Council; Agency for Science, Technology and Research","keywords":"Scalability; Computer science; Task (project management); Artificial intelligence; Engineering","score_opus":0.06292899291217222,"score_gpt":0.32759518318869,"score_spread":0.26466619027651783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106590465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018039417,0.00016837148,0.994007,0.0012444046,0.0008242777,0.00039811246,0.00021620726,0.00010837546,0.0012293077],"genre_scores_gemma":[0.96624756,0.00017095923,0.020025218,0.00043103483,0.00010621692,0.00028909717,0.000011469443,0.000060279166,0.012658193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99504334,0.00030187189,0.0005336201,0.0006926436,0.0029608626,0.00046763872],"domain_scores_gemma":[0.9979787,0.0007425984,0.00007294044,0.0006502353,0.0003794649,0.00017604756],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006732073,0.00022901424,0.00028846404,0.00054400746,0.0012771769,0.00015591485,0.000771112,0.0000656142,0.0029510828],"category_scores_gemma":[0.000030327043,0.00017302825,0.00011561394,0.0024998798,0.0003015422,0.00032699114,0.0000075566363,0.00065820676,0.000089872185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018628796,0.00022344243,0.000024119092,0.0000032555015,0.000027364016,0.00002171913,0.00030835017,0.9769774,0.00004558001,0.00005026978,0.0011026774,0.021029543],"study_design_scores_gemma":[0.003943375,0.0023300303,0.00022169985,0.000046402954,0.00008295156,0.00025646968,0.002923473,0.7678594,0.005404861,0.003209422,0.21255186,0.0011700508],"about_ca_topic_score_codex":0.000031570027,"about_ca_topic_score_gemma":0.000085590465,"teacher_disagreement_score":0.9739818,"about_ca_system_score_codex":0.00029288197,"about_ca_system_score_gemma":0.0003116449,"threshold_uncertainty_score":0.9979603},"labels":[],"label_agreement":null},{"id":"W3106732744","doi":"10.1007/978-3-030-60382-3_5","title":"Learning-Based Reconfigurable Access Schemes for Virtualized M2M Networks","year":2020,"lang":"en","type":"book-chapter","venue":"Wireless networks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Regret; Thresholding; Scheme (mathematics); Thompson sampling; Estimator; Network packet; Sampling scheme; Sampling (signal processing); Throughput; Real-time computing; Computer network; Artificial intelligence; Machine learning; Telecommunications","score_opus":0.12933821713852361,"score_gpt":0.398868518956655,"score_spread":0.26953030181813137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106732744","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000076282035,0.0025448503,0.924906,0.0010443253,0.0017168486,0.00201325,0.00009332118,0.0004198427,0.06725392],"genre_scores_gemma":[0.057552934,0.0018367016,0.0023896112,0.0021342016,0.0075329253,0.00078746147,0.0013691394,0.00095690915,0.92544013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990913,0.00030247724,0.0020172636,0.002591486,0.0027332532,0.0014425435],"domain_scores_gemma":[0.9869843,0.0075458223,0.0016006428,0.0016113634,0.00151365,0.00074422936],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0028362437,0.0011308276,0.0022338603,0.0006039851,0.00083065557,0.0016447512,0.0041459263,0.0016218717,0.0033506178],"category_scores_gemma":[0.001854593,0.0009901734,0.0010221904,0.0006585374,0.0005820031,0.0006308688,0.00057739124,0.0032320349,0.0004015369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079177815,0.000027784688,0.000024116369,0.00003791976,0.00016387363,0.000065301974,0.000022359072,0.62633705,0.0000019195334,0.0053140023,0.057428557,0.30978534],"study_design_scores_gemma":[0.0010966181,0.00022464558,0.0000034627478,0.00018321103,0.000040150084,0.0000029179653,0.000016415732,0.5322834,0.000027275602,0.010077779,0.45538643,0.0006576944],"about_ca_topic_score_codex":0.000010955194,"about_ca_topic_score_gemma":0.000048842026,"teacher_disagreement_score":0.9225164,"about_ca_system_score_codex":0.00024591506,"about_ca_system_score_gemma":0.0005189182,"threshold_uncertainty_score":0.99967426},"labels":[],"label_agreement":null},{"id":"W3110181803","doi":"10.1609/aaai.v35i8.16820","title":"Decentralized Multi-Agent Linear Bandits with Safety Constraints","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Science Foundation","keywords":"Regret; Computer science; Mathematical optimization; Network topology; Upper and lower bounds; Bipartite graph; Linear programming; Graph; Telecommunications network; Mathematics; Theoretical computer science; Computer network; Machine learning","score_opus":0.26689795052528154,"score_gpt":0.43374491983382724,"score_spread":0.1668469693085457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110181803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3714171,0.0002921396,0.58106154,0.017340468,0.0022294475,0.0030670327,0.0002940631,0.00027956866,0.024018634],"genre_scores_gemma":[0.9874324,0.0001317736,0.0101515185,0.00017261057,0.000070737675,0.000022108747,0.0000021091394,0.000023475459,0.0019932736],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9948213,0.000083299776,0.0011029703,0.00091815635,0.0024430219,0.00063125207],"domain_scores_gemma":[0.99388355,0.00068332365,0.0005697558,0.00053720525,0.004070977,0.00025518864],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016736067,0.0003089238,0.0005287943,0.00018767978,0.0003664207,0.0003509172,0.001861379,0.00012443149,0.0023116304],"category_scores_gemma":[0.007015855,0.00018734946,0.00018847488,0.0017599905,0.0013132184,0.00038904027,0.00044824762,0.0005330491,0.00047234475],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024336996,0.001747181,0.0051852996,0.000087914275,0.00020339455,0.00006496065,0.004172777,0.0035897011,0.10736001,0.25284672,0.0010552262,0.62125313],"study_design_scores_gemma":[0.0002780351,0.00029457986,0.0012876366,0.00031340207,0.000025691576,0.000046888,0.004934984,0.047415335,0.8890674,0.053895634,0.002007994,0.00043241112],"about_ca_topic_score_codex":0.000014012012,"about_ca_topic_score_gemma":0.00005515578,"teacher_disagreement_score":0.7817074,"about_ca_system_score_codex":0.0000958323,"about_ca_system_score_gemma":0.00048482773,"threshold_uncertainty_score":0.99860036},"labels":[],"label_agreement":null},{"id":"W3112678130","doi":"10.48550/arxiv.2012.03800","title":"Revenue Maximization and Learning in Products Ranking","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Revenue; Computer science; Product (mathematics); Regret; Ranking (information retrieval); Maximization; Purchasing; Mathematical optimization; Econometrics; Mathematics; Economics; Artificial intelligence; Machine learning; Marketing; Business","score_opus":0.2775072153582469,"score_gpt":0.29570446150170665,"score_spread":0.018197246143459744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112678130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6521058,0.00026218654,0.34446836,0.001161093,0.0003859293,0.0007079171,0.000025342262,0.000108895125,0.0007744857],"genre_scores_gemma":[0.994322,0.00032314615,0.0010537384,0.000028230312,0.00010253688,8.732169e-7,0.00001394843,0.000019935156,0.0041355873],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970692,0.0006071678,0.0002998387,0.0013821382,0.00034810053,0.00029357194],"domain_scores_gemma":[0.9981807,0.00055679865,0.0002802336,0.0005412178,0.0003194155,0.00012167576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015966179,0.00019911698,0.0003720856,0.00056753546,0.00017062384,0.00017656201,0.0007976769,0.00018937573,0.000050042225],"category_scores_gemma":[0.00556795,0.00021265313,0.000059529735,0.0017447751,0.00014677044,0.0003559589,0.0016306861,0.0013500268,0.00009077771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012081355,0.000030112873,0.026349636,0.00006709387,0.00001762724,0.0005715201,0.0008762472,0.96063083,0.000080558566,0.0010495901,0.00029283823,0.009913155],"study_design_scores_gemma":[0.001015104,0.0000678073,0.02511206,0.00017239846,0.00002419025,0.0000067707288,0.000709123,0.7688574,0.00016929918,0.19806401,0.0052823713,0.0005194172],"about_ca_topic_score_codex":0.00008367273,"about_ca_topic_score_gemma":0.00007136608,"teacher_disagreement_score":0.34341463,"about_ca_system_score_codex":0.00015533286,"about_ca_system_score_gemma":0.00019808521,"threshold_uncertainty_score":0.86717427},"labels":[],"label_agreement":null},{"id":"W3114060070","doi":"","title":"Distributed Online Optimization over a Heterogeneous Network with Any-Batch Mirror Descent","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Stochastic gradient descent; Distributed computing; Gradient descent; Artificial intelligence; Artificial neural network","score_opus":0.15685260508525875,"score_gpt":0.4146580197922753,"score_spread":0.25780541470701657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114060070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049897704,0.00005011759,0.93629694,0.0118463235,0.00025427507,0.00031601355,0.00025041157,0.0001707439,0.0009174616],"genre_scores_gemma":[0.98263663,0.000039963168,0.015223086,0.0007219948,0.00024353708,0.000014236723,0.0005605839,0.000030729327,0.0005292185],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99603087,0.00026059852,0.00049641175,0.00070429966,0.0021240697,0.00038373354],"domain_scores_gemma":[0.9979592,0.00040940262,0.00031537778,0.00024407338,0.00081472314,0.00025725475],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045992303,0.00024405969,0.00028945334,0.00014007355,0.00020588425,0.00043533792,0.00094497984,0.00007257251,0.0038658753],"category_scores_gemma":[0.001935779,0.0001807135,0.00008417863,0.00066110905,0.0000968568,0.00029444927,0.00024711498,0.0007144342,0.00016915303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005412533,0.00007341495,0.016320618,0.0000023369491,0.000045459554,0.00007897044,0.000115824325,0.97444284,0.00010864704,0.0004025049,0.00017750106,0.007690614],"study_design_scores_gemma":[0.00082968635,0.0004310286,0.00366732,0.0000428397,0.0000058861183,0.000016553842,0.000089948,0.9854024,0.00008518537,0.00059221004,0.008623037,0.00021392274],"about_ca_topic_score_codex":0.00006239656,"about_ca_topic_score_gemma":0.00009039599,"teacher_disagreement_score":0.93273896,"about_ca_system_score_codex":0.00011313449,"about_ca_system_score_gemma":0.00011120758,"threshold_uncertainty_score":0.99704474},"labels":[],"label_agreement":null},{"id":"W3114093453","doi":"10.1017/9781108571401.015","title":"The Exp3 Algorithm","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Algorithm; Computer science; Content (measure theory); Information retrieval; Mathematics","score_opus":0.09992261373328512,"score_gpt":0.31480413668482143,"score_spread":0.2148815229515363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114093453","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.415977e-7,0.00040346684,0.04138717,0.00025611377,0.0005488335,0.00055970665,0.00047690864,0.00013726766,0.95622957],"genre_scores_gemma":[0.000034902172,0.0002444971,0.00080658874,0.00009341058,0.0004403382,0.000001419882,0.00001889025,0.0000630783,0.99829686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948669,0.00017404446,0.000502852,0.0011781328,0.0027222475,0.0005558044],"domain_scores_gemma":[0.99469405,0.0019184793,0.0004620465,0.0016346164,0.0008176918,0.00047308957],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008366896,0.00047798528,0.0006097805,0.00026563756,0.0009915346,0.00045347225,0.0037010312,0.0003795776,0.000026985117],"category_scores_gemma":[0.00047576454,0.00036531762,0.00045947527,0.000050213544,0.0010173949,0.00021245187,0.0019898894,0.0012350823,0.00059009367],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093649185,0.000004858253,2.5579902e-7,0.0000060806465,0.00011317137,0.0008522704,0.000043171363,0.000009344741,0.000005856621,0.5270783,0.27258953,0.19920354],"study_design_scores_gemma":[0.00039890019,0.00006851192,0.0000044811823,0.000027097869,0.000041420506,0.000018566803,0.00014912557,0.0016799817,0.00012854271,0.00073010346,0.9963505,0.0004027152],"about_ca_topic_score_codex":0.0000307769,"about_ca_topic_score_gemma":0.0000027043527,"teacher_disagreement_score":0.723761,"about_ca_system_score_codex":0.00027728456,"about_ca_system_score_gemma":0.00031073007,"threshold_uncertainty_score":0.9998799},"labels":[],"label_agreement":null},{"id":"W3115085521","doi":"10.1017/9781108571401.005","title":"Stochastic Processes and Markov Chains","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Markov chain; Content (measure theory); Computer science; Markov process; Mathematics; Statistics; Machine learning","score_opus":0.08431149224347785,"score_gpt":0.3036433095587427,"score_spread":0.21933181731526485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115085521","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016764674,0.00044307197,0.074660264,0.00012654133,0.00016125466,0.00062642066,0.0005915484,0.00012906318,0.9232451],"genre_scores_gemma":[0.0021455628,0.00007244246,0.00029766135,0.00007336902,0.0002037296,0.0000012681551,0.000020000844,0.000054546534,0.9971314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99633026,0.00007147533,0.0003533909,0.0012220382,0.001626338,0.00039651457],"domain_scores_gemma":[0.996553,0.0010757458,0.00034011895,0.0007345148,0.0008053341,0.0004913113],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003591363,0.0004458911,0.000672286,0.0004537995,0.00033370528,0.000229972,0.0013534181,0.0003253015,0.00002342918],"category_scores_gemma":[0.0009372215,0.0004331936,0.00014267261,0.000056409393,0.0007147066,0.00023939513,0.0013959229,0.0007499839,0.00008392973],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007234681,0.0000277273,0.000002995496,0.00038045953,0.0003043706,0.0021838944,0.00038375752,0.00008724026,0.000033460146,0.8380864,0.107510075,0.0502761],"study_design_scores_gemma":[0.00076692447,0.00014816805,0.000013164155,0.00015038933,0.00009275627,0.00004471635,0.00018371461,0.001662578,0.000060435406,0.0004674206,0.99572366,0.00068607525],"about_ca_topic_score_codex":0.000019888874,"about_ca_topic_score_gemma":0.0000048281745,"teacher_disagreement_score":0.8882136,"about_ca_system_score_codex":0.00014312254,"about_ca_system_score_gemma":0.00039561762,"threshold_uncertainty_score":0.999812},"labels":[],"label_agreement":null},{"id":"W3116408070","doi":"10.1017/9781108571401.009","title":"The Explore-Then-Commit Algorithm","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Commit; Computer science; Content (measure theory); Algorithm; Database; Mathematics","score_opus":0.1372628476713435,"score_gpt":0.3203234640648492,"score_spread":0.18306061639350568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116408070","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002332445,0.0004445668,0.04938399,0.00036899728,0.0006109394,0.0006741212,0.0004534877,0.0001760105,0.9478856],"genre_scores_gemma":[0.0000818179,0.00032088533,0.0008906896,0.00011374784,0.00048380237,0.0000026744976,0.000025145471,0.000084562394,0.9979967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99415094,0.00023563781,0.00060504663,0.0013323402,0.0030121233,0.00066390354],"domain_scores_gemma":[0.99372363,0.0022767745,0.0005497344,0.0020235346,0.00088266406,0.0005436496],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001002809,0.0005906671,0.000758877,0.00032865588,0.0011551733,0.000533095,0.004636827,0.00042693905,0.000034278524],"category_scores_gemma":[0.0004905498,0.00044960526,0.0005606806,0.00006518731,0.0011806448,0.00028294322,0.002428866,0.0015135952,0.0007103565],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014958555,0.000009393495,5.4033455e-7,0.000009935051,0.00018456359,0.0010386907,0.00013799421,0.000013554395,0.000007202164,0.46503112,0.26674688,0.26667053],"study_design_scores_gemma":[0.0004953756,0.00008818437,0.0000049376945,0.000038577055,0.0000568134,0.000018341156,0.0003726393,0.0018309789,0.00016067112,0.0011911718,0.9952441,0.00049825356],"about_ca_topic_score_codex":0.00003515457,"about_ca_topic_score_gemma":0.0000027282624,"teacher_disagreement_score":0.7284972,"about_ca_system_score_codex":0.0003210335,"about_ca_system_score_gemma":0.00030249433,"threshold_uncertainty_score":0.99979556},"labels":[],"label_agreement":null},{"id":"W3117242735","doi":"10.1017/9781108571401.023","title":"Contextual and Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Link (geometry); Information retrieval; Internet privacy; Computer network; Mathematics","score_opus":0.11857060093907623,"score_gpt":0.32116987956180976,"score_spread":0.20259927862273353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117242735","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042320782,0.00029226986,0.009844857,0.00011220054,0.00022796434,0.00047037838,0.0006824865,0.000108649954,0.98821884],"genre_scores_gemma":[0.00141651,0.00011906746,0.0003062611,0.000110643065,0.00030271432,5.0090864e-7,0.000026034293,0.000047708043,0.99767053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964758,0.00010062761,0.0003824818,0.001134075,0.0015471635,0.00035985166],"domain_scores_gemma":[0.9969523,0.00089511217,0.00030857348,0.0007588144,0.00056191604,0.0005233154],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042010588,0.0004124389,0.00070843473,0.00036577552,0.0002997283,0.00016125807,0.0012274997,0.00039310954,0.000039302762],"category_scores_gemma":[0.00044524603,0.00039925092,0.00021424194,0.000029452971,0.0007480906,0.00021930282,0.0013735043,0.00087785296,0.00022708844],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041131454,0.000010571847,0.0000053665894,0.000039163202,0.00017482787,0.0019675063,0.0001414151,0.00001714615,0.000039555653,0.8038243,0.16563156,0.02773727],"study_design_scores_gemma":[0.00077802,0.00011745514,0.000019157844,0.000047098903,0.000049368147,0.000026197433,0.00009546034,0.00097289047,0.00014411488,0.00019329786,0.99714595,0.0004110155],"about_ca_topic_score_codex":0.000029307483,"about_ca_topic_score_gemma":0.0000028619213,"teacher_disagreement_score":0.83151436,"about_ca_system_score_codex":0.00012220883,"about_ca_system_score_gemma":0.00018289068,"threshold_uncertainty_score":0.9998459},"labels":[],"label_agreement":null},{"id":"W3117424601","doi":"10.1017/9781108571401.008","title":"Stochastic Bandits with Finitely Many Arms","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Mathematical economics; Mathematics","score_opus":0.10339968304591471,"score_gpt":0.2996677950151826,"score_spread":0.19626811196926788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117424601","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025529118,0.00010302749,0.14953166,0.00011133804,0.0002291796,0.00070666475,0.0006811874,0.0001655058,0.8484459],"genre_scores_gemma":[0.0031496356,0.000020532027,0.0006101977,0.0000966156,0.00028336066,0.0000018034747,0.0000453534,0.00009272616,0.99569976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945702,0.00010439893,0.0004574708,0.0015108552,0.0027809036,0.0005761737],"domain_scores_gemma":[0.99563277,0.0011182601,0.0005089459,0.0012974485,0.00080935366,0.00063320954],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040302807,0.00062759523,0.00089913676,0.00063346943,0.00034617222,0.0002642047,0.0022758746,0.00040543408,0.00007654687],"category_scores_gemma":[0.00030846614,0.0005412124,0.00029536398,0.000074077165,0.00077379576,0.00028472257,0.001077141,0.0012541227,0.00056374643],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020820412,0.000043177348,0.0000045779416,0.00009238766,0.00056983094,0.0077516604,0.0003662349,0.0019849555,0.000028734683,0.816973,0.15101144,0.019091988],"study_design_scores_gemma":[0.0013419375,0.0003547862,0.00003317934,0.00016708637,0.00013878438,0.00006379564,0.00016316485,0.0022645162,0.00008678011,0.00035645362,0.9941729,0.0008566503],"about_ca_topic_score_codex":0.0000277126,"about_ca_topic_score_gemma":0.0000040043133,"teacher_disagreement_score":0.8431614,"about_ca_system_score_codex":0.0002671252,"about_ca_system_score_gemma":0.00038624488,"threshold_uncertainty_score":0.99970394},"labels":[],"label_agreement":null},{"id":"W3118438270","doi":"10.1214/23-aos2315","title":"Relaxing the i.i.d. assumption: Adaptively minimax optimal regret via root-entropic regularization","year":2023,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Regret; Minimax; Mathematics; Mathematical optimization; Regularization (linguistics); Entropy (arrow of time); Adversarial system; Computer science; Artificial intelligence; Statistics","score_opus":0.3214253860286645,"score_gpt":0.4722292110110216,"score_spread":0.15080382498235712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118438270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010075963,0.00019827465,0.98001754,0.008340136,0.0002500227,0.00034207854,0.00034290407,0.000054015283,0.00037904287],"genre_scores_gemma":[0.924117,0.00087074784,0.041126806,0.000422012,0.0006813922,0.00006743817,0.00014673399,0.00008510833,0.032482732],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99574566,0.0005067955,0.0006784822,0.00034405253,0.0022971714,0.00042784863],"domain_scores_gemma":[0.99265695,0.0048380294,0.0004380071,0.00084137847,0.0011451392,0.0000804996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039961897,0.0001507093,0.00026314205,0.00020948866,0.00047803522,0.0001670131,0.0012055757,0.00006638638,0.00024247427],"category_scores_gemma":[0.007074946,0.00008143314,0.00007952615,0.0016349094,0.00052797137,0.00026126232,0.00034347718,0.00028716744,0.0005294697],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005077708,0.00012440147,0.0014788057,0.00003899744,0.00021321497,0.000113814,0.005397922,0.09701305,0.0014437834,0.06985162,0.45224917,0.37156746],"study_design_scores_gemma":[0.0005076634,0.00039815472,0.09779119,0.00005273684,0.000031575124,0.000020612417,0.0024961636,0.40567783,0.002779147,0.45650512,0.033438385,0.00030142273],"about_ca_topic_score_codex":0.000016223012,"about_ca_topic_score_gemma":0.000020691514,"teacher_disagreement_score":0.93889076,"about_ca_system_score_codex":0.000022161295,"about_ca_system_score_gemma":0.00009412037,"threshold_uncertainty_score":0.84698826},"labels":[],"label_agreement":null},{"id":"W3121333123","doi":"10.2139/ssrn.3685465","title":"Learning Product Rankings Robust to Fake Users","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Product (mathematics); Computer science; Business; Econometrics; Marketing; Economics; Mathematics","score_opus":0.08311210502914192,"score_gpt":0.37509100048157773,"score_spread":0.2919788954524358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121333123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22898324,0.001485651,0.72699773,0.04058318,0.00040205117,0.00050212577,0.0000025675,0.00013648772,0.0009069677],"genre_scores_gemma":[0.9889696,0.00043827467,0.0019251419,0.00061483186,0.0012136819,0.0000075909193,0.000001202258,0.000045314664,0.0067843474],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99266064,0.00035725068,0.0006148662,0.00069064857,0.002560324,0.0031162435],"domain_scores_gemma":[0.99804866,0.00037226724,0.00023660234,0.00030567157,0.00056557695,0.00047122344],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075537222,0.00020727492,0.00034741694,0.00034385844,0.00055268384,0.00046992523,0.0014994208,0.000054404347,0.0002973606],"category_scores_gemma":[0.010444473,0.0001574525,0.00017030259,0.0019600256,0.00007270551,0.0006328256,0.00024567594,0.004039685,0.001239104],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005890058,0.00006864006,0.008244061,0.000005747291,0.00016999224,0.000074481904,0.0037654676,0.21179238,0.0032904157,0.004086647,0.0057699503,0.7621432],"study_design_scores_gemma":[0.0049634334,0.0065644076,0.004583824,0.0000692471,0.00006420694,0.0018524209,0.040165197,0.03013015,0.0042539216,0.3642349,0.541183,0.0019353265],"about_ca_topic_score_codex":0.000013719043,"about_ca_topic_score_gemma":0.0001042457,"teacher_disagreement_score":0.7602079,"about_ca_system_score_codex":0.00063926587,"about_ca_system_score_gemma":0.001929857,"threshold_uncertainty_score":0.99953854},"labels":[],"label_agreement":null},{"id":"W3127662496","doi":"10.1109/lcsys.2020.3043591","title":"On Data-Driven Multi-Product Pricing","year":2020,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Computer science; Boosting (machine learning); Mathematical optimization; Parametric statistics; Robust optimization; Task (project management); Product (mathematics); Machine learning; Artificial intelligence; Econometrics; Mathematics; Economics","score_opus":0.22847096646366055,"score_gpt":0.40817026663983635,"score_spread":0.1796993001761758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127662496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028346095,0.00028259112,0.9414235,0.025726277,0.0024310262,0.0012872505,0.00022105988,0.00018272767,0.00009951569],"genre_scores_gemma":[0.99127823,0.0000026162047,0.00063397095,0.0061894334,0.0015573199,0.000042077852,0.000010137501,0.00003916792,0.00024706958],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99385154,0.0006714511,0.00086850434,0.0014556162,0.0025269417,0.00062595773],"domain_scores_gemma":[0.99498576,0.0021024826,0.00034474433,0.0019752916,0.00024381895,0.0003479244],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021663618,0.00027057194,0.000662088,0.00023576849,0.00021630317,0.00050633505,0.00280478,0.000059670172,0.0000428258],"category_scores_gemma":[0.0056956825,0.00019775557,0.00010563976,0.0007729414,0.0001292644,0.000667462,0.00018988068,0.00044465944,0.0023779478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022497628,0.00006259756,0.00082173327,0.000034717927,0.00012448743,0.00030877886,0.00051778706,0.7265955,0.09279614,0.000044133358,0.17039312,0.008076019],"study_design_scores_gemma":[0.0028005913,0.00010664169,0.00057437585,0.00004157367,0.000016156398,0.000013345413,0.00018087908,0.968392,0.0003110987,0.000018058272,0.027211545,0.00033374672],"about_ca_topic_score_codex":0.000075608594,"about_ca_topic_score_gemma":0.00000817635,"teacher_disagreement_score":0.9629321,"about_ca_system_score_codex":0.000106336716,"about_ca_system_score_gemma":0.000063143394,"threshold_uncertainty_score":0.99839884},"labels":[],"label_agreement":null},{"id":"W3128801098","doi":"10.1109/focs46700.2020.00132","title":"Optimal anytime regret for two experts","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Computer science; Human–computer interaction; Artificial intelligence; Machine learning","score_opus":0.301288413499801,"score_gpt":0.5098735360741435,"score_spread":0.20858512257434253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128801098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007062467,0.00009079501,0.9678625,0.019215807,0.00014480464,0.00043561083,0.00002431159,0.000108662316,0.0050550834],"genre_scores_gemma":[0.5045461,0.000009624486,0.43353525,0.0051826145,0.001412357,0.00017097013,0.000014117575,0.0000626765,0.05506626],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99745643,0.00005750794,0.00030470322,0.0005713856,0.0012413026,0.0003686726],"domain_scores_gemma":[0.9976295,0.0012637352,0.00006190387,0.00038840884,0.00035276095,0.00030369114],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00076866173,0.00011224302,0.00022789693,0.000089982,0.00012841824,0.00019810333,0.0008300086,0.00004041672,0.0027354688],"category_scores_gemma":[0.0047695558,0.00007347172,0.000116390576,0.0005820478,0.00009229041,0.00040334786,0.00022379497,0.000083707484,0.0009313341],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003523498,0.00005404469,0.00023908271,0.0000047901785,0.000021350008,0.000042350573,0.0013367985,0.0103447605,0.004047628,0.0015015841,0.80277115,0.1792841],"study_design_scores_gemma":[0.0013883271,0.00036235963,0.00006844247,0.0000026950825,0.0000024120786,0.0000071547834,0.001428056,0.39810807,0.019491928,0.005194571,0.573707,0.00023899536],"about_ca_topic_score_codex":0.000004189298,"about_ca_topic_score_gemma":0.000003262584,"teacher_disagreement_score":0.5343272,"about_ca_system_score_codex":0.000022911805,"about_ca_system_score_gemma":0.00006879664,"threshold_uncertainty_score":0.9998466},"labels":[],"label_agreement":null},{"id":"W3133930710","doi":"10.1007/978-3-030-67661-2_2","title":"Exponential Convergence of Gradient Methods in Concave Network Zero-Sum Games","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Zero-sum game; Zero (linguistics); Generalization; Lipschitz continuity; Convergence (economics); Nash equilibrium; Mathematics; Regular polygon; Computer science; Applied mathematics; Mathematical optimization; Mathematical analysis","score_opus":0.09317908722572378,"score_gpt":0.42548853662502933,"score_spread":0.33230944939930557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133930710","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032315092,0.0023423855,0.9917277,0.000187584,0.0038753732,0.00047492754,0.000014600689,0.000025076237,0.001029221],"genre_scores_gemma":[0.10100289,0.0003191653,0.89542115,0.00039433726,0.00075822877,0.000022556744,0.000009822367,0.000060073224,0.0020118118],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9905719,0.00045859575,0.0017160815,0.002300238,0.0038439163,0.0011092646],"domain_scores_gemma":[0.9897674,0.0064220917,0.0007281635,0.0017773103,0.0010428836,0.00026217874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0080579445,0.0005513115,0.0013494496,0.0014374515,0.00017450194,0.00032576342,0.0037123496,0.00041070985,0.00057507254],"category_scores_gemma":[0.0028955892,0.0004571788,0.0002849576,0.0025569191,0.0024903251,0.00044788007,0.002253177,0.0013099203,0.000039869316],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034108467,0.00004134475,0.00047744488,0.000022519467,0.000015522517,0.00024623153,0.00070331927,0.24476694,0.00050605414,0.002877792,0.00010917441,0.75019956],"study_design_scores_gemma":[0.0007078239,0.0002960934,0.0012876041,0.0006999429,0.00001187126,0.000071689596,0.0000057830084,0.38065243,0.01208077,0.595755,0.0074847634,0.00094623317],"about_ca_topic_score_codex":0.000053884647,"about_ca_topic_score_gemma":0.000243016,"teacher_disagreement_score":0.74925333,"about_ca_system_score_codex":0.000363343,"about_ca_system_score_gemma":0.0010145291,"threshold_uncertainty_score":0.999788},"labels":[],"label_agreement":null},{"id":"W3134845586","doi":"10.1017/apr.2021.61","title":"Conditions for indexability of restless bandits and an algorithm to compute Whittle index","year":2022,"lang":"en","type":"article","venue":"Advances in Applied Probability","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Heuristic; Generalization; Mathematical optimization; Index (typography); Mathematics; Class (philosophy); Computation; Algorithm; Greedy algorithm; Computer science; Artificial intelligence","score_opus":0.08425595088796484,"score_gpt":0.4533254396725827,"score_spread":0.36906948878461787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134845586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38658437,0.00029948197,0.60458386,0.00041914606,0.00044629618,0.0051256004,0.001454357,0.000079082194,0.0010078083],"genre_scores_gemma":[0.934737,0.000009334971,0.06347952,0.000084553816,0.00005560591,0.0015344929,0.000041346662,0.000018460598,0.00003964088],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953227,0.00040638,0.0010159453,0.0012759235,0.0014798165,0.0004992181],"domain_scores_gemma":[0.9952358,0.0027890233,0.00027012159,0.0011131276,0.00035251275,0.00023938947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057823043,0.00021731427,0.00059409795,0.0003896728,0.00041426107,0.00005988373,0.0010519137,0.00007168059,0.00019008934],"category_scores_gemma":[0.0012598797,0.00020232002,0.00006916038,0.0017274714,0.0005770663,0.00049681496,0.0008499417,0.00041181743,0.0000043157365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008519353,0.0012078054,0.03690567,0.000100856196,0.0000139520225,0.000003248425,0.001423999,0.22260399,0.00034136235,0.011546379,0.00022999124,0.7247708],"study_design_scores_gemma":[0.0013823106,0.00049928145,0.045881547,0.000006808267,0.0000041779163,0.000003932809,0.0010841304,0.032321166,0.0006298629,0.8998873,0.017991703,0.0003077473],"about_ca_topic_score_codex":0.000027450464,"about_ca_topic_score_gemma":0.0002954368,"teacher_disagreement_score":0.88834095,"about_ca_system_score_codex":0.0002575053,"about_ca_system_score_gemma":0.00017509675,"threshold_uncertainty_score":0.8250371},"labels":[],"label_agreement":null},{"id":"W3136224158","doi":"10.1007/978-3-030-85172-9_9","title":"SEH: Size Estimate Hedging for Single-Server Queues","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Queue; Computer science; Scheduling (production processes); Heuristic; Simple (philosophy); Real-time computing; Distributed computing; Mathematical optimization; Computer network; Mathematics; Artificial intelligence","score_opus":0.12103199500715305,"score_gpt":0.4367620829872396,"score_spread":0.31573008798008656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136224158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05901913,0.00058273436,0.93431365,0.001460688,0.003756265,0.0007201137,0.000018066523,0.0001077127,0.000021643526],"genre_scores_gemma":[0.54889023,0.0000071967825,0.45020628,0.00035659855,0.00044669406,0.0000474467,0.000005629417,0.000025076804,0.000014869303],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99083304,0.00026426103,0.0010288877,0.0029720794,0.0036398391,0.0012618694],"domain_scores_gemma":[0.98472327,0.010586854,0.0004163158,0.0022959006,0.0017017617,0.00027590655],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006201715,0.00052494986,0.00090019207,0.00088226004,0.00047342508,0.0037100348,0.0052178544,0.00034657726,0.0000843],"category_scores_gemma":[0.022478068,0.00042253072,0.00029831158,0.0033599995,0.0010706031,0.00082224316,0.006136363,0.0011958778,0.000025366046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013273888,0.000061151055,0.0005588515,0.00004203729,0.000006173403,0.00006441199,0.00088954635,0.6448827,0.001080561,0.0000058723704,0.00002019129,0.3523752],"study_design_scores_gemma":[0.00032090707,0.00008299454,0.0012550676,0.00030612876,0.000005167772,0.000036405723,0.00000837326,0.8528789,0.025401566,0.1190525,0.00013930371,0.0005126714],"about_ca_topic_score_codex":0.000075428274,"about_ca_topic_score_gemma":0.00021079488,"teacher_disagreement_score":0.48987108,"about_ca_system_score_codex":0.0005433418,"about_ca_system_score_gemma":0.0013104266,"threshold_uncertainty_score":0.9998227},"labels":[],"label_agreement":null},{"id":"W3154042965","doi":"10.2139/ssrn.3803777","title":"Feature-Based Nonparametric Inventory Control with Censored Demand","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nonparametric statistics; Feature (linguistics); Econometrics; Computer science; Control (management); Statistics; Inventory control; Artificial intelligence; Operations research; Mathematics","score_opus":0.026232811545800604,"score_gpt":0.34524579493030144,"score_spread":0.31901298338450085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154042965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050317854,0.00912843,0.9357745,0.003749456,0.00025521233,0.00023577455,0.00000929689,0.000039007347,0.00049044006],"genre_scores_gemma":[0.9875145,0.00045600237,0.0023399682,0.00034563013,0.0003191226,0.000010851293,0.0000040689106,0.000036595044,0.008973267],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99240994,0.0006865912,0.00043742787,0.00058519986,0.0029209442,0.0029598658],"domain_scores_gemma":[0.9962356,0.0011636061,0.0003367786,0.0006042761,0.0013452343,0.00031450004],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006199839,0.00024118987,0.0004619919,0.0007059574,0.00042641367,0.00043852348,0.000877763,0.0001284333,0.00020178987],"category_scores_gemma":[0.0028852369,0.00016041343,0.00021481558,0.0027914753,0.00018121403,0.00041848718,0.00005517371,0.0030102003,0.00017036549],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008448955,0.0026037327,0.2020552,0.00004235035,0.0031333778,0.0046962886,0.0006892588,0.111759126,0.005848064,0.073244534,0.020209657,0.56726944],"study_design_scores_gemma":[0.032744948,0.004232847,0.015075659,0.00013262205,0.0002474537,0.0085671395,0.006720143,0.06491522,0.01336418,0.7769466,0.075131685,0.001921523],"about_ca_topic_score_codex":0.0000063348725,"about_ca_topic_score_gemma":0.00045361818,"teacher_disagreement_score":0.9371966,"about_ca_system_score_codex":0.001094052,"about_ca_system_score_gemma":0.008053568,"threshold_uncertainty_score":0.9992899},"labels":[],"label_agreement":null},{"id":"W3157613611","doi":"","title":"Online Sparse Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Reinforcement learning; Dimension (graph theory); Upper and lower bounds; Time horizon; Q-learning; Oracle; Mathematics; Lasso (programming language); Mathematical optimization; Computer science; Markov process; Combinatorics; Discrete mathematics; Artificial intelligence; Statistics","score_opus":0.40048191254290866,"score_gpt":0.49729921246262404,"score_spread":0.09681729991971538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157613611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024951494,0.00002423779,0.9870315,0.001999762,0.00060095143,0.00008122922,0.000150016,0.000023687784,0.007593464],"genre_scores_gemma":[0.96811193,0.00044556105,0.020336296,0.00031868156,0.00020867001,0.000007851381,0.000153691,0.000011536032,0.010405786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967614,0.00017084515,0.0006843545,0.00050544186,0.0016163564,0.0002616357],"domain_scores_gemma":[0.99615526,0.0014761115,0.00016740357,0.00025696447,0.0017949227,0.00014934831],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00077064073,0.0001498582,0.00020343164,0.0002096347,0.00018676628,0.0005560044,0.00045583525,0.000058567308,0.0054442734],"category_scores_gemma":[0.008803629,0.00012972594,0.000040491046,0.00030660012,0.00022076217,0.0001965958,0.00021325155,0.00036002594,0.0006861209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008131028,0.00012572749,0.00013384646,0.0000018494947,0.000019146231,0.00014412138,0.00024827287,0.020063894,0.0005229427,0.50864875,0.0004327381,0.46957737],"study_design_scores_gemma":[0.000039820326,0.0001505419,0.00028590203,0.000024331717,0.000003644799,0.000020115827,0.0032257736,0.545452,0.003981931,0.4394213,0.007235308,0.00015934714],"about_ca_topic_score_codex":0.000022998096,"about_ca_topic_score_gemma":0.00024356102,"teacher_disagreement_score":0.9666952,"about_ca_system_score_codex":0.00005514658,"about_ca_system_score_gemma":0.0001852285,"threshold_uncertainty_score":0.99954563},"labels":[],"label_agreement":null},{"id":"W3158392704","doi":"","title":"On the Suboptimality of Negative Momentum for Minimax Optimization","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Momentum (technical analysis); Minimax; Convergence (economics); Mathematical optimization; Mathematics; Rate of convergence; Simple (philosophy); Applied mathematics; Computer science; Economics; Key (lock)","score_opus":0.47666892159196084,"score_gpt":0.4878975526146724,"score_spread":0.011228631022711544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158392704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001281908,0.000003684052,0.9846703,0.010936055,0.00019614813,0.0003307421,0.0009739091,0.00000885308,0.0015983959],"genre_scores_gemma":[0.9631561,0.00004531416,0.03594643,0.00051134505,0.00008620172,0.00003363411,0.000027413924,0.000008252024,0.00018529333],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770045,0.00013342987,0.0005871176,0.00036646143,0.0010555972,0.00015695757],"domain_scores_gemma":[0.99191666,0.0061887586,0.00025733988,0.0001727121,0.001372377,0.00009215467],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008409644,0.00012232138,0.00018650516,0.000101271784,0.0001292821,0.00020719584,0.00057974504,0.00004130648,0.001292315],"category_scores_gemma":[0.01604395,0.00008185102,0.0000438139,0.00024031085,0.00034937356,0.0001240588,0.00007915507,0.00014642972,0.00006073702],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068982,0.000067673944,0.000015250815,0.0000037247514,0.00002080044,0.000002087957,0.00080414576,0.053480964,0.00019397205,0.8894948,0.0011388193,0.05408794],"study_design_scores_gemma":[0.00003283263,0.00032582486,0.000024902654,0.000008618651,0.0000025266252,2.7664248e-7,0.0013342474,0.5953615,0.004806139,0.39791626,0.00012959591,0.000057319958],"about_ca_topic_score_codex":0.000012769548,"about_ca_topic_score_gemma":0.0000119604265,"teacher_disagreement_score":0.9618742,"about_ca_system_score_codex":0.000026640206,"about_ca_system_score_gemma":0.00008281524,"threshold_uncertainty_score":0.9996206},"labels":[],"label_agreement":null},{"id":"W3162671465","doi":"10.1109/infocom42981.2021.9488698","title":"Delay-Tolerant Constrained OCO with Application to Network Resource Allocation","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada); Ontario Tech University; University of Toronto","funders":"","keywords":"Regret; Computer science; Mathematical optimization; Benchmark (surveying); Sequence (biology); Constraint (computer-aided design); Convex function; Convex optimization; Resource allocation; Sublinear function; Term (time); Regular polygon; Mathematics","score_opus":0.04998465779926876,"score_gpt":0.3846377056724134,"score_spread":0.33465304787314465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162671465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003849968,0.000049739196,0.98217237,0.0036525582,0.00003908314,0.0004228621,0.000005612552,0.0000688871,0.009738905],"genre_scores_gemma":[0.8900028,0.0000032214848,0.09547024,0.0015431573,0.0002805279,0.00014404366,0.000033412016,0.000022563638,0.012500057],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968409,0.00016182497,0.00040599992,0.0006613719,0.0015520124,0.00037787872],"domain_scores_gemma":[0.9968142,0.0010896017,0.000089047404,0.00081532,0.0009607536,0.00023107603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013480292,0.00012186878,0.00020621577,0.000111460926,0.00020220644,0.00021710474,0.0004566302,0.000057674828,0.0005667402],"category_scores_gemma":[0.00075984356,0.000084232706,0.00003965257,0.0021430082,0.00010013161,0.00018908721,0.00014586598,0.00014257741,0.00074486365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011245066,0.000055085013,0.0005009446,0.0000020524499,0.000016194921,0.000038624064,0.00021817803,0.7180675,0.0009103372,0.002828788,0.009275641,0.26797417],"study_design_scores_gemma":[0.00077981775,0.00018152987,0.002228154,0.000025103118,0.000008681852,0.00008934754,0.0017535387,0.36858281,0.0037193678,0.010087309,0.6121755,0.0003688007],"about_ca_topic_score_codex":0.000011816076,"about_ca_topic_score_gemma":0.00020638248,"teacher_disagreement_score":0.8867021,"about_ca_system_score_codex":0.00005891302,"about_ca_system_score_gemma":0.00020642843,"threshold_uncertainty_score":0.9573964},"labels":[],"label_agreement":null},{"id":"W3167121994","doi":"10.1007/978-3-030-78270-2_49","title":"Multi-armed Bandit Algorithms for Adaptive Learning: A Survey","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Adaptive learning; Artificial intelligence; Machine learning","score_opus":0.20252700003973068,"score_gpt":0.420883279384972,"score_spread":0.21835627934524132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167121994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000037630267,0.00082014746,0.99536604,0.00023253997,0.002032223,0.0010048654,0.00013437531,0.00007564321,0.00029653386],"genre_scores_gemma":[0.03106192,0.00012233082,0.9418125,0.0005218766,0.0014354419,0.00009673785,0.00012214493,0.00016679324,0.024660245],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98957115,0.00034409759,0.0011704207,0.0032378086,0.004396665,0.0012798334],"domain_scores_gemma":[0.9805433,0.013883475,0.0006067235,0.0015290182,0.0030441093,0.00039335815],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0091466075,0.0007266086,0.0012331953,0.0016824638,0.0006486442,0.0010970052,0.0038745685,0.0005522476,0.00030687926],"category_scores_gemma":[0.013151508,0.0005880591,0.00035354856,0.0018422159,0.0018463774,0.00056883565,0.0016959388,0.0018285982,0.00014722258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008011207,0.00006410952,0.00025345336,0.000013051964,0.00003057053,0.00015592152,0.00052176387,0.14809196,0.000063137406,0.00013521462,0.00013170553,0.850459],"study_design_scores_gemma":[0.0010843282,0.0005100659,0.0016059675,0.0001948685,0.000009269477,0.000045477835,0.0000039616734,0.9393708,0.0007657494,0.046037093,0.009440383,0.00093199767],"about_ca_topic_score_codex":0.00006613248,"about_ca_topic_score_gemma":0.00081429724,"teacher_disagreement_score":0.849527,"about_ca_system_score_codex":0.0005557118,"about_ca_system_score_gemma":0.0016044958,"threshold_uncertainty_score":0.99994},"labels":[],"label_agreement":null},{"id":"W3170243566","doi":"10.48550/arxiv.2106.06885","title":"Online Learning with Optimism and Delay","year":2021,"lang":"en","type":"preprint","venue":"OpenBU (Boston University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Optimism; Computer science; Benchmarking; Online learning; Perspective (graphical); Robustness (evolution); Optimism bias; Machine learning; Artificial intelligence; Psychology; Multimedia; Marketing","score_opus":0.09327714844652883,"score_gpt":0.36399998972249875,"score_spread":0.2707228412759699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170243566","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8069931,0.0007243738,0.1622245,0.001427179,0.00043413232,0.0009130535,0.0001244486,0.00015458996,0.02700461],"genre_scores_gemma":[0.5500834,0.0019083043,0.09169285,0.00014251903,0.00022919977,0.0000031173363,0.00035036897,0.00011431234,0.3554759],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99584657,0.0004653028,0.00029865457,0.0013972112,0.0015488078,0.00044345768],"domain_scores_gemma":[0.9968012,0.0007114645,0.00031735093,0.0009286727,0.0009090796,0.00033222482],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008270846,0.00033687148,0.00062633987,0.0009208757,0.0004230455,0.0006844656,0.0015267312,0.00030428567,0.0007972174],"category_scores_gemma":[0.00072672375,0.0002900508,0.00012006421,0.0012630988,0.0003659153,0.00062736636,0.004612237,0.0016996994,0.000048241935],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012628165,0.00091094925,0.013844695,0.0001526859,0.0007759481,0.02194409,0.005866226,0.64167416,0.00045917724,0.00092609687,0.002473287,0.3097099],"study_design_scores_gemma":[0.0051478352,0.0009866563,0.013758475,0.0008694061,0.00026756886,0.0004226369,0.0505167,0.06664244,0.0009416639,0.0014887755,0.8561087,0.0028490853],"about_ca_topic_score_codex":0.00020645908,"about_ca_topic_score_gemma":0.00042450096,"teacher_disagreement_score":0.8536355,"about_ca_system_score_codex":0.0002080328,"about_ca_system_score_gemma":0.0005305358,"threshold_uncertainty_score":0.9999552},"labels":[],"label_agreement":null},{"id":"W3173847742","doi":"10.1017/9781108571401.019","title":"Foundations of Information Theory","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Information theory; Internet privacy; World Wide Web; Information retrieval; Mathematics","score_opus":0.08999575418988723,"score_gpt":0.3177145385875525,"score_spread":0.22771878439766527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173847742","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004749999,0.000026089416,0.132981,0.00003690478,0.00015005963,0.0003276596,0.0005736981,0.000048759044,0.8658511],"genre_scores_gemma":[0.00095822144,0.000028518976,0.0006149886,0.000047409867,0.000067265835,5.1776414e-7,0.00007494928,0.000016384653,0.9981917],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997456,0.0001043761,0.00047730675,0.00035389833,0.0014219687,0.00018644836],"domain_scores_gemma":[0.9966133,0.0009125601,0.00058959605,0.000740282,0.00096435135,0.0001798837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006171387,0.00022202714,0.00042453085,0.0005477285,0.00017877304,0.00010321101,0.0012970578,0.00022947828,0.000060257178],"category_scores_gemma":[0.0006840178,0.00021980192,0.00024256011,0.000043841857,0.00047919762,0.00061692554,0.0007264853,0.0004500395,0.0002539454],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010866679,0.000003123331,5.2676296e-7,0.00001917447,0.000052175998,0.000021174303,0.00009240408,0.000037938837,0.0000070607553,0.9588638,0.021205397,0.019588543],"study_design_scores_gemma":[0.00034063248,0.000053762356,0.000014859582,0.00003447413,0.000043404845,0.0000036426675,0.00016962853,0.00042123004,0.00020024028,0.003275774,0.9952366,0.00020578864],"about_ca_topic_score_codex":0.000016263222,"about_ca_topic_score_gemma":7.330903e-7,"teacher_disagreement_score":0.97403115,"about_ca_system_score_codex":0.00013819443,"about_ca_system_score_gemma":0.00027132707,"threshold_uncertainty_score":0.89632624},"labels":[],"label_agreement":null},{"id":"W3174263485","doi":"","title":"Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Randomness; Intuition; Computer science; Mathematical economics; Mathematical optimization; Fictitious play; Mathematics; Game theory; Machine learning; Statistics","score_opus":0.1626154911242037,"score_gpt":0.42643700495823694,"score_spread":0.26382151383403324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174263485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120090514,0.00030776643,0.876941,0.00080064504,0.00007278096,0.00043739824,0.000036852376,0.00008756394,0.0012254708],"genre_scores_gemma":[0.95846975,0.000070755006,0.019476838,0.00011053532,0.000026441012,0.00006686257,0.00002513696,0.000037000245,0.021716705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99578893,0.001689111,0.00039409506,0.0007850388,0.00092745567,0.0004153894],"domain_scores_gemma":[0.992115,0.005055907,0.00023232533,0.00090855744,0.0014547785,0.00023343587],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022726406,0.00027454132,0.00042239064,0.00021960367,0.000801171,0.00046652675,0.00065214414,0.0001324946,0.0014454967],"category_scores_gemma":[0.009764556,0.00019018949,0.000051326617,0.0006781371,0.0008184698,0.00028465458,0.0003726801,0.0009979575,0.00032595734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003524124,0.0013937902,0.0058526793,0.000026068175,0.00034348553,0.0003423078,0.026631506,0.7613249,0.006077575,0.06926664,0.00062684686,0.124590084],"study_design_scores_gemma":[0.0064720083,0.0010832503,0.018784447,0.00048501894,0.00004972678,0.000106921485,0.0342658,0.92626536,0.0023853448,0.0065031066,0.0026373784,0.00096163416],"about_ca_topic_score_codex":0.000007704017,"about_ca_topic_score_gemma":0.000054665725,"teacher_disagreement_score":0.8574642,"about_ca_system_score_codex":0.00006731567,"about_ca_system_score_gemma":0.0004030881,"threshold_uncertainty_score":0.9994673},"labels":[],"label_agreement":null},{"id":"W3174325474","doi":"","title":"Asymptotically Optimal Information-Directed Sampling","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Asymptotically optimal algorithm; Frequentist inference; Regret; Thompson sampling; Mathematical optimization; Computer science; Simple (philosophy); Connection (principal bundle); Upper and lower bounds; Sampling (signal processing); Mathematics; Bayesian probability; Artificial intelligence; Bayesian inference; Machine learning","score_opus":0.1378188340422346,"score_gpt":0.4246927229571403,"score_spread":0.2868738889149057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174325474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032292604,0.00005506676,0.9059206,0.0010785214,0.00036317614,0.00014121935,0.000008208945,0.00035244567,0.059788104],"genre_scores_gemma":[0.9637124,0.000040858915,0.018994521,0.00035116845,0.000115501134,0.000018571784,0.000035762052,0.000020019132,0.016711194],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962031,0.0007660618,0.0005478999,0.0004444576,0.0015817817,0.00045668537],"domain_scores_gemma":[0.9920865,0.0051508737,0.00018725551,0.0006041747,0.0017666036,0.00020455456],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0035358376,0.00017707981,0.00029167338,0.00029891514,0.00039254624,0.000753348,0.0007080177,0.00012124162,0.0057177152],"category_scores_gemma":[0.044458833,0.00014455894,0.00010119013,0.0008911118,0.00021811876,0.0007590629,0.0002976987,0.0008656105,0.00445378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037420014,0.00011497434,0.0021217603,0.000015419932,0.000058350117,0.00007218361,0.002539765,0.074776866,0.00086286996,0.36944446,0.000778159,0.548841],"study_design_scores_gemma":[0.0019517312,0.0006025491,0.021880012,0.00026898994,0.000023426612,0.000095817326,0.013581846,0.26563576,0.005231222,0.5396683,0.14985758,0.0012027237],"about_ca_topic_score_codex":0.0000010339377,"about_ca_topic_score_gemma":0.0000012212009,"teacher_disagreement_score":0.9314198,"about_ca_system_score_codex":0.00004742933,"about_ca_system_score_gemma":0.0004966563,"threshold_uncertainty_score":0.9963214},"labels":[],"label_agreement":null},{"id":"W3175059381","doi":"10.1017/9781108571401.028","title":"Stochastic Linear Bandits with Finitely Many Arms","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Mathematics; Mathematical optimization; Mathematical analysis","score_opus":0.10763108277616515,"score_gpt":0.3067051927718164,"score_spread":0.19907410999565125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175059381","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000320774,0.000101545214,0.18647483,0.000115514624,0.00024201759,0.00075073953,0.0007787558,0.00018036237,0.8113242],"genre_scores_gemma":[0.0021624814,0.000023753879,0.0010717106,0.00010102211,0.00038555855,0.0000017707295,0.000055350778,0.00010075218,0.9960976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945294,0.00010784904,0.00048515297,0.0015278577,0.00276394,0.00058577966],"domain_scores_gemma":[0.9954953,0.0011226616,0.0005184351,0.0013138468,0.00089917186,0.00065054453],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004238583,0.0006454371,0.00092805445,0.00063509063,0.00035288546,0.00020231142,0.002251294,0.0004357112,0.000072525276],"category_scores_gemma":[0.00035502162,0.00055646,0.00030889065,0.00008014542,0.0007746032,0.00027837718,0.0011012383,0.0013655729,0.0006325053],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003599178,0.00007721022,0.0000073480737,0.00015983389,0.000913754,0.0119768195,0.0005888625,0.00570001,0.000047436606,0.79353255,0.16062804,0.02276898],"study_design_scores_gemma":[0.0014012639,0.00039430664,0.000023270139,0.00017490538,0.00014260341,0.000059456022,0.00014958347,0.0056070443,0.0001110334,0.00022372828,0.99084693,0.00086588226],"about_ca_topic_score_codex":0.000028883473,"about_ca_topic_score_gemma":0.0000037838747,"teacher_disagreement_score":0.83021885,"about_ca_system_score_codex":0.00024687534,"about_ca_system_score_gemma":0.00040601115,"threshold_uncertainty_score":0.9996887},"labels":[],"label_agreement":null},{"id":"W3175406278","doi":"10.1109/tai.2021.3074122","title":"Optimal Policy for Bernoulli Bandits: Computation and Algorithm Gauge","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Bernoulli's principle; Algorithm; Mathematical optimization; Computation; Variety (cybernetics); Approximate Bayesian computation; Time horizon; Thompson sampling; Bayesian probability; Artificial intelligence; Mathematics; Inference","score_opus":0.16748091965585976,"score_gpt":0.45981303194073087,"score_spread":0.2923321122848711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175406278","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031708062,0.00007917414,0.99316585,0.0019791315,0.00074486533,0.0003845285,0.00032070983,0.0000651155,0.000089836525],"genre_scores_gemma":[0.8046497,0.00019488535,0.19155774,0.0003382264,0.0005111034,0.00015843492,0.000020093032,0.000052411873,0.002517421],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678123,0.00016757741,0.0007362015,0.0008005803,0.0010469849,0.00046742454],"domain_scores_gemma":[0.99607193,0.0022714618,0.000120998804,0.00038931376,0.00091324165,0.00023306583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009088255,0.00021453782,0.00030879656,0.00051405316,0.0006005295,0.00042157664,0.0003294162,0.00012796142,0.00033755501],"category_scores_gemma":[0.00053961744,0.00019860532,0.00016599942,0.0015002526,0.00029992408,0.0004150641,0.0000069596545,0.00031200345,0.00030322195],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006814166,0.00017106782,6.477033e-7,0.0000045344746,0.000018008453,0.000013625004,0.0003171574,0.14908862,0.0007488881,0.00074609835,0.00012297787,0.8487002],"study_design_scores_gemma":[0.00011399242,0.0002777654,0.000019169716,0.000020671694,0.000015499994,0.000045642322,0.0014786005,0.6159874,0.28826508,0.09066554,0.002834002,0.00027658488],"about_ca_topic_score_codex":0.00006321401,"about_ca_topic_score_gemma":0.0001452722,"teacher_disagreement_score":0.84842366,"about_ca_system_score_codex":0.00011428581,"about_ca_system_score_gemma":0.0002917866,"threshold_uncertainty_score":0.809889},"labels":[],"label_agreement":null},{"id":"W3175841314","doi":"","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture MDPs","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Mathematics; Minimax; Logarithm; Estimator; Bounded function; Combinatorics; Discrete mathematics; Regret; Mathematical optimization; Markov process; Computer science; Artificial intelligence; Statistics","score_opus":0.12812209112907322,"score_gpt":0.42388866202890896,"score_spread":0.2957665708998357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175841314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023605369,0.00025679034,0.9585086,0.0013069413,0.00047041057,0.00044191518,0.000006517675,0.00019224573,0.015211196],"genre_scores_gemma":[0.7834133,0.000089690686,0.01105389,0.00024243518,0.00038781023,0.000090867055,0.000060687,0.00006121117,0.20460014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947803,0.00095329806,0.000679712,0.0010694737,0.001713616,0.00080360076],"domain_scores_gemma":[0.99164605,0.00530716,0.00033886707,0.00075519783,0.0016744662,0.0002782703],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005012404,0.00032667146,0.0005150852,0.0003043687,0.00078146125,0.0005602275,0.00096400786,0.0002190779,0.003917007],"category_scores_gemma":[0.028045539,0.00027040983,0.0002631378,0.00072539505,0.0002924948,0.00037757578,0.000385049,0.0014008351,0.0012192228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012290671,0.00012449885,0.0003676342,0.000033430762,0.00009495215,0.00014689316,0.003442448,0.6244938,0.0044542016,0.05522158,0.0022336529,0.30815786],"study_design_scores_gemma":[0.0022263383,0.0018669744,0.00055470475,0.00020049543,0.00003248378,0.000039545484,0.01101002,0.5287054,0.013861144,0.051441442,0.38917512,0.0008863292],"about_ca_topic_score_codex":0.000002503219,"about_ca_topic_score_gemma":0.0000019372328,"teacher_disagreement_score":0.94745475,"about_ca_system_score_codex":0.00009700968,"about_ca_system_score_gemma":0.00055369677,"threshold_uncertainty_score":0.9999748},"labels":[],"label_agreement":null},{"id":"W3177486623","doi":"10.1017/9781108571401.033","title":"Foundations of Convex Analysis","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regular polygon; Content (measure theory); Mathematics; Geometry","score_opus":0.1365231072922998,"score_gpt":0.3444356365794961,"score_spread":0.2079125292871963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177486623","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016612943,0.00005625388,0.07984783,0.000062414074,0.000110270244,0.0002948253,0.0009008263,0.000050554852,0.9186604],"genre_scores_gemma":[0.0040047686,0.000035481404,0.00055501505,0.000028026412,0.00006489683,4.463134e-7,0.00007862491,0.000025254743,0.9952075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99645853,0.000104350875,0.0005275754,0.000844306,0.0018191544,0.00024608712],"domain_scores_gemma":[0.99586445,0.0009316454,0.0006280181,0.0011517545,0.0011395639,0.00028458424],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042233162,0.00029112876,0.00094262074,0.0011479047,0.00019254319,0.000091977185,0.0016934212,0.0002700049,0.00012871771],"category_scores_gemma":[0.00030472578,0.0002962749,0.0007128099,0.00017147267,0.00067420513,0.00017456539,0.0008705123,0.00050588767,0.00012531104],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000116797564,0.00001294726,0.000015663272,0.000021086831,0.0014022853,0.00023655905,0.000079009165,0.0002692005,0.000026503196,0.95586485,0.035698988,0.0062561273],"study_design_scores_gemma":[0.00035353118,0.000053110525,0.00005429413,0.000017888518,0.00068874605,0.0000029276832,0.00009308964,0.0024775208,0.00022414236,0.00033669703,0.9953963,0.00030175067],"about_ca_topic_score_codex":0.00007269273,"about_ca_topic_score_gemma":0.000007380798,"teacher_disagreement_score":0.9596973,"about_ca_system_score_codex":0.00015201971,"about_ca_system_score_gemma":0.00026066697,"threshold_uncertainty_score":0.9999489},"labels":[],"label_agreement":null},{"id":"W3178495416","doi":"10.48550/arxiv.2107.06196","title":"No Regrets for Learning the Prior in Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Task (project management); Thompson sampling; Key (lock); Computer science; Bayesian probability; Bayes' theorem; Artificial intelligence; Sampling (signal processing); Prior probability; Machine learning; Mathematical optimization; Mathematics; Engineering; Computer vision","score_opus":0.25855875260942035,"score_gpt":0.3217372327608468,"score_spread":0.06317848015142646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178495416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4622746,0.00034889687,0.52897215,0.00043303345,0.0015607638,0.0016108381,0.000042704683,0.00010427288,0.004652742],"genre_scores_gemma":[0.9623779,0.00022490902,0.0009659732,0.00004686781,0.00020137742,0.0000071082504,0.000024155952,0.000030441137,0.036121283],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963687,0.0005308037,0.0004358562,0.0015523749,0.0005305122,0.00058175705],"domain_scores_gemma":[0.99344575,0.003635188,0.00037437055,0.0013540738,0.0010403262,0.0001502841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028520185,0.00029470393,0.0005216708,0.0005070712,0.00038512936,0.00038429527,0.0023930632,0.00033394402,0.0004281755],"category_scores_gemma":[0.007203807,0.00023025293,0.0003482729,0.0014397609,0.00025630472,0.00037031822,0.0022154239,0.0015127435,0.0002552986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002926361,0.000111837966,0.008336466,0.000055310822,0.00007500968,0.00069609913,0.00072598737,0.97328126,0.000040809424,0.002010514,0.0016218042,0.012752248],"study_design_scores_gemma":[0.001957383,0.00015763043,0.010708685,0.00024870073,0.00004923008,0.000009609273,0.0032889529,0.85739297,0.00023287977,0.07787619,0.047267333,0.00081043475],"about_ca_topic_score_codex":0.000087711735,"about_ca_topic_score_gemma":0.00033204313,"teacher_disagreement_score":0.52800614,"about_ca_system_score_codex":0.00031410236,"about_ca_system_score_gemma":0.00049636164,"threshold_uncertainty_score":0.9389442},"labels":[],"label_agreement":null},{"id":"W3182076562","doi":"10.1111/poms.13778","title":"Sublinear regret for learning POMDPs","year":2022,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Markov decision process; Reinforcement learning; Oracle; Computer science; Sublinear function; Partially observable Markov decision process; Mathematical optimization; Upper and lower bounds; Time horizon; Artificial intelligence; Markov chain; Machine learning; Markov process; Markov model; Mathematics; Statistics; Discrete mathematics","score_opus":0.12616657133808326,"score_gpt":0.43079632801594514,"score_spread":0.30462975667786185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182076562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05658526,0.0008073216,0.8675482,0.0603576,0.0033816139,0.005138849,0.000038296555,0.00044445496,0.005698371],"genre_scores_gemma":[0.67794484,0.00023306865,0.0721116,0.00030994354,0.0004737701,0.0016288131,0.000058875194,0.00002723494,0.24721186],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982799,0.00014490123,0.00023884933,0.00046589875,0.0007153575,0.000155068],"domain_scores_gemma":[0.99938196,0.00005964645,0.000031200856,0.0002750667,0.00020928947,0.00004283994],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0022940438,0.000065709966,0.000087149085,0.00033614875,0.0016032455,0.0002559104,0.00020584401,0.000009100879,0.00044027506],"category_scores_gemma":[0.00084119424,0.000056834666,0.00003062372,0.0006661533,0.000032726886,0.00030202,0.0002982441,0.0001364701,0.000033263543],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006963938,0.00020400628,0.00039492475,0.000017750883,0.000048232894,0.0000038405756,0.0010937569,0.7380575,0.000107809254,0.018811721,0.034710046,0.2064808],"study_design_scores_gemma":[0.00028489245,0.00014076923,0.0005008031,0.0000014473303,0.000008947546,0.000009455171,0.004201521,0.1394288,0.00015295327,0.0029728538,0.8521903,0.0001072727],"about_ca_topic_score_codex":0.000004440992,"about_ca_topic_score_gemma":0.000012708134,"teacher_disagreement_score":0.81748027,"about_ca_system_score_codex":0.00006409312,"about_ca_system_score_gemma":0.000017420338,"threshold_uncertainty_score":0.99969655},"labels":[],"label_agreement":null},{"id":"W318353367","doi":"","title":"Using Adaptive Consultation of Experts to Improve Convergence Rates in Multiagent Learning (Short Paper)","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Regret; Computer science; Outcome (game theory); Advice (programming); Convergence (economics); Set (abstract data type); Nash equilibrium; Class (philosophy); Multi-agent system; Process (computing); Frame (networking); Order (exchange); Artificial intelligence; Machine learning; Mathematical optimization; Mathematics; Mathematical economics","score_opus":0.28694779666301773,"score_gpt":0.48108388591712026,"score_spread":0.19413608925410253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W318353367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.739297,0.00006834953,0.25969097,0.000043656823,0.00012379674,0.00037655805,0.0000032430069,0.00001606824,0.00038038046],"genre_scores_gemma":[0.9710754,0.00003403185,0.027557129,0.000047011632,0.000022052189,0.000021812972,0.0000010021952,0.0000097699,0.0012317504],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971323,0.00021133723,0.000640094,0.00048909715,0.0012162449,0.00031090435],"domain_scores_gemma":[0.99719596,0.0015534383,0.00010503996,0.00025142,0.0007618938,0.0001322353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009986495,0.00012456164,0.00028165473,0.00037376885,0.00013126725,0.000024601042,0.00032216372,0.00005608925,0.0005583688],"category_scores_gemma":[0.0059724674,0.00009562562,0.000049294773,0.0011531,0.00017510074,0.00051983795,0.00016188434,0.0001419198,0.00007135466],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046597293,0.00021555199,0.06993903,0.000006530362,0.000024295548,0.00014260327,0.017297117,0.26613897,0.5618468,0.00014026546,0.00037910877,0.0834038],"study_design_scores_gemma":[0.00092255865,0.00035921423,0.033480667,0.000032480948,0.0000024416152,0.000014316333,0.023043085,0.6084722,0.33194423,0.0005400631,0.0008578656,0.0003308468],"about_ca_topic_score_codex":0.0003845637,"about_ca_topic_score_gemma":0.000119313314,"teacher_disagreement_score":0.34233326,"about_ca_system_score_codex":0.00009814247,"about_ca_system_score_gemma":0.00014106865,"threshold_uncertainty_score":0.71500325},"labels":[],"label_agreement":null},{"id":"W3184471030","doi":"","title":"Deep Reinforcement Learning for Optimal Stopping with Application in Financial Engineering","year":2021,"lang":"en","type":"article","venue":"Les Cahiers du GERAD","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Optimal stopping; Reinforcement learning; Computer science; Benchmark (surveying); Categorical variable; Stochastic control; Deep learning; Artificial intelligence; Mathematical optimization; Machine learning; Optimal control; Mathematics","score_opus":0.023690737743615155,"score_gpt":0.3158420411063364,"score_spread":0.29215130336272127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184471030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103664376,0.000105334795,0.8955191,0.00026324738,0.000059706763,0.00026229583,5.657045e-7,0.000029677363,0.00009571775],"genre_scores_gemma":[0.9065232,0.000020076002,0.09184491,0.00006195622,0.00016639574,0.00020229067,0.000019428993,0.000021075133,0.0011406664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981596,0.000044509103,0.00033131771,0.0004212025,0.0006860211,0.0003573575],"domain_scores_gemma":[0.9986522,0.00065916235,0.000092277565,0.00025138463,0.00026936713,0.00007558326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080455974,0.00011940898,0.00020402415,0.00022789744,0.00021415055,0.00011901109,0.00025283635,0.00008789581,0.000027726732],"category_scores_gemma":[0.0023945235,0.0001041467,0.000053790634,0.0007791435,0.00006308989,0.00025015356,0.00006259281,0.00035188656,0.000014354445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005366272,0.000011849472,0.0009765424,0.0000092831015,0.0000050125013,0.000025279554,0.0008344891,0.946993,0.0006875841,0.002572851,0.000026978547,0.04780345],"study_design_scores_gemma":[0.0009243516,0.00009872451,0.0035351908,0.000019327981,0.0000035169446,0.000017536768,0.00093915476,0.96945536,0.002468414,0.0010990945,0.021236869,0.0002024553],"about_ca_topic_score_codex":0.000010544271,"about_ca_topic_score_gemma":0.00004071594,"teacher_disagreement_score":0.80367416,"about_ca_system_score_codex":0.00021878471,"about_ca_system_score_gemma":0.00011153531,"threshold_uncertainty_score":0.4246979},"labels":[],"label_agreement":null},{"id":"W3186527071","doi":"10.23919/acc50511.2021.9482649","title":"On Data-driven Multi-Product Pricing","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Computer science; Boosting (machine learning); Mathematical optimization; Parametric statistics; Task (project management); Product (mathematics); Robust optimization; Machine learning; Artificial intelligence; Mathematics; Engineering","score_opus":0.41519689702321394,"score_gpt":0.5222217993256624,"score_spread":0.10702490230244843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186527071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017524797,0.00025916958,0.9626105,0.0036772361,0.00084561727,0.00026762282,0.000065567925,0.00013276111,0.014616751],"genre_scores_gemma":[0.59598714,0.000052986525,0.26562017,0.0009625776,0.0004771183,0.0000106284015,0.000083628336,0.000039267896,0.13676646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962729,0.00017703077,0.00034650843,0.0010469557,0.0018322674,0.0003243068],"domain_scores_gemma":[0.99511427,0.0015471652,0.000063619715,0.0026587052,0.00049272523,0.00012351254],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015073773,0.00010324496,0.00020085691,0.00016455563,0.00015799313,0.00025405263,0.0015072903,0.000030015153,0.0030399845],"category_scores_gemma":[0.01638079,0.0000688648,0.000040730243,0.0011114952,0.000070735565,0.0005224405,0.0011470998,0.00022084346,0.0034554328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004915342,0.000566753,0.0022382427,0.000008091939,0.000050203973,0.00067363365,0.00036366205,0.027509414,0.006232892,0.0028317417,0.1411715,0.8183047],"study_design_scores_gemma":[0.001774699,0.00013106936,0.015842473,0.000034334073,0.000009933296,0.00007650849,0.0017949615,0.7035817,0.050425146,0.02206399,0.20362431,0.0006408802],"about_ca_topic_score_codex":0.000015229698,"about_ca_topic_score_gemma":0.00009972261,"teacher_disagreement_score":0.81766385,"about_ca_system_score_codex":0.00004070679,"about_ca_system_score_gemma":0.00015781439,"threshold_uncertainty_score":0.9978714},"labels":[],"label_agreement":null},{"id":"W3186893068","doi":"10.2139/ssrn.3841273","title":"A General Framework for Resource Constrained Revenue Management with Demand Learning and Large Action Space","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Space (punctuation); Action (physics); Action learning; Revenue; Computer science; Business; Microeconomics; Economics; Mathematical economics; Mathematics; Mathematics education; Finance","score_opus":0.03539432286056208,"score_gpt":0.39525911774602984,"score_spread":0.35986479488546774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186893068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045639157,0.0020013987,0.95007145,0.0017915106,0.0000630298,0.00018707308,0.0000062736385,0.000014097272,0.00022598486],"genre_scores_gemma":[0.84412384,0.0050945524,0.08147149,0.00016649222,0.0009104035,0.000041612668,0.000010747127,0.00006545658,0.06811543],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965454,0.00028377248,0.00027883032,0.0004032956,0.0008816092,0.0016071146],"domain_scores_gemma":[0.9986141,0.00059563544,0.00020580184,0.00018716166,0.000273855,0.00012348061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047257054,0.00013294097,0.00022035376,0.00017339969,0.0006179646,0.00029507172,0.00021490068,0.000076572374,0.000050352082],"category_scores_gemma":[0.0011965137,0.000100777565,0.00007123913,0.0005160993,0.00007991959,0.00021755596,0.00009414677,0.0016618241,0.000008380947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011667724,0.00017193877,0.0051261866,0.000041019983,0.00064857485,0.00028182042,0.00080248964,0.003823273,0.00065610115,0.36648965,0.0011897897,0.6196024],"study_design_scores_gemma":[0.0021324356,0.0005469176,0.00048376605,0.00007225281,0.000040589362,0.0016029353,0.014795791,0.0032461598,0.0003630012,0.789689,0.18679819,0.00022894445],"about_ca_topic_score_codex":0.0000016369061,"about_ca_topic_score_gemma":0.00020764078,"teacher_disagreement_score":0.8686,"about_ca_system_score_codex":0.00030680266,"about_ca_system_score_gemma":0.00064522185,"threshold_uncertainty_score":0.7219891},"labels":[],"label_agreement":null},{"id":"W3187572640","doi":"10.24963/ijcai.2021/481","title":"Toward Optimal Solution for the Context-Attentive Bandit Problem","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Thompson sampling; Regret; Computer science; Context (archaeology); Dialog box; Variety (cybernetics); Machine learning; Artificial intelligence; Recommender system; Baseline (sea); Sampling (signal processing); World Wide Web","score_opus":0.21702170598571818,"score_gpt":0.4445649393414074,"score_spread":0.2275432333556892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187572640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009638014,0.0004355109,0.9838049,0.011617287,0.0003366196,0.00058641017,0.000036686586,0.000036746118,0.0021820667],"genre_scores_gemma":[0.8166755,0.00007093976,0.07158538,0.000831533,0.00046548518,0.00036782754,0.000021346306,0.000029075014,0.10995296],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99726856,0.0001268918,0.00038540244,0.00051477825,0.001292169,0.0004121857],"domain_scores_gemma":[0.99455154,0.0034574633,0.000094370705,0.0004740617,0.001331712,0.000090836445],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001854029,0.00011374244,0.00019994985,0.000080936974,0.00039058237,0.00036526186,0.0006327327,0.0000595517,0.0019629668],"category_scores_gemma":[0.0027307882,0.000060946,0.0001762753,0.00059851544,0.00018452849,0.00038643708,0.0002844781,0.0001606304,0.00043550442],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024565152,0.00017115143,0.00034122428,0.000011932088,0.00012958384,0.000044743385,0.0019866154,0.0030671924,0.0016254608,0.007977441,0.1716906,0.81270844],"study_design_scores_gemma":[0.0031285677,0.0002943806,0.0025811146,0.000020859237,0.000032492742,0.000073707255,0.017381154,0.26519266,0.02761878,0.05489406,0.6283628,0.00041944266],"about_ca_topic_score_codex":0.0000220411,"about_ca_topic_score_gemma":0.000103010665,"teacher_disagreement_score":0.91221946,"about_ca_system_score_codex":0.00006629997,"about_ca_system_score_gemma":0.0002017541,"threshold_uncertainty_score":0.99894935},"labels":[],"label_agreement":null},{"id":"W3193611757","doi":"10.1109/twc.2022.3141094","title":"Unifying Futures and Spot Market: Overbooking-Enabled Resource Trading in Mobile Edge Networks","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Futures contract; Negotiation; Dynamic pricing; Forward contract; Spot market; Profit (economics); Incentive; Operations research; Business; Microeconomics; Economics; Electricity","score_opus":0.06693934700005788,"score_gpt":0.3613072301788384,"score_spread":0.29436788317878054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193611757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15799186,0.0036153258,0.8270536,0.0022860887,0.000595288,0.0017424186,0.00017479839,0.00028439864,0.006256202],"genre_scores_gemma":[0.99548566,0.00073247077,0.0010209348,0.00013673917,0.000029949777,0.0006123099,0.0000081086555,0.000042497035,0.0019313453],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588144,0.001335373,0.00069870794,0.0005693444,0.0010450076,0.00047010908],"domain_scores_gemma":[0.9931522,0.0041035637,0.00018381044,0.0023087782,0.00009549557,0.0001561783],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0025817214,0.00021725977,0.00036416817,0.0009348379,0.0029015148,0.00023468565,0.0022696475,0.00009157137,0.0008358211],"category_scores_gemma":[0.000056266566,0.00022089285,0.00012334941,0.0022436953,0.0003506276,0.00038278682,0.000092105554,0.0016422914,0.000008995249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021249792,0.00060218,0.00017662787,0.000007761406,0.00004183658,0.00001604412,0.0032847303,0.6150019,0.00037784048,0.00031571698,0.001095052,0.37886778],"study_design_scores_gemma":[0.0012924103,0.00019162669,0.0010987932,0.000053366763,0.00002076464,0.000059809456,0.013445217,0.92003787,0.0004340027,0.002004997,0.060897667,0.00046350475],"about_ca_topic_score_codex":0.0000924895,"about_ca_topic_score_gemma":0.0005164086,"teacher_disagreement_score":0.8374938,"about_ca_system_score_codex":0.0003386804,"about_ca_system_score_gemma":0.000089684974,"threshold_uncertainty_score":0.9983966},"labels":[],"label_agreement":null},{"id":"W3193685318","doi":"10.1017/9781108571401.047","title":"Markov Decision Processes","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Markov decision process; Markov chain; Markov process; Mathematics; Machine learning; Statistics","score_opus":0.09019827160613175,"score_gpt":0.318277106807889,"score_spread":0.22807883520175726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193685318","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012937354,0.0003366039,0.041969907,0.00008084723,0.00033510252,0.00060605374,0.00055622245,0.00017805453,0.9559243],"genre_scores_gemma":[0.0004218734,0.0002161066,0.0016760093,0.00009793164,0.00029778606,0.0000011786344,0.00003262384,0.00007797408,0.9971785],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99411774,0.00009407621,0.00057910435,0.001586638,0.0031271563,0.0004952799],"domain_scores_gemma":[0.99390036,0.0021044654,0.0005079779,0.0013509743,0.0015644291,0.00057177566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058419706,0.000560778,0.00084776926,0.00063440425,0.00039147882,0.00031954254,0.003023895,0.00050400145,0.00009093113],"category_scores_gemma":[0.0018113079,0.00052980136,0.0003419926,0.00009827926,0.0005378936,0.00037058195,0.0019480048,0.0010036818,0.00061512453],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010244484,0.000026959708,0.0000054177917,0.00015132006,0.00017995646,0.0030369551,0.000098635646,0.000058321628,0.00002545934,0.3083013,0.54589343,0.14119779],"study_design_scores_gemma":[0.00059300335,0.000100267665,0.000011228681,0.0001456687,0.000055492404,0.000023547875,0.0000652104,0.00028570133,0.00024367792,0.0007832408,0.9971431,0.00054985477],"about_ca_topic_score_codex":0.000019932106,"about_ca_topic_score_gemma":0.000004897228,"teacher_disagreement_score":0.45124966,"about_ca_system_score_codex":0.00028542895,"about_ca_system_score_gemma":0.0006383496,"threshold_uncertainty_score":0.9997153},"labels":[],"label_agreement":null},{"id":"W3193757218","doi":"10.1017/9781108571401.002","title":"Bandits, Probability and Concentration","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Information retrieval; Mathematics","score_opus":0.11115866577009616,"score_gpt":0.3057460466407874,"score_spread":0.19458738087069127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193757218","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008286885,0.00019371288,0.012022378,0.00013341328,0.000183952,0.00079560693,0.0004277346,0.00009879875,0.9860615],"genre_scores_gemma":[0.0028237451,0.0000939631,0.00051197386,0.000057414858,0.00016664878,8.752558e-7,0.000034127563,0.00002833091,0.99628294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99672514,0.00012923864,0.00037544896,0.0011126096,0.0013607983,0.00029677514],"domain_scores_gemma":[0.9974298,0.00059175794,0.00031643384,0.000725034,0.0005493711,0.00038763208],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000510509,0.00033290312,0.00053812173,0.00013597202,0.00027117686,0.00020805334,0.0008435413,0.0003241706,0.000028113456],"category_scores_gemma":[0.0004269077,0.00032374964,0.00015675041,0.000027394217,0.0007014069,0.00026929143,0.0007588266,0.00063256256,0.00006567774],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002027161,0.0000084987205,0.000014080432,0.000043837845,0.000062273284,0.00027992539,0.000079838515,0.000017048093,0.000035020275,0.9448836,0.040820237,0.013552933],"study_design_scores_gemma":[0.000563056,0.000087229564,0.00007427515,0.000037637372,0.000043942156,0.000011515154,0.00003700124,0.00075497356,0.00022644871,0.0013602953,0.9964559,0.0003477216],"about_ca_topic_score_codex":0.00002441698,"about_ca_topic_score_gemma":0.0000026466414,"teacher_disagreement_score":0.95563567,"about_ca_system_score_codex":0.00021012382,"about_ca_system_score_gemma":0.00027726786,"threshold_uncertainty_score":0.99992144},"labels":[],"label_agreement":null},{"id":"W3199199701","doi":"10.48550/arxiv.2106.00589","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Term (time); Horizon; Computer science; Reinforcement; Recommender system; Artificial intelligence; Machine learning; Engineering; Mathematics","score_opus":0.3178481876547598,"score_gpt":0.33843505747722585,"score_spread":0.020586869822466047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199199701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42411193,0.000104723724,0.5742497,0.000008132888,0.0008042459,0.0004041939,0.000004357499,0.000045825545,0.00026693052],"genre_scores_gemma":[0.99701506,0.00029615196,0.00055997615,0.00000551457,0.00014261546,0.0000024643252,0.000113546346,0.000038727758,0.001825945],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99495304,0.0008642212,0.0009167229,0.001804889,0.0007780028,0.00068310555],"domain_scores_gemma":[0.99607366,0.0010089568,0.00067917095,0.0010713193,0.0009315503,0.0002353536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0035194166,0.00040178688,0.0007244952,0.002347994,0.0003120847,0.0008133372,0.0013579968,0.00044461453,0.00024282168],"category_scores_gemma":[0.0023692085,0.00044004677,0.00024793495,0.0038020024,0.00010343229,0.0010391028,0.0029962533,0.0017345774,0.00004048256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041129835,0.00004202049,0.03875087,0.000072555726,0.000037777692,0.0004587152,0.000096185555,0.9431597,0.00010926551,0.00010330884,0.0000068385793,0.017121628],"study_design_scores_gemma":[0.00041391884,0.00008787575,0.0021588951,0.00019782346,0.000039121453,0.0000081054695,0.0017385436,0.99437106,0.00016750858,0.00027599983,0.000083451916,0.00045767866],"about_ca_topic_score_codex":0.0007767502,"about_ca_topic_score_gemma":0.00021686358,"teacher_disagreement_score":0.5736897,"about_ca_system_score_codex":0.0020286827,"about_ca_system_score_gemma":0.0004875768,"threshold_uncertainty_score":0.99980515},"labels":[],"label_agreement":null},{"id":"W3202520435","doi":"10.1109/icdcs51616.2021.00126","title":"Poster: Multi-agent Combinatorial Bandits with Moving Arms","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Scheduling (production processes); Overhead (engineering); Wireless network; Crowdsourcing; Task (project management); Distributed computing; Wireless; Enhanced Data Rates for GSM Evolution; Job shop scheduling; Upper and lower bounds; Computer network; Mathematical optimization; Artificial intelligence; Routing (electronic design automation); Mathematics","score_opus":0.12498049373758835,"score_gpt":0.42311053471533827,"score_spread":0.2981300409777499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202520435","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28572527,0.00049388345,0.6890552,0.0039235465,0.0046956907,0.00078106095,0.000045366927,0.00028897365,0.014990988],"genre_scores_gemma":[0.9610067,0.000014568938,0.016588954,0.00023764287,0.0002685028,0.000018334491,0.000008743763,0.000027132817,0.021829424],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9957192,0.00020423971,0.0004252991,0.00070930657,0.0024719632,0.0004699681],"domain_scores_gemma":[0.99694186,0.000972321,0.00009882797,0.00077322277,0.00096098863,0.00025275938],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010624506,0.00016720722,0.00029641093,0.00017556931,0.00020183157,0.00045226974,0.0006163957,0.000072523384,0.002446072],"category_scores_gemma":[0.0020801811,0.000103375074,0.000083091814,0.0010752605,0.0001205627,0.00047118327,0.00039243163,0.00025358686,0.0010213476],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002149174,0.006382978,0.22406463,0.00009960733,0.00078802556,0.015140759,0.011621044,0.014632747,0.028354585,0.014346186,0.06928825,0.613132],"study_design_scores_gemma":[0.034887016,0.0023069775,0.17691316,0.0002228599,0.000076634955,0.0011330646,0.018411554,0.068120174,0.3645317,0.074255645,0.2554832,0.0036579992],"about_ca_topic_score_codex":0.00002320405,"about_ca_topic_score_gemma":0.00010352416,"teacher_disagreement_score":0.6752814,"about_ca_system_score_codex":0.000081401195,"about_ca_system_score_gemma":0.00025299937,"threshold_uncertainty_score":0.99975646},"labels":[],"label_agreement":null},{"id":"W3203261540","doi":"10.1287/moor.2023.1351","title":"Bilateral Trade: A Regret Minimization Perspective","year":2023,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Ministero dell’Istruzione, dell’Università e della Ricerca; Agence Nationale de la Recherche","keywords":"Regret; Hindsight bias; Bounded function; Mathematical economics; Mathematics; Benchmark (surveying); Perspective (graphical); Statistics; Psychology","score_opus":0.46240689411217983,"score_gpt":0.5846736458382126,"score_spread":0.12226675172603274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203261540","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69696254,0.0004098687,0.216302,0.044214,0.0006167447,0.0055794334,0.00048767682,0.00056604185,0.03486169],"genre_scores_gemma":[0.9482973,0.00007876384,0.030780556,0.0000132220675,0.000119888005,0.00016652985,0.000028715936,0.000041938132,0.020473054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993554,0.00049209304,0.0007778608,0.00048228563,0.0041714394,0.0005223506],"domain_scores_gemma":[0.99368286,0.0027501173,0.000056822755,0.00096350204,0.0024061345,0.00014053936],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007288245,0.00012493097,0.00031721438,0.0019562184,0.00051663705,0.00040760823,0.0010784608,0.00009700667,0.0008551619],"category_scores_gemma":[0.019157631,0.0000922782,0.00012533709,0.0065231053,0.00047824156,0.0005338051,0.00036990584,0.0003886021,0.0012904215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015917892,0.002048657,0.0008404882,0.000229384,0.00027803757,0.00018037592,0.11023017,0.3466407,0.023277355,0.3539258,0.13741761,0.024772236],"study_design_scores_gemma":[0.0004815291,0.0002125975,0.0014587188,0.000047663074,0.0000046299215,0.000014707678,0.027517017,0.80067676,0.0057807695,0.1621712,0.0014590804,0.00017534514],"about_ca_topic_score_codex":0.000048434147,"about_ca_topic_score_gemma":0.00008468294,"teacher_disagreement_score":0.45403606,"about_ca_system_score_codex":0.00015030308,"about_ca_system_score_gemma":0.00031696763,"threshold_uncertainty_score":0.99948716},"labels":[],"label_agreement":null},{"id":"W3204390043","doi":"10.2139/ssrn.3930622","title":"Dynamic Pricing with Fairness Constraints","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Dynamic pricing; Business; Economics; Microeconomics","score_opus":0.029526493173406148,"score_gpt":0.37649545766479586,"score_spread":0.3469689644913897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204390043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08927623,0.0015721673,0.90580606,0.0014005861,0.00019118488,0.00009955852,0.0000034206296,0.000028498884,0.0016223147],"genre_scores_gemma":[0.9880082,0.00062288676,0.0021755642,0.000059153408,0.00009003177,0.0000034394122,0.0000020498833,0.000023888319,0.009014775],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939904,0.00028121565,0.0004779541,0.00047099398,0.0021193,0.0026601425],"domain_scores_gemma":[0.9976339,0.00056632987,0.00022650286,0.00042848202,0.0009686452,0.00017618964],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0050194394,0.00016866761,0.00029879747,0.00026557513,0.00039917452,0.00037236183,0.00074038905,0.00006594929,0.00046086757],"category_scores_gemma":[0.001544949,0.000112618065,0.000107484746,0.0012761186,0.00027375153,0.0005169939,0.00012008423,0.0023512277,0.00020296269],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015192373,0.00015632271,0.0033966114,0.0000045582324,0.00025151978,0.0007089194,0.00038359195,0.0038960504,0.0015533204,0.035179358,0.00011538453,0.9542024],"study_design_scores_gemma":[0.0019699319,0.00046407533,0.002757977,0.000050015162,0.000022633485,0.01507469,0.020597817,0.0053882096,0.0011349804,0.9492532,0.0028698805,0.00041657226],"about_ca_topic_score_codex":0.000005193132,"about_ca_topic_score_gemma":0.00088849646,"teacher_disagreement_score":0.9537859,"about_ca_system_score_codex":0.0010207344,"about_ca_system_score_gemma":0.007252098,"threshold_uncertainty_score":0.9999504},"labels":[],"label_agreement":null},{"id":"W3204874277","doi":"10.48550/arxiv.2109.14733","title":"Batched Bandits with Crowd Externalities","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Externality; Computer science; Economics; Microeconomics","score_opus":0.28149544233302065,"score_gpt":0.2986513873188594,"score_spread":0.017155944985838723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204874277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5806645,0.00019852603,0.41496187,0.00012252218,0.0005008649,0.00029578168,0.00006187363,0.000108986496,0.003085047],"genre_scores_gemma":[0.95732224,0.00017805253,0.0011086925,0.000057980465,0.00019302424,0.000002282832,0.000029972065,0.000040900984,0.041066825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99532706,0.00049734104,0.0004466514,0.0020560334,0.0010095604,0.0006633629],"domain_scores_gemma":[0.9945298,0.0011666026,0.00042882445,0.0022066578,0.0012979097,0.0003702193],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00118436,0.00046044856,0.00074861344,0.0006172873,0.00027717723,0.0007493423,0.0025734452,0.00035785386,0.0020577947],"category_scores_gemma":[0.00081242895,0.00039311673,0.00031846814,0.0015063594,0.00052822183,0.0007183997,0.0025265538,0.0011498783,0.00034710093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006610124,0.0003222139,0.029039448,0.00012141527,0.0004795135,0.010435607,0.0018221244,0.9448555,0.000096019496,0.005000719,0.0025595366,0.0046068593],"study_design_scores_gemma":[0.0077265454,0.0008153214,0.061833,0.0014224863,0.00049330306,0.00023486727,0.03155563,0.3797205,0.00578316,0.48257816,0.022132842,0.00570417],"about_ca_topic_score_codex":0.00027120285,"about_ca_topic_score_gemma":0.00041834236,"teacher_disagreement_score":0.565135,"about_ca_system_score_codex":0.00031383403,"about_ca_system_score_gemma":0.0007160879,"threshold_uncertainty_score":0.99985206},"labels":[],"label_agreement":null},{"id":"W3208296466","doi":"10.1609/aaai.v36i8.20891","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Convergence (economics); Gradient method; Computer science; Mathematical optimization; Applied mathematics; Work (physics); Rate of convergence; Mathematics; Economics; Physics; Telecommunications","score_opus":0.23281244621401168,"score_gpt":0.4911329585570102,"score_spread":0.2583205123429986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208296466","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95850223,0.00015011847,0.021528449,0.010980661,0.00057012873,0.0012937392,0.00009169479,0.000042695992,0.0068402984],"genre_scores_gemma":[0.990052,0.00004814765,0.009317246,0.00011475511,0.00003034001,0.0000580424,3.4364e-7,0.000012903365,0.00036623573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954155,0.0002173798,0.0012861834,0.0007427468,0.0018710493,0.000467112],"domain_scores_gemma":[0.99631035,0.0012552005,0.00087352813,0.000417695,0.0010116596,0.00013157513],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0071444763,0.00021452169,0.00050910073,0.0006441697,0.00029104546,0.000110112174,0.0022704478,0.000059300568,0.0005070998],"category_scores_gemma":[0.009762134,0.00015939616,0.00012743194,0.0029357912,0.00094434124,0.00031219653,0.0014856735,0.0006047828,0.000011753648],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005668318,0.00048016885,0.005402951,0.00007285725,0.000021380829,0.0000022133331,0.00780279,0.0025023913,0.124172054,0.49268085,0.0002527278,0.3660428],"study_design_scores_gemma":[0.00005902191,0.00039473115,0.0036302244,0.0000652124,0.000006500173,0.00000796612,0.010563852,0.056922205,0.37199664,0.555453,0.0006692909,0.00023134885],"about_ca_topic_score_codex":0.00033196362,"about_ca_topic_score_gemma":0.000018234947,"teacher_disagreement_score":0.36581144,"about_ca_system_score_codex":0.00014823796,"about_ca_system_score_gemma":0.00028888453,"threshold_uncertainty_score":0.9985791},"labels":[],"label_agreement":null},{"id":"W3210467483","doi":"10.48550/arxiv.2111.00870","title":"Statistical Consequences of Dueling Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Computer science; Thompson sampling; Operations research; Management science; Machine learning; Mathematics; Economics","score_opus":0.32076907952479783,"score_gpt":0.33607742809936747,"score_spread":0.015308348574569641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210467483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5042049,0.00011669547,0.4936008,0.000047741818,0.00045594445,0.00018056086,0.00015271947,0.000034275206,0.0012063483],"genre_scores_gemma":[0.994461,0.00028042,0.0030132213,0.00001711743,0.00006543287,6.861396e-7,0.000036709083,0.000017225673,0.0021082165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961589,0.0005760414,0.0006100498,0.0014295013,0.00078947924,0.00043601892],"domain_scores_gemma":[0.9938175,0.0029053842,0.00047172155,0.0012468925,0.0013017863,0.00025670722],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015326239,0.00027749003,0.00072509405,0.00052646623,0.00014743055,0.00018309169,0.0017678168,0.00030555294,0.001605549],"category_scores_gemma":[0.0037099265,0.00026578357,0.00022241462,0.0011793162,0.0010670715,0.0003027714,0.0018899704,0.0007902421,0.0001355662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020694724,0.00022090477,0.023433456,0.00015360364,0.00021607737,0.0028941284,0.00037147372,0.94774234,0.0005452814,0.015968088,0.0008415589,0.007406122],"study_design_scores_gemma":[0.001781101,0.00031854585,0.02317275,0.00056784775,0.0002160737,0.00005037325,0.005495337,0.46065226,0.011954624,0.49290094,0.0013156212,0.0015745403],"about_ca_topic_score_codex":0.00015996081,"about_ca_topic_score_gemma":0.00006417343,"teacher_disagreement_score":0.49058756,"about_ca_system_score_codex":0.00015281582,"about_ca_system_score_gemma":0.0008892489,"threshold_uncertainty_score":0.99997944},"labels":[],"label_agreement":null},{"id":"W3211530479","doi":"","title":"UCB-based Algorithms for Multinomial Logistic Regression Bandits","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multinomial logistic regression; Regret; Outcome (game theory); Computer science; Probabilistic logic; Logistic regression; Algorithm; Click-through rate; Revenue; Combinatorics; Mathematics; Artificial intelligence; Machine learning; Discrete mathematics; Mathematical economics; Information retrieval; Economics","score_opus":0.44194649559173543,"score_gpt":0.360482215254491,"score_spread":0.08146428033724445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211530479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06136786,0.00007053458,0.9365673,0.00023773097,0.00061539205,0.00033307736,0.00010267822,0.00008697029,0.00061844074],"genre_scores_gemma":[0.9791237,0.000018245335,0.007169648,0.00010711,0.00020777495,0.0000026500375,0.000037408125,0.000023881103,0.013309591],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710417,0.00028570753,0.00034923048,0.0012199092,0.00046838465,0.0005725966],"domain_scores_gemma":[0.99443066,0.0029972417,0.00021068324,0.0009612998,0.0011035122,0.00029661023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010255926,0.00023017563,0.0003732739,0.00034139527,0.0004402034,0.0001516565,0.00093297963,0.00017016666,0.0006494885],"category_scores_gemma":[0.0045501622,0.00019994588,0.00027418436,0.0016011506,0.0002727943,0.0004126797,0.00028128971,0.00025190375,0.00036875706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018359972,0.0010174997,0.013996724,0.000072794035,0.00013813698,0.0051230816,0.00023822644,0.8525462,0.0028963161,0.0105085885,0.020025073,0.09160135],"study_design_scores_gemma":[0.003622112,0.0001676784,0.0025553505,0.00003819688,0.00003273367,0.0000108527975,0.00046995666,0.9341701,0.007987352,0.03140034,0.019135486,0.0004098052],"about_ca_topic_score_codex":0.000019168767,"about_ca_topic_score_gemma":0.000055310968,"teacher_disagreement_score":0.92939764,"about_ca_system_score_codex":0.00019618771,"about_ca_system_score_gemma":0.00040189558,"threshold_uncertainty_score":0.81535566},"labels":[],"label_agreement":null},{"id":"W3211820441","doi":"","title":"Best-case lower bounds in online learning","year":2021,"lang":"en","type":"article","venue":"University of Twente Research Information","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Agencia Nacional de Investigación y Desarrollo; Natural Sciences and Engineering Research Council of Canada; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Sublinear function; Regret; Upper and lower bounds; Hindsight bias; Online learning; Computer science; Contrast (vision); Online algorithm; Mathematical optimization; Mathematics; Artificial intelligence; Algorithm; Machine learning; Discrete mathematics","score_opus":0.18059709452720507,"score_gpt":0.4517273856144851,"score_spread":0.27113029108728004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211820441","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9556517,0.0001001132,0.03044889,0.0013535948,0.00014655002,0.0002635024,0.000057102206,0.00002427847,0.011954257],"genre_scores_gemma":[0.98525524,0.0002474242,0.0031056996,0.000014270625,0.000025833833,2.699879e-7,0.00006435625,0.0000044489675,0.011282471],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99613434,0.00052498264,0.00035687294,0.00019366312,0.0023946865,0.0003954478],"domain_scores_gemma":[0.9958362,0.0009922573,0.00013074456,0.0003729463,0.0025265284,0.00014131112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041323276,0.00006944108,0.00017617547,0.0013301296,0.00034528432,0.00014569964,0.0005244347,0.00008383119,0.0008586104],"category_scores_gemma":[0.006744383,0.00007229376,0.00007360434,0.0025156508,0.00027625408,0.0027991023,0.0006453612,0.0007238774,0.0005243687],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078093103,0.00089392904,0.020013755,0.00011693608,0.000051369625,0.0071157385,0.013226357,0.041346196,0.00048439082,0.00104797,0.009943168,0.9049792],"study_design_scores_gemma":[0.0031066309,0.00052868755,0.008694933,0.00015884891,0.0000052395744,0.0003625573,0.20035449,0.1666261,0.0007693064,0.0034461706,0.6156561,0.00029096947],"about_ca_topic_score_codex":0.00045326859,"about_ca_topic_score_gemma":0.00075167324,"teacher_disagreement_score":0.9046883,"about_ca_system_score_codex":0.00024911805,"about_ca_system_score_gemma":0.0003572902,"threshold_uncertainty_score":0.94011813},"labels":[],"label_agreement":null},{"id":"W3212514152","doi":"","title":"Regime Switching Bandits","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain; Markov decision process; Upper and lower bounds; Stochastic matrix; Markov process; Observable; Computer science; State (computer science); Partially observable Markov decision process; Matrix (chemical analysis); Reinforcement learning; Probably approximately correct learning; Artificial intelligence; Mathematical optimization; Mathematics; Markov model; Algorithm; Machine learning; Unsupervised learning; Generalization error; Statistics","score_opus":0.1121872631780489,"score_gpt":0.4130105025504202,"score_spread":0.3008232393723713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212514152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082169466,0.0027639132,0.87272084,0.0057414593,0.0048091034,0.00087446196,0.000039585375,0.0006715997,0.0302096],"genre_scores_gemma":[0.99512273,0.000006911885,0.0007822564,0.00030343197,0.00025932473,0.000028140503,0.000024443076,0.000010948894,0.0034617847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99571383,0.00018478298,0.0010990128,0.00028172243,0.0023438383,0.00037681556],"domain_scores_gemma":[0.9964792,0.00037049458,0.00052642036,0.0006795596,0.0017928092,0.00015150201],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016955025,0.0001557213,0.00028666947,0.00034056982,0.00047448906,0.002745844,0.00075940206,0.00009541439,0.00008997495],"category_scores_gemma":[0.0050725415,0.00011697036,0.000072423725,0.0015073045,0.000040928207,0.0073641143,0.00023484397,0.00029610484,0.0008845954],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054175274,0.00004579893,0.0012538354,0.00030783407,0.00001934173,0.00007105109,0.0050873626,0.06673161,0.0013783652,0.0009930024,0.028528184,0.89552945],"study_design_scores_gemma":[0.0006979033,0.000041384705,0.0012486996,0.00015637622,0.000005606272,0.00048266395,0.005695292,0.77072996,0.00226205,0.002917672,0.21540877,0.00035364213],"about_ca_topic_score_codex":0.000014196104,"about_ca_topic_score_gemma":0.0000030887559,"teacher_disagreement_score":0.9129533,"about_ca_system_score_codex":0.00008831041,"about_ca_system_score_gemma":0.00026858755,"threshold_uncertainty_score":0.9998933},"labels":[],"label_agreement":null},{"id":"W3212608195","doi":"","title":"Fair Algorithms for Multi-Agent Multi-Armed Bandits","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Sublinear function; Multi-armed bandit; Computer science; Nash equilibrium; Mathematical optimization; Social Welfare; Mathematical economics; Artificial intelligence; Algorithm; Mathematics; Machine learning; Discrete mathematics; Law","score_opus":0.3178937303358701,"score_gpt":0.4768734040535386,"score_spread":0.15897967371766852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212608195","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030717384,0.0007228466,0.99220884,0.0004401992,0.0020317056,0.0010136727,0.00013711094,0.00020231864,0.0001715568],"genre_scores_gemma":[0.91702765,0.00003127621,0.066700436,0.0007126965,0.00069442973,0.0008499573,0.00036899894,0.00006318709,0.013551339],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99495983,0.0001976643,0.0016269413,0.00048545457,0.0020919996,0.00063813815],"domain_scores_gemma":[0.9945136,0.00051964616,0.0007355689,0.00053556345,0.0034376173,0.00025805802],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019557537,0.00028102935,0.00047750314,0.00044019325,0.0006819244,0.0021933727,0.0007167211,0.0001727831,0.00005060016],"category_scores_gemma":[0.004486904,0.00021653077,0.00016939348,0.0013171353,0.00010472837,0.0052282196,0.00017972798,0.00027983348,0.00040514616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112038,0.00027335563,0.00090576085,0.00082338165,0.000055385233,0.000035905774,0.0059637274,0.08091226,0.0010626186,0.00016144222,0.012355158,0.897339],"study_design_scores_gemma":[0.0017917068,0.000049491253,0.0008369175,0.000073120085,0.00000715734,0.00007989419,0.0036781223,0.91362035,0.001996765,0.0000718389,0.07752557,0.0002690395],"about_ca_topic_score_codex":0.000017887185,"about_ca_topic_score_gemma":0.000010951975,"teacher_disagreement_score":0.92550844,"about_ca_system_score_codex":0.00018458211,"about_ca_system_score_gemma":0.0003871471,"threshold_uncertainty_score":0.9988424},"labels":[],"label_agreement":null},{"id":"W3212900133","doi":"10.1109/tcns.2022.3153872","title":"Scalable Operator Allocation for Multirobot Assistance: A Restless Bandit Approach","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Scalability; Leverage (statistics); Robot; Computer science; Operator (biology); Mathematical optimization; Heuristic; Robot kinematics; Distributed computing; Artificial intelligence; Mobile robot; Mathematics","score_opus":0.08808758998774956,"score_gpt":0.3626182202265537,"score_spread":0.27453063023880414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212900133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009635644,0.00069159496,0.9927296,0.0002052945,0.0024353277,0.0022653257,0.00042557012,0.000060065013,0.0002236763],"genre_scores_gemma":[0.98913616,0.000012150117,0.002691304,0.000061010167,0.00035399728,0.002889061,0.000010608447,0.000043300763,0.004802421],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944759,0.0008660421,0.0011282746,0.000757884,0.002199382,0.00057249755],"domain_scores_gemma":[0.9951455,0.0026774022,0.00042854677,0.00086928037,0.0007145382,0.00016471242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004530754,0.00023506323,0.00072029006,0.0003406066,0.0010564806,0.00018215817,0.0009268795,0.00010246306,0.00013560044],"category_scores_gemma":[0.00011139122,0.0002013753,0.00027848443,0.0014015302,0.00012349091,0.00029474206,0.0000055471605,0.0004159614,0.000021663996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008014103,0.00028020653,0.000035224937,0.000026490303,0.00008899849,0.0000020140762,0.00009778426,0.98815864,0.0004523965,0.00014149421,0.0043652803,0.005550031],"study_design_scores_gemma":[0.0035392141,0.00046832074,0.00007844526,0.000029804227,0.000040654126,0.00001425182,0.0008746971,0.9750979,0.00021889243,0.00020984442,0.019190073,0.00023793797],"about_ca_topic_score_codex":0.000054495427,"about_ca_topic_score_gemma":0.00003159976,"teacher_disagreement_score":0.9900383,"about_ca_system_score_codex":0.00030429184,"about_ca_system_score_gemma":0.00021878666,"threshold_uncertainty_score":0.82118464},"labels":[],"label_agreement":null},{"id":"W3213203216","doi":"","title":"An Empirical Study of Neural Kernel Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Thompson sampling; Machine learning; Artificial intelligence; Gaussian process; Bayesian probability; Kernel (algebra); Artificial neural network; Deep neural networks; Process (computing); Gaussian; Mathematics","score_opus":0.3374988530824604,"score_gpt":0.3759152304890423,"score_spread":0.03841637740658188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213203216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94128907,0.000048802918,0.057089392,0.000035178113,0.00056699675,0.0005242145,0.00004024828,0.00006635119,0.0003397311],"genre_scores_gemma":[0.9978426,0.000026831896,0.00017886002,0.00002604829,0.00012700944,0.0000014993747,0.000022306624,0.000030230545,0.0017445958],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943228,0.0012467136,0.0006744272,0.0021629692,0.0010839221,0.0005091949],"domain_scores_gemma":[0.9939777,0.0009856668,0.0005166597,0.002795026,0.0013185082,0.0004064318],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001457743,0.0003855876,0.0008843074,0.00077999296,0.00019674937,0.000269284,0.0032651233,0.0003423361,0.00069633086],"category_scores_gemma":[0.0010374158,0.0003623859,0.00031591865,0.0020624057,0.00029925912,0.0006583608,0.0028250916,0.0011458909,0.000079410616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002084242,0.0019203569,0.1859731,0.00001967146,0.00012641739,0.0019420552,0.0019125324,0.8052868,0.0000459617,0.00006054985,0.0003903529,0.002113764],"study_design_scores_gemma":[0.0021765388,0.001039987,0.19835569,0.000042788644,0.000120105666,0.000012295403,0.022221657,0.76024324,0.00021538258,0.014587685,0.00019898367,0.00078565854],"about_ca_topic_score_codex":0.00026154908,"about_ca_topic_score_gemma":0.00048598592,"teacher_disagreement_score":0.05691053,"about_ca_system_score_codex":0.00018138146,"about_ca_system_score_gemma":0.00039171494,"threshold_uncertainty_score":0.9998828},"labels":[],"label_agreement":null},{"id":"W3215887789","doi":"10.1109/tai.2021.3117743","title":"Delayed Reward Bernoulli Bandits: Optimal Policy and Predictive Meta-Algorithm PARDI","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bernoulli's principle; Computer science; Outcome (game theory); Reinforcement learning; Mathematical optimization; Index (typography); Algorithm; Range (aeronautics); Artificial intelligence; Mathematics; Mathematical economics; Engineering","score_opus":0.19533306039765136,"score_gpt":0.4366686007048083,"score_spread":0.24133554030715693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215887789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015801551,0.00033246618,0.99344355,0.002303076,0.00077555876,0.00036069282,0.0006889727,0.00010247103,0.00041308545],"genre_scores_gemma":[0.9445038,0.0008550307,0.04616744,0.00044524932,0.0005705924,0.00018332405,0.00001484475,0.00007540531,0.0071843225],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9940932,0.0005434546,0.0011270184,0.0013084256,0.0021914588,0.0007364607],"domain_scores_gemma":[0.9946184,0.002598298,0.00018774644,0.0009733269,0.0011644225,0.00045781786],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016378618,0.0003932847,0.00072000164,0.0006974454,0.0007294998,0.0005293017,0.0006665266,0.00021831668,0.0018885583],"category_scores_gemma":[0.0009832603,0.00032278124,0.00046309197,0.0026643893,0.00062547525,0.0007017735,0.000020358359,0.00077410403,0.0008024031],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000276168,0.0004115898,0.0000016233806,0.000004302745,0.0007166246,0.00016032487,0.0009330759,0.22762331,0.0007190156,0.00046858165,0.00027532078,0.7684101],"study_design_scores_gemma":[0.00018284378,0.0009088996,0.000039386254,0.000025253872,0.00059256994,0.00022460084,0.004038605,0.3348873,0.5582369,0.090529755,0.00952305,0.00081081124],"about_ca_topic_score_codex":0.00016682124,"about_ca_topic_score_gemma":0.00023565296,"teacher_disagreement_score":0.94727606,"about_ca_system_score_codex":0.00018715492,"about_ca_system_score_gemma":0.0004765511,"threshold_uncertainty_score":0.99997556},"labels":[],"label_agreement":null},{"id":"W4200629132","doi":"10.2139/ssrn.3978421","title":"Optimal No-Regret Learning in Strongly Monotone Games with Bandit Feedback","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Monotone polygon; Mathematical economics; Mathematical optimization; Computer science; Mathematics; Economics; Machine learning","score_opus":0.0280459300877103,"score_gpt":0.35069296440617387,"score_spread":0.3226470343184636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200629132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79585385,0.004440777,0.19562192,0.0016043873,0.00024520216,0.00022445414,0.0000047545873,0.00005131125,0.0019533408],"genre_scores_gemma":[0.96105355,0.0016447129,0.002867937,0.000026155798,0.00041090694,0.000011575107,0.000006116737,0.000047396083,0.03393166],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923294,0.0005432355,0.0006995134,0.00067499536,0.002354707,0.0033981502],"domain_scores_gemma":[0.9974706,0.0006532565,0.00030743735,0.0004360214,0.0009074549,0.00022523517],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00570812,0.00026851683,0.00048688438,0.00047279082,0.00033724605,0.00049356744,0.0008690569,0.00011505224,0.00077378674],"category_scores_gemma":[0.0023703584,0.00019274169,0.00014607735,0.0015183135,0.0001696642,0.00085355295,0.00018909479,0.004981122,0.00051152654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020016828,0.0005799948,0.07693838,0.000011965096,0.00045997472,0.001607257,0.0012165371,0.6488621,0.0016645459,0.0061642923,0.0011389831,0.25935423],"study_design_scores_gemma":[0.03635082,0.014725344,0.08872917,0.00070646463,0.00016544241,0.025226086,0.1246829,0.212716,0.009410544,0.32559443,0.15663365,0.0050591677],"about_ca_topic_score_codex":0.00003236711,"about_ca_topic_score_gemma":0.0012847467,"teacher_disagreement_score":0.43614614,"about_ca_system_score_codex":0.0011410186,"about_ca_system_score_gemma":0.005417934,"threshold_uncertainty_score":0.99731445},"labels":[],"label_agreement":null},{"id":"W4205863870","doi":"10.1109/lra.2022.3140813","title":"Hybrid Hierarchical Learning for Adaptive Persuasion in Human-Robot Interaction","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Persuasion; Robot; Artificial intelligence; Human–computer interaction; Robustness (evolution); Benchmark (surveying); Architecture; Machine learning; Psychology","score_opus":0.09853142058525839,"score_gpt":0.4002143626322813,"score_spread":0.3016829420470229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205863870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31437424,0.000014605968,0.6806785,0.004165967,0.0003780014,0.00031300835,0.000006640903,0.000042230935,0.000026840278],"genre_scores_gemma":[0.9920699,0.000003297887,0.0071570547,0.00032481877,0.00009653172,0.00007955681,0.00001977483,0.000015686735,0.0002333772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976413,0.0003316676,0.00043494682,0.0004204961,0.00090552855,0.00026603855],"domain_scores_gemma":[0.9984812,0.001029395,0.00018073063,0.00015562859,0.00008785235,0.00006519152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014530588,0.00011413359,0.00019760933,0.0005506259,0.0006547672,0.0001627981,0.00023819106,0.000023458055,0.00007495341],"category_scores_gemma":[0.00041355524,0.0001073788,0.000068274676,0.0003507277,0.00007671664,0.00037300523,0.00012753738,0.00048031894,0.000009266347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004897959,0.000037970283,0.00022664212,0.0000035780017,0.000005379326,0.000010740826,0.0004741579,0.96737516,0.009630842,0.00027809292,0.0009120476,0.0209964],"study_design_scores_gemma":[0.0007075059,0.00023205606,0.0027475243,0.000010960168,0.000003686606,0.000019914885,0.0008176317,0.98869044,0.00063201826,0.003948492,0.0020404307,0.00014935897],"about_ca_topic_score_codex":0.000014052161,"about_ca_topic_score_gemma":0.000004621309,"teacher_disagreement_score":0.6776957,"about_ca_system_score_codex":0.00020148592,"about_ca_system_score_gemma":0.000026269829,"threshold_uncertainty_score":0.5036006},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11482899344122152,"score_gpt":0.33081690938041297,"score_spread":0.21598791593919145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206530644","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035801734,0.00020975135,0.03946491,0.00012864258,0.0006729875,0.0006799015,0.0010921597,0.00024357227,0.9575045],"genre_scores_gemma":[0.000032750257,0.00007456076,0.00087545987,0.00014334261,0.00083583535,0.0000019641834,0.00011502819,0.000084927866,0.9978361],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99306303,0.0003477292,0.0006209292,0.0017688914,0.003438138,0.0007612815],"domain_scores_gemma":[0.9947739,0.0013129212,0.000555442,0.0016787193,0.00090785534,0.000771136],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007940043,0.0006261509,0.001065312,0.0006843009,0.0004369043,0.00037265205,0.003900326,0.0006348997,0.0000718549],"category_scores_gemma":[0.00073524093,0.0006188633,0.00057100604,0.00014454749,0.00071267114,0.00035370217,0.002102896,0.0015481089,0.00097316795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011946069,0.00001455856,0.0000011423904,0.000028229162,0.00011137994,0.0017723065,0.00006649935,0.000036204325,0.000009526237,0.041974094,0.9389485,0.016918065],"study_design_scores_gemma":[0.0007876003,0.00011334562,0.000012763876,0.00005410996,0.00007220427,0.000026020514,0.000093029776,0.0017905787,0.00020626701,0.0001716167,0.9960379,0.00063458167],"about_ca_topic_score_codex":0.000040318864,"about_ca_topic_score_gemma":0.000001711019,"teacher_disagreement_score":0.057089347,"about_ca_system_score_codex":0.00074598106,"about_ca_system_score_gemma":0.0011258054,"threshold_uncertainty_score":0.9998047},"labels":[],"label_agreement":null},{"id":"W4207076830","doi":"10.3982/ecta18324","title":"Dynamically Aggregating Diverse Information","year":2022,"lang":"en","type":"article","venue":"Econometrica","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Computer science; Component (thermodynamics); Sample (material); Brownian motion; Gaussian; Point (geometry); Binary number; Mathematical optimization; Mathematics; Statistics","score_opus":0.10806584146520383,"score_gpt":0.3941978130461244,"score_spread":0.2861319715809206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207076830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46530578,0.0004685154,0.36280093,0.0056043244,0.0033275443,0.0014544865,0.0007733958,0.00040973272,0.1598553],"genre_scores_gemma":[0.9942659,0.000005503522,0.003301535,0.00024088209,0.00004645077,0.000047686208,0.000021222775,0.0000058879114,0.0020649175],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766225,0.000118852695,0.0005076086,0.00023813192,0.0012032827,0.000269881],"domain_scores_gemma":[0.9977537,0.0013076109,0.00027324527,0.000401454,0.00015148279,0.00011254919],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002097907,0.000074003816,0.00015721144,0.0019125822,0.0005422781,0.00024526566,0.00093164603,0.00001934252,0.009794329],"category_scores_gemma":[0.0064191027,0.00006738578,0.00007936535,0.00450893,0.000049617585,0.0013185154,0.0009168174,0.00025799594,0.0021096822],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002051791,0.000035887933,0.0041678953,0.0000014403774,0.000009197997,0.000006741534,0.00038969642,0.022575928,0.0000030268845,0.0004837156,0.007441931,0.964864],"study_design_scores_gemma":[0.0006182592,0.00025399146,0.025172558,0.000001397792,0.0000030968363,0.000021304106,0.0051775035,0.20011432,0.000035403395,0.020814225,0.7474874,0.00030049757],"about_ca_topic_score_codex":0.000017684537,"about_ca_topic_score_gemma":0.0000020327168,"teacher_disagreement_score":0.96456355,"about_ca_system_score_codex":0.00031035766,"about_ca_system_score_gemma":0.00006806033,"threshold_uncertainty_score":0.9986673},"labels":[],"label_agreement":null},{"id":"W4210906234","doi":"10.1287/opre.2021.2240","title":"Dynamic Learning and Decision Making via Basis Weight Vectors","year":2022,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Continuation; Basis (linear algebra); Computer science; Mathematical optimization; Bellman equation; Process (computing); Set (abstract data type); Time horizon; Decision maker; Class (philosophy); Mathematics; Artificial intelligence; Algorithm; Operations research","score_opus":0.10884847178026896,"score_gpt":0.5124579529953524,"score_spread":0.4036094812150834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210906234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5724715,0.0012053136,0.41993532,0.0019989484,0.00043345094,0.00096334936,0.000044869685,0.00009020891,0.0028570262],"genre_scores_gemma":[0.9714202,0.00010287076,0.01999274,0.000025173018,0.000053112784,0.00023807597,0.0000124075095,0.000030714837,0.008124648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9909055,0.0016352871,0.00050518813,0.0008602448,0.0054107513,0.00068300276],"domain_scores_gemma":[0.9937227,0.0045255395,0.000033715292,0.0006075744,0.0009256215,0.00018489128],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010797964,0.00013657793,0.0002258985,0.0016948971,0.0053423895,0.0008958862,0.0010072833,0.00005510056,0.008681056],"category_scores_gemma":[0.0070148674,0.000114835035,0.000064567175,0.0039962977,0.00030615204,0.0005689766,0.0020558008,0.0015517205,0.0004772037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010646248,0.00010958795,0.0034521467,0.0000033115905,0.000016506576,0.00007558951,0.00093730364,0.15961713,0.0025582865,0.00042994766,0.0020041112,0.8306896],"study_design_scores_gemma":[0.0004349611,0.00033698752,0.0047015306,0.000013010366,0.000002478585,0.000072201336,0.0033867848,0.9135497,0.00018882773,0.0141150635,0.06297898,0.00021944317],"about_ca_topic_score_codex":0.000067682624,"about_ca_topic_score_gemma":0.00035286488,"teacher_disagreement_score":0.8304702,"about_ca_system_score_codex":0.0004311402,"about_ca_system_score_gemma":0.0002724958,"threshold_uncertainty_score":0.99595255},"labels":[],"label_agreement":null},{"id":"W4210948966","doi":"10.1017/9781108571401.034","title":"Exp3 for Adversarial Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Adversarial system; Content (measure theory); Computer science; Operations research; Information retrieval; Artificial intelligence; Mathematics","score_opus":0.1468442251773642,"score_gpt":0.33969331728319785,"score_spread":0.19284909210583365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210948966","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000059564986,0.000088064706,0.10490989,0.000115242336,0.0008906349,0.0012401873,0.0020603272,0.0001492683,0.8905404],"genre_scores_gemma":[0.0002334298,0.00003804717,0.0017462677,0.0000958521,0.0012328898,0.00000311079,0.00011033211,0.000083241925,0.9964568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99551946,0.00009135813,0.0005292355,0.0014235274,0.00190233,0.0005340893],"domain_scores_gemma":[0.9954698,0.0014441992,0.00047875405,0.0010825485,0.0010016626,0.0005230232],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059409486,0.0005169849,0.0008703536,0.0004709438,0.00042661696,0.00015354007,0.0022378457,0.000569782,0.000050416475],"category_scores_gemma":[0.00083141116,0.0005220938,0.0006328738,0.00004054155,0.00046872185,0.0002746503,0.001125069,0.0007889897,0.00025958355],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013844182,0.000017122966,8.46956e-7,0.00005765379,0.0002350709,0.00062174734,0.000105281535,0.00013740647,0.000058723865,0.56949437,0.41505182,0.012835514],"study_design_scores_gemma":[0.0016698376,0.00019243127,0.0000024551118,0.0000472181,0.00009483634,0.000007989774,0.00006984898,0.0023803115,0.0005045986,0.00041729113,0.9940772,0.00053600234],"about_ca_topic_score_codex":0.00002260259,"about_ca_topic_score_gemma":0.000002384577,"teacher_disagreement_score":0.5790253,"about_ca_system_score_codex":0.0002800994,"about_ca_system_score_gemma":0.00039967892,"threshold_uncertainty_score":0.9997231},"labels":[],"label_agreement":null},{"id":"W4210963705","doi":"10.1017/9781108571401.025","title":"Stochastic Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Mathematical optimization; Mathematics","score_opus":0.11979194893295043,"score_gpt":0.324009890147398,"score_spread":0.20421794121444758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210963705","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006588361,0.00013267431,0.102954805,0.000089863264,0.00043011486,0.00056903,0.0007287989,0.00016880654,0.89491934],"genre_scores_gemma":[0.000902759,0.000025144356,0.00041518192,0.00009117535,0.0005236463,9.017018e-7,0.000045435816,0.00007757727,0.9979182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949664,0.000113132955,0.0005054659,0.0013867792,0.0025194804,0.00050877716],"domain_scores_gemma":[0.9958112,0.0010378446,0.00044637828,0.0012718095,0.0008070286,0.0006257222],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047974836,0.00053574255,0.0008436346,0.0005614132,0.00035433465,0.00016308528,0.0024066928,0.0004814042,0.00008521656],"category_scores_gemma":[0.0006630486,0.0005304795,0.000425456,0.00005431943,0.0005826276,0.00023289563,0.0015329354,0.0012255224,0.00104917],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048961723,0.000020630472,7.6291656e-7,0.00004581073,0.00024932917,0.0024660297,0.00011248537,0.001012908,0.00003433605,0.7218031,0.25903133,0.014733639],"study_design_scores_gemma":[0.00067793194,0.00011523627,0.0000055339647,0.000070447204,0.0000761273,0.000021486807,0.00004954399,0.004092747,0.00009046318,0.00032121444,0.9939188,0.000560475],"about_ca_topic_score_codex":0.000023873275,"about_ca_topic_score_gemma":0.0000018687995,"teacher_disagreement_score":0.7348875,"about_ca_system_score_codex":0.00027579904,"about_ca_system_score_gemma":0.00034105332,"threshold_uncertainty_score":0.9997286},"labels":[],"label_agreement":null},{"id":"W4210974166","doi":"10.1017/9781108571401.032","title":"Adversarial Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Adversarial system; Computer science; Artificial intelligence; Mathematics","score_opus":0.11693523532589903,"score_gpt":0.322636180878772,"score_spread":0.20570094555287297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210974166","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007529015,0.00009653202,0.020086816,0.000114026305,0.00082183466,0.00058548833,0.0009084964,0.00018093475,0.97719836],"genre_scores_gemma":[0.0004061801,0.000058995243,0.00058163435,0.00010395333,0.0010138823,6.8376823e-7,0.00006277908,0.0000746351,0.99769723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946663,0.0001427622,0.0005394318,0.0014511837,0.0026833818,0.0005169581],"domain_scores_gemma":[0.9959385,0.0008704062,0.0004809911,0.001291867,0.0007983242,0.00061994797],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005501669,0.00054764346,0.0008739706,0.0005332594,0.0003745946,0.00016695473,0.002564318,0.0005984436,0.00011736349],"category_scores_gemma":[0.00061595853,0.0005475213,0.00052163715,0.00005432543,0.0005887923,0.00029461307,0.0017117151,0.0012749948,0.0010186243],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007345558,0.000016687254,0.0000019437707,0.000032857795,0.00023491526,0.002763023,0.00009333159,0.00015371051,0.00003767199,0.6129887,0.37075704,0.012185572],"study_design_scores_gemma":[0.0010389541,0.00011708657,0.0000064871497,0.00004700059,0.00007836867,0.000015102995,0.000049662467,0.0013670158,0.0002424178,0.00023650944,0.99625444,0.00054692314],"about_ca_topic_score_codex":0.000042030922,"about_ca_topic_score_gemma":0.0000025632105,"teacher_disagreement_score":0.62549746,"about_ca_system_score_codex":0.00030905945,"about_ca_system_score_gemma":0.00041457132,"threshold_uncertainty_score":0.9997592},"labels":[],"label_agreement":null},{"id":"W4211022090","doi":"10.1017/9781108571401.039","title":"Non-stationary Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Mathematics","score_opus":0.09910510505895859,"score_gpt":0.31753404481789693,"score_spread":0.21842893975893835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211022090","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001220368,0.00009447955,0.019815765,0.00012424316,0.0003770816,0.0005471076,0.00080517755,0.00011418026,0.9781098],"genre_scores_gemma":[0.0007337286,0.000060091494,0.00047800515,0.00012423984,0.00033679933,0.0000010646706,0.000091696376,0.000061153085,0.9981132],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954984,0.00007301717,0.0004583344,0.0012151694,0.0023511655,0.00040388023],"domain_scores_gemma":[0.9965,0.00076233706,0.00041704104,0.0010265002,0.0008119108,0.000482204],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004089881,0.0004450379,0.00066143874,0.00053687074,0.0003522866,0.00017491596,0.0020102884,0.0003926986,0.000091881506],"category_scores_gemma":[0.00024155703,0.0004519147,0.00035363148,0.00005043495,0.00047011478,0.0003068354,0.0012000784,0.0009102737,0.00086036115],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025400892,0.000012471106,0.000003884846,0.00003364291,0.00013936551,0.0022533962,0.00009589075,0.000100978585,0.000031236163,0.45517704,0.529065,0.012833055],"study_design_scores_gemma":[0.000593497,0.00008542747,0.000051380885,0.000050408107,0.000045370532,0.000015905418,0.00007265763,0.0011862045,0.00016572732,0.00045417488,0.9968121,0.0004671337],"about_ca_topic_score_codex":0.000023961125,"about_ca_topic_score_gemma":0.0000015089967,"teacher_disagreement_score":0.4677471,"about_ca_system_score_codex":0.0002658245,"about_ca_system_score_gemma":0.00036281324,"threshold_uncertainty_score":0.99991757},"labels":[],"label_agreement":null},{"id":"W4211042912","doi":"10.1017/9781108571401.037","title":"Other Topics","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Information retrieval; Content (measure theory); World Wide Web; Data science; Mathematics","score_opus":0.13200117096951755,"score_gpt":0.3249582694357428,"score_spread":0.19295709846622525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211042912","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000034500476,0.00010618654,0.016566763,0.00019731288,0.00031756875,0.00036898843,0.00041910913,0.00012076848,0.98189986],"genre_scores_gemma":[0.000084645806,0.000025804731,0.00043360368,0.00021073334,0.00048222436,4.533906e-7,0.000011486744,0.00005447838,0.99869657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99646014,0.000086489345,0.00036003548,0.0009924193,0.0017479962,0.00035294902],"domain_scores_gemma":[0.99732155,0.00039329578,0.0003055124,0.0011238415,0.0004893837,0.00036643198],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033077947,0.00037021434,0.0005843402,0.00032653607,0.00021739214,0.00016600308,0.0019938212,0.00039003944,0.0001086618],"category_scores_gemma":[0.0002569177,0.00035970184,0.00033764335,0.000031792955,0.00040720621,0.00016548391,0.00112538,0.0008131634,0.00060706073],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078330246,0.0000050110093,0.0000016034135,0.000012737439,0.00006782167,0.00058085896,0.000040436098,0.0000127111625,0.00000976096,0.8083191,0.1731768,0.017694829],"study_design_scores_gemma":[0.0003658898,0.00005405551,0.000006228981,0.000030724095,0.00003428629,0.000008269286,0.0000435535,0.00028788552,0.00013932963,0.0007217118,0.9979398,0.00036822355],"about_ca_topic_score_codex":0.00003559046,"about_ca_topic_score_gemma":0.0000026697062,"teacher_disagreement_score":0.82476306,"about_ca_system_score_codex":0.00020287323,"about_ca_system_score_gemma":0.00019209262,"threshold_uncertainty_score":0.9998855},"labels":[],"label_agreement":null},{"id":"W4211056168","doi":"10.1017/9781108571401.014","title":"Adversarial Bandits with Finitely Many Arms","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Adversarial system; Computer science; Content (measure theory); Computer security; Internet privacy; Political science; Business; Artificial intelligence; Mathematics","score_opus":0.10016456268885476,"score_gpt":0.29781126606216896,"score_spread":0.1976467033733142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211056168","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029107543,0.0000761886,0.032500487,0.000141792,0.00043632288,0.00073232607,0.00085266074,0.00017868426,0.9650524],"genre_scores_gemma":[0.001460426,0.00004599646,0.0008361629,0.00010930551,0.00054288417,0.0000013675896,0.00006221973,0.000089165485,0.99685246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942686,0.00013094537,0.00048668144,0.0015766824,0.002952936,0.0005841865],"domain_scores_gemma":[0.995771,0.0009398603,0.0005459539,0.0013157818,0.0008006649,0.00062677305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046018662,0.000639874,0.00092932093,0.0006008401,0.00036507586,0.00026976742,0.0024187074,0.0005014431,0.00010449366],"category_scores_gemma":[0.00028730993,0.0005572598,0.0003604395,0.000073850526,0.000780043,0.00035754027,0.0011999004,0.0013023267,0.00054803246],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032569387,0.000037016645,0.00001147249,0.00006954301,0.000566998,0.00896487,0.0003216395,0.00035059114,0.00003264409,0.73163146,0.23795095,0.016805895],"study_design_scores_gemma":[0.0016960579,0.0002964066,0.000031529362,0.00009359409,0.00011893137,0.000037559836,0.00013574598,0.0006621361,0.0001854437,0.0002194934,0.99582607,0.0006970086],"about_ca_topic_score_codex":0.000048115522,"about_ca_topic_score_gemma":0.0000054244706,"teacher_disagreement_score":0.75787514,"about_ca_system_score_codex":0.0002981691,"about_ca_system_score_gemma":0.00046707774,"threshold_uncertainty_score":0.9996879},"labels":[],"label_agreement":null},{"id":"W4211058984","doi":"10.1017/9781108571401.041","title":"Pure Exploration","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Information retrieval; Mathematics","score_opus":0.1638929471716128,"score_gpt":0.3254588598612687,"score_spread":0.16156591268965592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211058984","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000051796815,0.00009382247,0.038376674,0.00023241059,0.00031413563,0.00049763697,0.000366716,0.00015125451,0.9599622],"genre_scores_gemma":[0.0005805319,0.00007586633,0.00030755447,0.00008642014,0.0003385325,0.00000103362,0.000058380745,0.000052251442,0.99849945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99594915,0.00010978418,0.0003988282,0.0010912857,0.0021195847,0.00033138195],"domain_scores_gemma":[0.99697083,0.00044907499,0.00038970105,0.0010642825,0.00074417697,0.00038191784],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040122948,0.00038872415,0.0005707989,0.00043576947,0.00029554142,0.00023500413,0.0017595452,0.00040887162,0.000050713817],"category_scores_gemma":[0.0003533787,0.00038876286,0.00030811148,0.000044165914,0.00035422758,0.0005184197,0.001025904,0.000859012,0.000664909],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014978668,0.000006582458,4.5922596e-7,0.000019668516,0.00006768629,0.0012001288,0.00010780749,0.00006917117,0.000031878622,0.74828887,0.23078167,0.019276317],"study_design_scores_gemma":[0.00039228672,0.00007418036,0.0000022004476,0.000039445596,0.000035634243,0.000010516652,0.00015810507,0.00051309634,0.00029472605,0.0010844426,0.99700755,0.00038781684],"about_ca_topic_score_codex":0.000013233206,"about_ca_topic_score_gemma":0.0000024428743,"teacher_disagreement_score":0.7662259,"about_ca_system_score_codex":0.00023821305,"about_ca_system_score_gemma":0.00022328731,"threshold_uncertainty_score":0.9998564},"labels":[],"label_agreement":null},{"id":"W4211059639","doi":"10.1017/9781108571401.006","title":"Stochastic Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Economics","score_opus":0.11560849620300741,"score_gpt":0.3168541208218191,"score_spread":0.20124562461881168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211059639","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000488186,0.00013921474,0.08056353,0.00008807271,0.0004194935,0.0005410046,0.00064521696,0.00015784492,0.9174407],"genre_scores_gemma":[0.0012784206,0.000021381235,0.00022025855,0.00008628184,0.00037936572,8.800201e-7,0.000036116424,0.00007010363,0.9979072],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99507344,0.00010744376,0.00047091983,0.0013519791,0.0025057576,0.00049044],"domain_scores_gemma":[0.9959933,0.0010208542,0.00043171016,0.0012407085,0.0007127907,0.000600622],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004513962,0.0005112229,0.0008048364,0.00055103394,0.00034109078,0.0002171587,0.0024121052,0.00044198468,0.000088882436],"category_scores_gemma":[0.0005778166,0.00050794595,0.00040469374,0.000048531834,0.00056937267,0.00023307503,0.0014893253,0.001105525,0.0009363011],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027035648,0.000011090974,4.3749804e-7,0.000025552712,0.00015155131,0.0015523086,0.000066660876,0.00032671398,0.000020382415,0.730881,0.25393134,0.012762645],"study_design_scores_gemma":[0.0006241272,0.00009830118,0.000007438519,0.00006408695,0.00007134367,0.000022097369,0.00005103853,0.0015371153,0.000067528345,0.0005236361,0.99639416,0.0005391585],"about_ca_topic_score_codex":0.000021962984,"about_ca_topic_score_gemma":0.000001860393,"teacher_disagreement_score":0.74246275,"about_ca_system_score_codex":0.00029473414,"about_ca_system_score_gemma":0.0003172402,"threshold_uncertainty_score":0.9998416},"labels":[],"label_agreement":null},{"id":"W4211077145","doi":"10.1017/9781108571401.031","title":"Asymptotic Lower Bounds for Stochastic Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Applied mathematics; Mathematical optimization; Computer science","score_opus":0.10754279321445281,"score_gpt":0.3270016872116386,"score_spread":0.21945889399718577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211077145","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011909962,0.00012421317,0.31650048,0.00009907204,0.0008602024,0.0012319086,0.0013780223,0.00015094422,0.6796432],"genre_scores_gemma":[0.0015501629,0.00001520929,0.00089850323,0.00010977001,0.0007068586,0.000004189972,0.00008117706,0.00010811206,0.996526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950913,0.0000818275,0.00057645893,0.0015311034,0.002069521,0.0006497505],"domain_scores_gemma":[0.994655,0.0018427476,0.0004892743,0.001230699,0.001176865,0.0006053733],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060568104,0.0006061848,0.0009616341,0.0005710662,0.00051081233,0.00024897134,0.0022411232,0.0005449331,0.00005260161],"category_scores_gemma":[0.0009929261,0.0006063469,0.0006311309,0.000055502915,0.00063218095,0.00026666495,0.0010573245,0.0008923636,0.00033608335],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016484796,0.000049935268,8.5629176e-7,0.0001283458,0.00046736395,0.0010390095,0.0001258116,0.0016270956,0.000043665896,0.6959745,0.28750864,0.011386279],"study_design_scores_gemma":[0.0012778082,0.000339132,0.0000041595817,0.000096857184,0.00014451683,0.000015790045,0.00004113324,0.009691535,0.000068964975,0.0006841411,0.9869686,0.0006673754],"about_ca_topic_score_codex":0.000013219001,"about_ca_topic_score_gemma":0.0000025440809,"teacher_disagreement_score":0.6994599,"about_ca_system_score_codex":0.0003702545,"about_ca_system_score_gemma":0.00046772245,"threshold_uncertainty_score":0.9996388},"labels":[],"label_agreement":null},{"id":"W4211113691","doi":"10.1017/9781108571401.044","title":"Thompson Sampling","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sampling (signal processing); Computer science; Computer vision","score_opus":0.20164323119999739,"score_gpt":0.3504672175813527,"score_spread":0.1488239863813553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211113691","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006647279,0.00015288289,0.047753863,0.00012484833,0.00038154318,0.0004399982,0.0004487699,0.00017265623,0.9505188],"genre_scores_gemma":[0.0003445206,0.00006211541,0.0013245585,0.00009871352,0.0004082292,5.619701e-7,0.00003186334,0.00006725714,0.9976622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995391,0.00010363467,0.00046139464,0.0013308474,0.0022467,0.00046643565],"domain_scores_gemma":[0.9962285,0.0009819436,0.00042535688,0.0012267043,0.00064765965,0.00048979226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005541827,0.0004686382,0.0007583228,0.00048619683,0.0003692966,0.00025800586,0.0023758528,0.00043609543,0.00007814335],"category_scores_gemma":[0.00045992137,0.00046951862,0.0004240531,0.000045625875,0.00044196183,0.00023760152,0.001612759,0.0011297603,0.0005357892],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020346558,0.000008168447,0.0000016712944,0.000029231462,0.00011427579,0.0009562899,0.000071758666,0.0000918272,0.000058488436,0.8774192,0.089448094,0.031597544],"study_design_scores_gemma":[0.00041186492,0.00006307287,0.000010601477,0.000061641265,0.000048415826,0.000014405683,0.00008269515,0.00062648644,0.0001784416,0.00048092823,0.9975464,0.00047509768],"about_ca_topic_score_codex":0.000022863156,"about_ca_topic_score_gemma":0.0000015429908,"teacher_disagreement_score":0.9080983,"about_ca_system_score_codex":0.00029329417,"about_ca_system_score_gemma":0.0002456865,"threshold_uncertainty_score":0.99977565},"labels":[],"label_agreement":null},{"id":"W4211119672","doi":"10.1017/9781108571401.017","title":"Lower Bounds for Bandits with Finitely Many Arms","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Combinatorics; Mathematics","score_opus":0.10913095436271733,"score_gpt":0.3121324960950227,"score_spread":0.20300154173230536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211119672","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003172265,0.00010023459,0.11066399,0.00016631406,0.0004101714,0.0011812504,0.0014727492,0.00014457051,0.885829],"genre_scores_gemma":[0.0010536716,0.000034166264,0.0016605065,0.00014419228,0.00038473745,0.0000049426308,0.00007482809,0.000103011065,0.99653995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99530715,0.000066381275,0.0004527769,0.0014939343,0.0020739508,0.0006058369],"domain_scores_gemma":[0.99542284,0.0012755762,0.00048437022,0.0012037739,0.0010896112,0.00052384456],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049214315,0.0005934607,0.0008754752,0.00052536867,0.0004375276,0.0003497973,0.0020864445,0.00044577877,0.00005196274],"category_scores_gemma":[0.0002971665,0.00051363575,0.00042487076,0.000059354657,0.0007150434,0.00031357058,0.000761248,0.0008292683,0.00017713617],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003371621,0.000042108426,0.0000060131315,0.00011204338,0.00045743393,0.0025322007,0.0001852758,0.00014758858,0.000027365566,0.6629704,0.31609893,0.014049007],"study_design_scores_gemma":[0.0015011214,0.00052049936,0.000016562748,0.000098113036,0.00011072597,0.000023157532,0.0000872891,0.00088403333,0.0001729976,0.0004809519,0.9954507,0.00065388106],"about_ca_topic_score_codex":0.000017633876,"about_ca_topic_score_gemma":0.000005087124,"teacher_disagreement_score":0.67935175,"about_ca_system_score_codex":0.00026794174,"about_ca_system_score_gemma":0.000411902,"threshold_uncertainty_score":0.99973154},"labels":[],"label_agreement":null},{"id":"W4211129173","doi":"10.1017/9781108571401.003","title":"Introduction","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.09092964838076466,"score_gpt":0.3070685843658825,"score_spread":0.21613893598511785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211129173","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000038113815,0.0000862313,0.018268807,0.00055520487,0.00063518406,0.0003872611,0.0002572333,0.00015243831,0.97965384],"genre_scores_gemma":[0.00012858414,0.000051043982,0.00037560193,0.00006511262,0.001582864,4.8854315e-7,0.0000390154,0.000048650007,0.9977086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99599147,0.00010201007,0.00038696226,0.0012682093,0.0019148134,0.00033652596],"domain_scores_gemma":[0.9970224,0.000367356,0.00036552866,0.0011784672,0.0007078667,0.00035841676],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004691056,0.00036959746,0.0005803148,0.0004600122,0.00026835973,0.00017783666,0.001637741,0.0003539395,0.00012296122],"category_scores_gemma":[0.0004626286,0.00037306384,0.00030970827,0.000043108565,0.00044667025,0.00025792368,0.0010363217,0.000937436,0.0009389389],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010843329,0.000003919629,2.719087e-7,0.000009470804,0.000050175542,0.0003185575,0.000019390602,0.000027510225,0.000028054988,0.52167314,0.46596968,0.01179135],"study_design_scores_gemma":[0.00032929648,0.00006970072,0.00000519292,0.000015787926,0.000043049364,0.00001835126,0.00004835617,0.0003606119,0.0003061661,0.00034527693,0.9981015,0.0003567577],"about_ca_topic_score_codex":0.000017777746,"about_ca_topic_score_gemma":0.0000010300396,"teacher_disagreement_score":0.53213173,"about_ca_system_score_codex":0.00029609815,"about_ca_system_score_gemma":0.00018485208,"threshold_uncertainty_score":0.99987215},"labels":[],"label_agreement":null},{"id":"W4211143440","doi":"10.1017/9781108571401.016","title":"The Exp3-IX Algorithm","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Algorithm; Computer science","score_opus":0.09735901328993013,"score_gpt":0.3147774227942208,"score_spread":0.21741840950429064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211143440","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012662126,0.00043393573,0.042533565,0.00027623778,0.0006088802,0.000611598,0.0005357672,0.00015020565,0.9548485],"genre_scores_gemma":[0.000041544918,0.00026634274,0.0008827424,0.00010178332,0.00047603305,0.0000017155144,0.000021586151,0.00006942865,0.99813884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944917,0.00019422323,0.0005443699,0.0012731913,0.0028866061,0.0006099116],"domain_scores_gemma":[0.99434835,0.0020180314,0.0004990482,0.0017445099,0.0008754295,0.0005146055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00090357085,0.0005233904,0.0006639976,0.0002942071,0.001063156,0.0004872802,0.003915399,0.00041464408,0.000032250355],"category_scores_gemma":[0.00050686876,0.00040266945,0.000495856,0.000057028323,0.0010920177,0.00023721586,0.0021418897,0.0013324182,0.0006445459],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011326283,0.0000062092467,3.4086287e-7,0.000007886262,0.00013330046,0.0009989261,0.00005558575,0.000011987221,0.000007619871,0.50624985,0.2879847,0.20443036],"study_design_scores_gemma":[0.0004438637,0.00007638917,0.0000050941953,0.000031210056,0.000046495337,0.000020298621,0.00017153779,0.001837633,0.00014254822,0.0007604758,0.99602103,0.00044342843],"about_ca_topic_score_codex":0.000037126643,"about_ca_topic_score_gemma":0.000003361062,"teacher_disagreement_score":0.7080363,"about_ca_system_score_codex":0.00030709465,"about_ca_system_score_gemma":0.0003400967,"threshold_uncertainty_score":0.9998425},"labels":[],"label_agreement":null},{"id":"W4211152972","doi":"10.1017/9781108571401.045","title":"Beyond Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.09638812491299197,"score_gpt":0.31239178348081303,"score_spread":0.21600365856782106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211152972","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006940721,0.00018339233,0.009716588,0.00013253049,0.00048367542,0.0005091112,0.000795808,0.00016041019,0.98801154],"genre_scores_gemma":[0.0004379108,0.000066212706,0.0003431513,0.0001469143,0.0004265966,7.1936086e-7,0.00004723505,0.00006970896,0.99846154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99493474,0.00011700964,0.00048428605,0.0013944274,0.0025770895,0.00049247924],"domain_scores_gemma":[0.99606895,0.0008300855,0.00043849964,0.0013253101,0.00073303044,0.000604119],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00050529704,0.0005138929,0.00081143185,0.0005489456,0.00035911327,0.00024079566,0.0025745146,0.00049307774,0.00011358935],"category_scores_gemma":[0.0003944774,0.0005097425,0.00044157825,0.000050739578,0.0005888999,0.00027845032,0.0016424427,0.0011213114,0.0009413401],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014017936,0.000006732328,0.0000012077992,0.000016871712,0.00009392189,0.0014057606,0.000041492694,0.00002088481,0.000020075935,0.6705526,0.3165338,0.011166469],"study_design_scores_gemma":[0.0005861884,0.00008883925,0.000011548354,0.000038735,0.000058884933,0.000019295921,0.000048575464,0.0003458469,0.00025674238,0.0011444653,0.9968817,0.0005191395],"about_ca_topic_score_codex":0.000022613263,"about_ca_topic_score_gemma":0.0000023330938,"teacher_disagreement_score":0.6803479,"about_ca_system_score_codex":0.00027821166,"about_ca_system_score_gemma":0.00030218615,"threshold_uncertainty_score":0.99983656},"labels":[],"label_agreement":null},{"id":"W4211163949","doi":"10.1017/9781108571401.046","title":"Partial Monitoring","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Mathematics","score_opus":0.15381143126167723,"score_gpt":0.33711437854307724,"score_spread":0.1833029472814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211163949","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002483018,0.00013573612,0.011489651,0.00006778072,0.00071018777,0.00037359426,0.00026118953,0.00016041879,0.9867766],"genre_scores_gemma":[0.0016705223,0.000057786452,0.00038733735,0.00002347416,0.0008487034,7.592618e-7,0.000011122264,0.000056384884,0.9969439],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99566084,0.00009875634,0.00042136043,0.0011489214,0.0022243147,0.0004457859],"domain_scores_gemma":[0.9969345,0.0006032612,0.0003508635,0.0010684676,0.00054078404,0.0005021269],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041768188,0.00041345312,0.00063953176,0.00036165296,0.00032451542,0.00022596125,0.0020376665,0.0003803601,0.00003588534],"category_scores_gemma":[0.00034440236,0.00042264693,0.00036354523,0.00003669987,0.0003990244,0.0002452723,0.0014313232,0.0009934909,0.0005097843],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042658535,0.00001600902,0.000020126496,0.000039734856,0.00023682711,0.0036673252,0.00013633035,0.00012769012,0.00014057243,0.8225113,0.12698953,0.04568793],"study_design_scores_gemma":[0.00041947403,0.00006255466,0.00001667259,0.000053089007,0.000046593606,0.000009464778,0.0000698884,0.0003858558,0.0012850474,0.00015427393,0.9970821,0.00041496832],"about_ca_topic_score_codex":0.000027728749,"about_ca_topic_score_gemma":4.067969e-7,"teacher_disagreement_score":0.8700926,"about_ca_system_score_codex":0.0002657223,"about_ca_system_score_gemma":0.00021720173,"threshold_uncertainty_score":0.99982256},"labels":[],"label_agreement":null},{"id":"W4211171003","doi":"10.1017/9781108571401.001","title":"Preface","year":2020,"lang":"en","type":"other","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Information retrieval; World Wide Web; Mathematics","score_opus":0.22434086232381706,"score_gpt":0.49645233803165617,"score_spread":0.2721114757078391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211171003","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.4425618e-8,0.00032627428,0.12101754,0.0008416518,0.0002557897,0.00018853058,0.00003286716,0.00022497625,0.8771123],"genre_scores_gemma":[0.000010706913,0.000045153032,0.011377232,0.0002084583,0.00046290076,0.000008132679,0.0000040674713,0.00023810942,0.98764527],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99667084,0.00007925753,0.00023958994,0.00061317434,0.002169687,0.00022745595],"domain_scores_gemma":[0.99858975,0.00035061283,0.00012327278,0.0007101807,0.00005123667,0.00017492441],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00035533597,0.00015363267,0.0003126072,0.0003066627,0.000023970868,0.00013587423,0.0012733198,0.00016129669,0.17646468],"category_scores_gemma":[0.0018831125,0.00009562924,0.00008506998,0.00065956236,0.000085409665,0.000050433893,0.0003402798,0.00024611468,0.046714637],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017631387,0.0000047217723,0.0000065833015,0.0000019498757,0.000007331527,0.000013645889,0.000009936903,0.000003975788,0.000002577925,0.00013678201,0.9639416,0.035869163],"study_design_scores_gemma":[0.00008449275,0.000018760464,0.000012430679,0.0000070132915,0.0000012694658,0.0000012119892,0.00003608765,0.0003227946,0.000040345334,0.0036183943,0.9957368,0.00012040733],"about_ca_topic_score_codex":0.000040310326,"about_ca_topic_score_gemma":0.00007914001,"teacher_disagreement_score":0.12975004,"about_ca_system_score_codex":0.000016665666,"about_ca_system_score_gemma":0.00007629539,"threshold_uncertainty_score":0.9540276},"labels":[],"label_agreement":null},{"id":"W4211172573","doi":"10.1017/9781108571401.030","title":"Minimax Lower Bounds for Stochastic Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Minimax; Mathematics; Mathematical optimization; Computer science; Applied mathematics","score_opus":0.12054412877025228,"score_gpt":0.3339099261002477,"score_spread":0.21336579732999544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211172573","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013198954,0.00014013053,0.24857463,0.00011541327,0.0008368838,0.0012257807,0.0020228075,0.00014230306,0.7469289],"genre_scores_gemma":[0.0008074808,0.000016652712,0.0012447684,0.0001109774,0.0007115166,0.000004458647,0.000088303765,0.00010225363,0.9969136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995187,0.00007407487,0.0005715983,0.0015333114,0.0020037265,0.000630286],"domain_scores_gemma":[0.99476475,0.0017648096,0.0004924417,0.0011986615,0.0011877088,0.00059162814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005824336,0.0005980679,0.0009548811,0.00055381266,0.00048694795,0.00023469943,0.0022583983,0.0005471642,0.00005368686],"category_scores_gemma":[0.0009102465,0.0005988721,0.0006364479,0.00005221433,0.0006643968,0.0002589132,0.0010842697,0.0008380241,0.00028794154],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020914413,0.000046997,6.0671704e-7,0.000111904315,0.00040208825,0.0010971974,0.00014462524,0.00059155957,0.00005777197,0.5197427,0.46261233,0.013100715],"study_design_scores_gemma":[0.0012357066,0.00032384982,0.0000028827978,0.000080402824,0.00011932518,0.000013621022,0.00005414454,0.006092222,0.0000954993,0.00053814944,0.99081385,0.00063032063],"about_ca_topic_score_codex":0.000015739963,"about_ca_topic_score_gemma":0.000003014045,"teacher_disagreement_score":0.5282015,"about_ca_system_score_codex":0.0003217503,"about_ca_system_score_gemma":0.0004606813,"threshold_uncertainty_score":0.99964625},"labels":[],"label_agreement":null},{"id":"W4211180791","doi":"10.1017/9781108571401.024","title":"Contextual Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Psychology; Artificial intelligence","score_opus":0.12866421338510198,"score_gpt":0.32146860365302693,"score_spread":0.19280439026792495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211180791","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009287781,0.00017531692,0.014155098,0.0001145008,0.00042036147,0.0005421338,0.00086922664,0.00016516734,0.9835489],"genre_scores_gemma":[0.0012350808,0.000053734282,0.0001843882,0.00014145156,0.00039162242,7.40854e-7,0.000043154465,0.00006502066,0.9978848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950922,0.00013327129,0.0005039981,0.0013438448,0.0024432214,0.00048343945],"domain_scores_gemma":[0.9959282,0.0010236233,0.00044517644,0.0011947724,0.0008135025,0.0005947003],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005029764,0.0005099729,0.00085722277,0.00047671096,0.0003386845,0.00023271421,0.0024574134,0.00048393884,0.00011266196],"category_scores_gemma":[0.0005416283,0.0005015835,0.0004429649,0.000041831943,0.00068462256,0.00026234865,0.0014893664,0.0011175442,0.0009834744],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022245281,0.0000074832906,0.0000011824375,0.000014908616,0.000111069414,0.0015266521,0.000054338718,0.000015652995,0.000020156622,0.66639227,0.31800395,0.013629874],"study_design_scores_gemma":[0.00077362504,0.000110413515,0.000011078211,0.000048812744,0.000053701024,0.000020714155,0.00009082167,0.00038342492,0.0002027152,0.00029877617,0.9974954,0.00051052554],"about_ca_topic_score_codex":0.00003202383,"about_ca_topic_score_gemma":0.0000032043715,"teacher_disagreement_score":0.6794914,"about_ca_system_score_codex":0.00027293456,"about_ca_system_score_gemma":0.00031674007,"threshold_uncertainty_score":0.99979436},"labels":[],"label_agreement":null},{"id":"W4211193691","doi":"10.1017/9781108571401.029","title":"Stochastic Linear Bandits with Sparsity","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Mathematical optimization; Mathematics; Mathematical analysis","score_opus":0.10929667756822216,"score_gpt":0.30482737592319514,"score_spread":0.195530698354973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211193691","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003519929,0.00007737174,0.14420152,0.00008253243,0.00021397539,0.0006921444,0.00069111,0.00017050141,0.85383564],"genre_scores_gemma":[0.0025363592,0.00001623711,0.000763125,0.00007491711,0.00034586017,8.716358e-7,0.000045804078,0.00007648473,0.99614036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947243,0.00011229564,0.00040977795,0.0014914892,0.0027220591,0.0005400761],"domain_scores_gemma":[0.99579686,0.0008155171,0.0004844827,0.0013090784,0.0009322326,0.0006618078],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043605297,0.0005917337,0.0009112709,0.00050664484,0.00042978322,0.00016329506,0.0021844502,0.00041514254,0.000056972043],"category_scores_gemma":[0.00030916464,0.0005239719,0.00028969173,0.00006952864,0.0007879618,0.00027226613,0.0012921456,0.0012702747,0.00048463038],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031883765,0.00006820739,0.000011699907,0.000122024496,0.00081061985,0.008760267,0.0002979598,0.004385681,0.0000375433,0.75785613,0.20968506,0.014776465],"study_design_scores_gemma":[0.0011795375,0.00029679225,0.000026785785,0.00012369464,0.00014385821,0.000048735918,0.00007560834,0.0031495634,0.000109946435,0.00016510274,0.9939186,0.00076175365],"about_ca_topic_score_codex":0.000042321182,"about_ca_topic_score_gemma":0.000007645833,"teacher_disagreement_score":0.78423357,"about_ca_system_score_codex":0.0002895378,"about_ca_system_score_gemma":0.0004193392,"threshold_uncertainty_score":0.99972117},"labels":[],"label_agreement":null},{"id":"W4211215680","doi":"10.1017/9781108571401.036","title":"The Relation between Adversarial and Stochastic Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Relation (database); Adversarial system; Content (measure theory); Computer science; Mathematical optimization; Theoretical computer science; Artificial intelligence; Mathematics; Data mining","score_opus":0.09798280793259397,"score_gpt":0.3136995318673979,"score_spread":0.21571672393480396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211215680","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000650313,0.00024758265,0.09831295,0.00025096894,0.00050376623,0.0008819871,0.00060319755,0.000108123095,0.8990264],"genre_scores_gemma":[0.005614539,0.000054430915,0.00015798284,0.000019339237,0.00072324474,7.025158e-7,0.00003780607,0.000040237337,0.9933517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99667406,0.00014591853,0.0004018819,0.00084624335,0.0016008966,0.00033102627],"domain_scores_gemma":[0.9953466,0.0027745934,0.0003974335,0.0007078871,0.00043778663,0.00033568294],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070293364,0.00033300996,0.00048421614,0.00022867334,0.0008266654,0.00020308772,0.0011552448,0.00037070332,0.0000067919177],"category_scores_gemma":[0.0008271929,0.0002673348,0.00017826057,0.00003708561,0.00071673334,0.00021930013,0.0010681027,0.0009650439,0.00010115294],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010179213,0.000007920764,0.000018313163,0.000033197717,0.00044889317,0.00042478502,0.0002965831,0.00061468146,0.00001750692,0.8838364,0.056716442,0.05656738],"study_design_scores_gemma":[0.00085768965,0.000108357985,0.00023178886,0.00004637922,0.00012369387,0.00000654025,0.00007343036,0.0033846234,0.000020500824,0.00076784374,0.99402344,0.00035571615],"about_ca_topic_score_codex":0.000023560451,"about_ca_topic_score_gemma":0.0000027149679,"teacher_disagreement_score":0.937307,"about_ca_system_score_codex":0.00016392116,"about_ca_system_score_gemma":0.00018973766,"threshold_uncertainty_score":0.9999779},"labels":[],"label_agreement":null},{"id":"W4211225820","doi":"10.1017/9781108571401.022","title":"High-Probability Lower Bounds","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Information retrieval; Mathematics; Mathematical analysis","score_opus":0.10183471744309376,"score_gpt":0.3042910215945722,"score_spread":0.20245630415147847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211225820","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000097192176,0.00009508083,0.012432336,0.0001818582,0.00086092495,0.0007124433,0.0008764658,0.00021904448,0.98452467],"genre_scores_gemma":[0.0019304001,0.000034156645,0.001029757,0.00011906346,0.00039194446,0.0000012393357,0.00004194159,0.00007029549,0.9963812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939628,0.00018094425,0.0006265578,0.001836129,0.0028119208,0.00058163435],"domain_scores_gemma":[0.9948548,0.0009145549,0.0004915274,0.0020497304,0.0010553763,0.0006339784],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083205686,0.00060574187,0.0010029054,0.0004223889,0.00043358057,0.0003310964,0.0029525596,0.0006000861,0.00016188057],"category_scores_gemma":[0.00067546417,0.0005954672,0.0005537357,0.00006421715,0.0011061577,0.00033571097,0.0021291915,0.0013463757,0.0006943199],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037336446,0.000021730924,0.0000023504501,0.000031086573,0.00011790251,0.0011909241,0.000032917455,0.000059570946,0.000020339829,0.8441265,0.1455013,0.0085219685],"study_design_scores_gemma":[0.000640169,0.00015604935,0.000026914931,0.00004183646,0.00006357399,0.0000103110115,0.000026293621,0.00022425638,0.0001614166,0.0036382473,0.99441165,0.00059929164],"about_ca_topic_score_codex":0.000102361686,"about_ca_topic_score_gemma":0.000006660843,"teacher_disagreement_score":0.84891033,"about_ca_system_score_codex":0.0005680239,"about_ca_system_score_gemma":0.00043049455,"threshold_uncertainty_score":0.99964964},"labels":[],"label_agreement":null},{"id":"W4211230244","doi":"10.1017/9781108571401.043","title":"Bayesian Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bayesian probability; Computer science; Content (measure theory); Artificial intelligence; Mathematics","score_opus":0.0991330921139965,"score_gpt":0.31334188231081306,"score_spread":0.21420879019681655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211230244","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025008846,0.00013045856,0.04851586,0.00013630788,0.00038681686,0.0005024551,0.0006034406,0.00017062048,0.9495515],"genre_scores_gemma":[0.0008722486,0.0000579632,0.00041872702,0.000121526995,0.00040403145,7.330843e-7,0.00004009877,0.00007429425,0.9980104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99495137,0.00013132113,0.0004958396,0.0014213617,0.0024909424,0.0005091812],"domain_scores_gemma":[0.9961232,0.00076008646,0.00043678217,0.0013674231,0.0006546796,0.0006578327],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000493814,0.000525783,0.00081991445,0.00056416576,0.0003649509,0.00024889398,0.002586954,0.0005019302,0.00012393983],"category_scores_gemma":[0.00039985913,0.0005234088,0.00045460253,0.00005233912,0.0005477044,0.00026893252,0.0014606138,0.0011203178,0.0007063168],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020465784,0.000009776994,0.0000023033951,0.000026821537,0.00013405165,0.002308797,0.000058649126,0.0000441694,0.0000203688,0.6278945,0.35175154,0.017544359],"study_design_scores_gemma":[0.000555702,0.00008653702,0.000010347384,0.00005285236,0.000055790253,0.000020247102,0.000049989114,0.001024697,0.00019710431,0.00053533184,0.9968783,0.00053307734],"about_ca_topic_score_codex":0.00002888678,"about_ca_topic_score_gemma":0.0000029519913,"teacher_disagreement_score":0.64512676,"about_ca_system_score_codex":0.00029169623,"about_ca_system_score_gemma":0.00031139312,"threshold_uncertainty_score":0.99972177},"labels":[],"label_agreement":null},{"id":"W4211235784","doi":"10.1017/9781108571401.007","title":"Concentration of Measure","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Measure (data warehouse); Content (measure theory); Computer science; Database; Mathematics","score_opus":0.1222825914765115,"score_gpt":0.3126055781601176,"score_spread":0.1903229866836061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211235784","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015404374,0.00015359487,0.02031203,0.00005324543,0.00019192418,0.0004209982,0.00044257368,0.000052716576,0.9783575],"genre_scores_gemma":[0.006178109,0.00004115743,0.0002578313,0.000029579624,0.00012766157,2.9386715e-7,0.000024700646,0.00002864274,0.993312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99642545,0.000106920976,0.00043216086,0.0007077883,0.0020911964,0.00023647858],"domain_scores_gemma":[0.99691105,0.00046494967,0.00052792544,0.0007591013,0.0010865453,0.00025045214],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043269148,0.000273724,0.000593983,0.0001942002,0.00012660913,0.00006317763,0.0013097193,0.0003119201,0.00003359004],"category_scores_gemma":[0.00039498197,0.0002724904,0.00027866926,0.00003502121,0.000491321,0.00018057792,0.00050111965,0.0005365396,0.00007813735],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002794097,0.000009545608,0.0000041348458,0.000036383328,0.00011945492,0.0003045753,0.000090840265,0.000050991926,0.0003258524,0.91463065,0.06807386,0.016074274],"study_design_scores_gemma":[0.000569388,0.000088909124,0.000015012361,0.000071208124,0.000056608067,0.000005438495,0.0000690408,0.00061014935,0.0022202209,0.0002523229,0.9957564,0.00028530828],"about_ca_topic_score_codex":0.00002178102,"about_ca_topic_score_gemma":0.0000012648732,"teacher_disagreement_score":0.9276825,"about_ca_system_score_codex":0.00015565625,"about_ca_system_score_gemma":0.00030042004,"threshold_uncertainty_score":0.9999727},"labels":[],"label_agreement":null},{"id":"W4211236808","doi":"10.1017/9781108571401.004","title":"Foundations of Probability","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Action (physics); Computer science; Mathematics; Physics","score_opus":0.17185258790490945,"score_gpt":0.3399381421757821,"score_spread":0.16808555427087266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211236808","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025371173,0.00004188494,0.02675077,0.00008239317,0.00016421963,0.00062670757,0.00068127725,0.000067572524,0.9715598],"genre_scores_gemma":[0.0013919577,0.00001871905,0.0014564389,0.000020145764,0.00009370776,7.945254e-7,0.000030586405,0.00002865688,0.996959],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964944,0.00011738976,0.00052643474,0.0008908237,0.0017176338,0.00025329585],"domain_scores_gemma":[0.99594796,0.00086700526,0.00052872597,0.0012179962,0.0011695621,0.00026872876],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005601719,0.0002906152,0.0006453394,0.00034191768,0.00019265925,0.00007542764,0.0017111336,0.0002776401,0.000062456274],"category_scores_gemma":[0.0007758874,0.000289055,0.00036323545,0.000050401504,0.0008506754,0.00020124413,0.0010819101,0.00059013214,0.00011950617],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000106357795,0.000013908491,0.00000421257,0.00004016224,0.00007286904,0.00008523753,0.00004681195,0.000041862455,0.000030560936,0.9661669,0.026160875,0.0072302017],"study_design_scores_gemma":[0.00035334102,0.00008171152,0.000033979853,0.00003988369,0.00005129827,0.0000041586363,0.00004090193,0.0003811932,0.0003263521,0.0033136252,0.99510276,0.0002707882],"about_ca_topic_score_codex":0.00004116825,"about_ca_topic_score_gemma":0.000003916248,"teacher_disagreement_score":0.96894187,"about_ca_system_score_codex":0.00021934845,"about_ca_system_score_gemma":0.0003983433,"threshold_uncertainty_score":0.99995613},"labels":[],"label_agreement":null},{"id":"W4211243395","doi":"10.1017/9781108571401.040","title":"Ranking","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Ranking (information retrieval); Computer science; Artificial intelligence","score_opus":0.13068629293194783,"score_gpt":0.32197352614614366,"score_spread":0.19128723321419583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211243395","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000053824297,0.00014997575,0.024169482,0.00009784833,0.00033840042,0.00042574076,0.00031025062,0.00015891633,0.974344],"genre_scores_gemma":[0.00054453436,0.00005126361,0.00045683296,0.00010837884,0.0003276938,4.842497e-7,0.000022128932,0.00006091639,0.99842775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954496,0.0001115262,0.0004335409,0.001210537,0.0023690835,0.00042572088],"domain_scores_gemma":[0.99657935,0.0008113823,0.0004022579,0.0011616222,0.00062468613,0.0004206903],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055456546,0.0004303686,0.00071807415,0.000491106,0.0003374367,0.00022864423,0.0024008602,0.00039621373,0.00007023878],"category_scores_gemma":[0.00040293307,0.0004321313,0.00041899522,0.000042253014,0.00046882033,0.00023310177,0.0015441325,0.0010432826,0.0005961311],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017421665,0.000005429018,0.0000013433489,0.00002016606,0.000104533225,0.0016468371,0.00005679657,0.00003555753,0.000030086227,0.8260262,0.14873959,0.023159226],"study_design_scores_gemma":[0.0005396702,0.000052201838,0.0000064005353,0.000054354965,0.000048330727,0.000015663281,0.000051343774,0.0005856827,0.00019103085,0.0005171552,0.9975007,0.0004374582],"about_ca_topic_score_codex":0.000025043033,"about_ca_topic_score_gemma":0.0000014067012,"teacher_disagreement_score":0.84876114,"about_ca_system_score_codex":0.000258231,"about_ca_system_score_gemma":0.0002378969,"threshold_uncertainty_score":0.999813},"labels":[],"label_agreement":null},{"id":"W4211244366","doi":"10.1017/9781108571401.035","title":"Follow-the-regularised-Leader and Mirror Descent","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Descent (aeronautics); Mathematics; Computer science; Geology; Physics; Meteorology","score_opus":0.13432570621830284,"score_gpt":0.30901764966248446,"score_spread":0.17469194344418162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211244366","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008730797,0.0004943254,0.0080855265,0.0010060967,0.00034856165,0.0009840984,0.00035013026,0.000118972646,0.988525],"genre_scores_gemma":[0.0015495835,0.000072949035,0.0005166364,0.0001885597,0.000117950105,0.0000013686222,0.000014640365,0.000056828536,0.99748147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958362,0.00015742486,0.0004081775,0.0011886792,0.0019495988,0.00045992143],"domain_scores_gemma":[0.9967365,0.00077427016,0.00034270345,0.0011824189,0.00049583724,0.00046821646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058265356,0.00046921955,0.0006506867,0.0003032181,0.00052373175,0.0002929425,0.0019004185,0.0003848916,0.000031973734],"category_scores_gemma":[0.0003004405,0.00037617225,0.000332003,0.00004485634,0.001079019,0.00020052899,0.0016167263,0.0010031388,0.00013559792],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046961164,0.000018656621,0.000011429107,0.000060160757,0.00030364905,0.0015174156,0.00030777292,0.000007523193,0.00011532349,0.794004,0.1769597,0.026224736],"study_design_scores_gemma":[0.00075985043,0.000071455666,0.000071145514,0.000047436835,0.0000983013,0.000026111236,0.0002097787,0.00043296214,0.00024393044,0.0003475133,0.9972701,0.00042138644],"about_ca_topic_score_codex":0.000055821234,"about_ca_topic_score_gemma":0.000008714567,"teacher_disagreement_score":0.8203104,"about_ca_system_score_codex":0.00019619895,"about_ca_system_score_gemma":0.000204968,"threshold_uncertainty_score":0.99986905},"labels":[],"label_agreement":null},{"id":"W4211244740","doi":"10.1017/9781108571401.021","title":"Instance-Dependent Lower Bounds","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Theoretical computer science; Information retrieval; Computer network; Mathematics; Mathematical analysis","score_opus":0.0978907667440073,"score_gpt":0.31089200036536113,"score_spread":0.2130012336213538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211244740","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021175398,0.0002162301,0.016050346,0.00011345325,0.0008143386,0.00055831193,0.0006833155,0.00019067278,0.98135215],"genre_scores_gemma":[0.0016774477,0.00011267514,0.00028550663,0.00015318838,0.0003692841,0.0000011281236,0.000025598185,0.000084216765,0.99729097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938561,0.00012044405,0.0005716904,0.0015879472,0.0032875796,0.00057629263],"domain_scores_gemma":[0.9958483,0.00057834794,0.00050109846,0.0016082978,0.00085971656,0.0006042532],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005690439,0.0005829194,0.0008705165,0.0005429032,0.00041962374,0.00036265058,0.0029126897,0.0005330862,0.00012331661],"category_scores_gemma":[0.00033724608,0.00058476493,0.00047465356,0.000056477587,0.00070957484,0.0003637875,0.0018728672,0.0013463801,0.0008206038],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005259554,0.000023982164,0.000002656409,0.000030547875,0.00018639781,0.0042155827,0.00008367401,0.000056096796,0.00004142102,0.7715218,0.20603208,0.017279811],"study_design_scores_gemma":[0.0007406721,0.00013196684,0.00000795397,0.00006151807,0.000054586402,0.000020169075,0.00007648325,0.0002806789,0.00018172975,0.00053657126,0.99730796,0.0005996853],"about_ca_topic_score_codex":0.00003600374,"about_ca_topic_score_gemma":0.0000076602155,"teacher_disagreement_score":0.7912759,"about_ca_system_score_codex":0.0005611734,"about_ca_system_score_gemma":0.00044390516,"threshold_uncertainty_score":0.9999574},"labels":[],"label_agreement":null},{"id":"W4211259986","doi":"10.1017/9781108571401.038","title":"Combinatorial Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Computer network; Information retrieval; Mathematics","score_opus":0.10123300665543071,"score_gpt":0.31341962928951744,"score_spread":0.21218662263408672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211259986","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008543922,0.000103714585,0.005567462,0.00009167276,0.0014659729,0.00054514414,0.0006035982,0.00016827363,0.9914456],"genre_scores_gemma":[0.0012735209,0.00004405993,0.000115760886,0.00006987546,0.00072976126,7.369075e-7,0.000042853233,0.00006753131,0.9976559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948343,0.00014293774,0.0004914903,0.0013134719,0.002744643,0.00047314167],"domain_scores_gemma":[0.99601877,0.00090621813,0.00045276518,0.0012288796,0.0008091738,0.0005842226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005377506,0.00050301186,0.0008467047,0.00046885278,0.00036566274,0.00024886,0.0025650593,0.00054615707,0.00007826779],"category_scores_gemma":[0.00051912136,0.00050765375,0.00043679547,0.000048642487,0.00056452,0.00025273932,0.0016065683,0.0011789867,0.00072152785],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019687256,0.0000079853135,8.672066e-7,0.000012651087,0.00007583669,0.00097509916,0.000026969736,0.0000094195075,0.0000104813535,0.817077,0.17771614,0.0038907137],"study_design_scores_gemma":[0.0010791806,0.00012124316,0.000007647609,0.0000422216,0.000057710713,0.000012754558,0.000035081288,0.00026113875,0.00022273419,0.0020811476,0.99556893,0.00051019277],"about_ca_topic_score_codex":0.000028492415,"about_ca_topic_score_gemma":0.000001056633,"teacher_disagreement_score":0.8178528,"about_ca_system_score_codex":0.00031805417,"about_ca_system_score_gemma":0.00034317735,"threshold_uncertainty_score":0.9997375},"labels":[],"label_agreement":null},{"id":"W4214636767","doi":"10.1109/lcsys.2022.3155067","title":"Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions","year":2022,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Convexity; Smoothness; Mathematical optimization; Lipschitz continuity; Convex optimization; Convex function; Regularization (linguistics); Upper and lower bounds; Mathematics; Function (biology); Bounded function; Computer science; Regular polygon; Artificial intelligence; Economics; Mathematical analysis","score_opus":0.09309093525136584,"score_gpt":0.3857145837651675,"score_spread":0.2926236485138016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214636767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11017316,0.00048842275,0.8683746,0.008859554,0.0040052114,0.0038051,0.0041770595,0.00007734875,0.00003952696],"genre_scores_gemma":[0.994419,0.0000028435486,0.0006347794,0.0007015659,0.00009398016,0.0009382239,0.0000525451,0.000041751122,0.0031153357],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945417,0.00083201367,0.0011792541,0.000702013,0.002174294,0.0005707096],"domain_scores_gemma":[0.99433523,0.0033973318,0.00074504357,0.00077325734,0.00058257,0.00016654533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030152004,0.00023458968,0.0007468408,0.00054078613,0.00051473273,0.000096906086,0.0009584019,0.00006460757,0.00013044232],"category_scores_gemma":[0.001262786,0.00019605485,0.00029427226,0.0008464386,0.0002502029,0.0002550109,0.000091482165,0.00042637473,0.000051731946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034533446,0.0009889097,0.006087966,0.00018174225,0.0007595988,0.00014766994,0.0014289083,0.5183588,0.30168062,0.0003631278,0.1511699,0.015379388],"study_design_scores_gemma":[0.010575252,0.0007841444,0.009998361,0.00007287296,0.00008824385,0.000060322353,0.0040403227,0.7266194,0.00013630664,0.00033178183,0.24668032,0.00061264186],"about_ca_topic_score_codex":0.00015996712,"about_ca_topic_score_gemma":0.00007774853,"teacher_disagreement_score":0.8842458,"about_ca_system_score_codex":0.0005517673,"about_ca_system_score_gemma":0.00017424603,"threshold_uncertainty_score":0.7994885},"labels":[],"label_agreement":null},{"id":"W4214732409","doi":"10.1093/beheco/arac027","title":"On the strategic learning of signal associations","year":2022,"lang":"en","type":"article","venue":"Behavioral Ecology","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Softmax function; Stochastic game; Profitability index; Machine learning; Artificial intelligence; Prior probability; Bayesian probability; Mathematical economics; Mathematics; Deep learning","score_opus":0.3098390872045215,"score_gpt":0.48165174083419166,"score_spread":0.17181265362967013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214732409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99698174,0.000016813345,0.00035592075,0.0007335816,0.00019215907,0.00017607129,0.00004862949,0.000016607888,0.0014784563],"genre_scores_gemma":[0.9974537,0.000001062695,0.000060020764,0.00006322477,0.000019575287,0.000078698096,0.0000085294205,0.000006738624,0.002308486],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971674,0.0009072133,0.00033025115,0.00023466574,0.0011118816,0.0002485856],"domain_scores_gemma":[0.99664694,0.002670184,0.000235325,0.00023233416,0.00017714339,0.000038094095],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022835257,0.00006520578,0.00017342731,0.0001796655,0.0006283126,0.00003130797,0.0006706881,0.000039913553,0.0145927435],"category_scores_gemma":[0.00047006016,0.00004449978,0.00008102052,0.00067344046,0.00013250006,0.00006819906,0.00028822696,0.000575325,0.00015627882],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003364282,0.00393758,0.26332897,0.000003304708,0.00006434483,0.00026286807,0.0030317483,0.43360785,0.0072636255,0.19384122,0.01767036,0.076651685],"study_design_scores_gemma":[0.00199198,0.009986319,0.376111,0.0000029551172,0.00005542403,0.000044583812,0.037687432,0.026677983,0.001602804,0.5244335,0.020797718,0.00060830725],"about_ca_topic_score_codex":0.000027200174,"about_ca_topic_score_gemma":0.000060609775,"teacher_disagreement_score":0.40692988,"about_ca_system_score_codex":0.00014005294,"about_ca_system_score_gemma":0.00015383949,"threshold_uncertainty_score":0.98630804},"labels":[],"label_agreement":null},{"id":"W4220814865","doi":"10.1080/14697688.2022.2049356","title":"The reinforcement learning Kelly strategy","year":2022,"lang":"en","type":"article","venue":"Quantitative Finance","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Portfolio; Reinforcement; Computer science; Artificial intelligence; Face (sociological concept); Mathematical optimization; Operations research; Economics; Mathematics; Psychology; Sociology; Finance; Social psychology","score_opus":0.1802992795779892,"score_gpt":0.4634093563427167,"score_spread":0.2831100767647275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220814865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21969637,0.008930347,0.7084072,0.005706525,0.0022890724,0.0018868898,0.000065814165,0.00021956803,0.05279821],"genre_scores_gemma":[0.9292367,0.00016171203,0.001135412,0.00006218964,0.000029745557,0.0001521998,0.0000043106456,0.000013596967,0.06920411],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958069,0.00062665046,0.00046952447,0.00043806303,0.0022138245,0.00044506957],"domain_scores_gemma":[0.99521744,0.0036340675,0.00029139643,0.00046518352,0.00035010354,0.000041825937],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0039851237,0.00011911522,0.00017242946,0.000117646196,0.0024979413,0.0002150754,0.0011974126,0.000016783126,0.0006325433],"category_scores_gemma":[0.003507318,0.00007863519,0.00008198753,0.001299853,0.00027122186,0.000286409,0.000509561,0.0006050184,0.000598735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010317539,0.000018135443,0.00027220603,8.124951e-7,0.000007377576,0.000022867276,0.0006839294,0.8557788,0.000087090484,0.080472834,0.006635244,0.05591754],"study_design_scores_gemma":[0.0002925821,0.00092987175,0.0038415787,0.0000032149767,0.0000013621527,0.0000058391274,0.006612137,0.1896764,0.00022241267,0.045410573,0.75284445,0.00015954964],"about_ca_topic_score_codex":0.000023555689,"about_ca_topic_score_gemma":0.000015723135,"teacher_disagreement_score":0.7462092,"about_ca_system_score_codex":0.000119228695,"about_ca_system_score_gemma":0.00016916907,"threshold_uncertainty_score":0.9988007},"labels":[],"label_agreement":null},{"id":"W4224280172","doi":"10.3390/jrfm15040172","title":"Best-Arm Identification Using Extreme Value Theory Estimates of the CVaR","year":2022,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CVAR; Estimator; Identification (biology); Expected shortfall; Extreme value theory; Selection (genetic algorithm); Value at risk; Econometrics; Computer science; Risk management; Sample (material); Value (mathematics); Mathematical optimization; Statistics; Mathematics; Economics; Finance; Artificial intelligence","score_opus":0.07843315199574445,"score_gpt":0.3692801890360355,"score_spread":0.290847037040291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224280172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3687705,0.0014467079,0.628376,0.00011985287,0.00086979277,0.00022469544,0.00002324087,0.0000028923357,0.0001663172],"genre_scores_gemma":[0.99319816,0.00035488998,0.0059558623,0.000024922396,0.00009251308,0.0000037963723,2.0879607e-7,0.0000070745255,0.00036259423],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99715996,0.0003246562,0.0006644059,0.00016057861,0.0015469672,0.0001434516],"domain_scores_gemma":[0.9981418,0.00046978905,0.00084117235,0.0002828618,0.00022396342,0.00004038654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054257666,0.00007664872,0.0001993753,0.00032131252,0.00049235445,0.000072063354,0.0006926608,0.000017718643,0.00009476679],"category_scores_gemma":[0.0014178291,0.000048509733,0.00012076324,0.0007125562,0.00012547853,0.00021476815,0.00054860243,0.0002546008,0.0000027323954],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025352897,0.0002830115,0.0069349166,0.000018704113,0.000030763524,0.00004501545,0.0011906306,0.06673735,0.00038337923,0.0152999265,0.0005171695,0.9083056],"study_design_scores_gemma":[0.0008665246,0.0002701091,0.12218566,0.000050434668,0.00014203176,0.00006190894,0.004292365,0.016051477,0.0007367208,0.82995754,0.025234215,0.00015102238],"about_ca_topic_score_codex":0.000013601318,"about_ca_topic_score_gemma":0.00000198602,"teacher_disagreement_score":0.9081546,"about_ca_system_score_codex":0.00007251105,"about_ca_system_score_gemma":0.000052495103,"threshold_uncertainty_score":0.37868422},"labels":[],"label_agreement":null},{"id":"W4225574046","doi":"10.1287/mnsc.2021.4194","title":"Analytical Solution to a Discrete-Time Model for Dynamic Learning and Decision Making","year":2022,"lang":"en","type":"article","venue":"Management Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Partially observable Markov decision process; Discrete time and continuous time; Computer science; Mathematical optimization; Markov decision process; Dynamic decision-making; Set (abstract data type); Time horizon; Bellman equation; Constant (computer programming); Markov process; Process (computing); Markov chain; Mathematics; Markov model; Artificial intelligence; Machine learning","score_opus":0.06880974970414613,"score_gpt":0.4639385086242527,"score_spread":0.39512875892010657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225574046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0385487,0.000017670316,0.9591754,0.0006486643,0.00009352442,0.00059486576,0.000008786834,0.000038017024,0.0008743372],"genre_scores_gemma":[0.87612575,0.0000030300032,0.11731672,0.00011683883,0.000009288166,0.00011780092,0.0000012391043,0.00000938396,0.0062999707],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947984,0.000058907986,0.00033462307,0.0010041407,0.003216972,0.0005869474],"domain_scores_gemma":[0.9986383,0.000592379,0.00008695554,0.00039154483,0.00013247783,0.00015836078],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0071474416,0.00011320074,0.0001685757,0.0010671701,0.0019428884,0.0004949909,0.0012502882,0.000013291622,0.0001488761],"category_scores_gemma":[0.001658395,0.000096215445,0.00005206043,0.0028077695,0.0002763932,0.0005386637,0.0032256173,0.0001612413,0.00006973559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085814565,0.000021118669,0.00021669015,0.0000030987383,0.0000032127496,0.0000059917274,0.00020330923,0.60843605,0.00016624414,0.0013603112,0.0005235977,0.38897455],"study_design_scores_gemma":[0.00020213524,0.00011874054,0.0014276095,0.000008135923,0.000005128895,0.000002877463,0.0005297196,0.9495514,0.000002897895,0.04544033,0.0025862616,0.00012477973],"about_ca_topic_score_codex":0.0000011856256,"about_ca_topic_score_gemma":0.0000032981188,"teacher_disagreement_score":0.8418587,"about_ca_system_score_codex":0.00033391503,"about_ca_system_score_gemma":0.000042903128,"threshold_uncertainty_score":0.99935645},"labels":[],"label_agreement":null},{"id":"W4226099433","doi":"10.1007/s00498-022-00323-4","title":"Logarithmic regret in online linear quadratic control using Riccati updates","year":2022,"lang":"en","type":"article","venue":"Mathematics of Control Signals and Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Regret; Logarithm; Sublinear function; Linear-quadratic regulator; Mathematics; Controller (irrigation); Hindsight bias; Riccati equation; Linear-quadratic-Gaussian control; Mathematical optimization; Optimal control; Control (management); Computer science; Control theory (sociology); Discrete mathematics; Statistics; Artificial intelligence; Differential equation","score_opus":0.13527012559156412,"score_gpt":0.4094376742189131,"score_spread":0.27416754862734893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226099433","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43554577,0.0045782155,0.5559345,0.0004960448,0.0003817344,0.0022773265,0.0005721189,0.00003655236,0.0001777537],"genre_scores_gemma":[0.9974689,0.000023898572,0.0020564434,0.000045286986,0.00007704875,0.000077658755,0.000005670937,0.000024443421,0.00022067272],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99467325,0.00080548634,0.0017255051,0.000415985,0.0019787399,0.00040104793],"domain_scores_gemma":[0.9940018,0.004092578,0.00081801246,0.00056325144,0.00040512707,0.000119243145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065347617,0.00021568505,0.0011586116,0.00054359186,0.00021179997,0.00013995064,0.00070585444,0.00006814316,0.00015412764],"category_scores_gemma":[0.0020190708,0.00016131745,0.00011336789,0.00073330244,0.00014440512,0.00020463872,0.00016168566,0.0003091049,0.000009139932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039302147,0.0017127678,0.007013188,0.00059729285,0.0002896136,0.00015885466,0.0038196605,0.95362216,0.022351678,0.0034670027,0.0005305188,0.00604421],"study_design_scores_gemma":[0.0024747183,0.00019735625,0.00014997362,0.00007590037,0.000022960652,0.00003788716,0.004188629,0.97886044,0.000043428874,0.013345845,0.00043146044,0.00017138396],"about_ca_topic_score_codex":0.00014492811,"about_ca_topic_score_gemma":0.00002389286,"teacher_disagreement_score":0.5619231,"about_ca_system_score_codex":0.00008997912,"about_ca_system_score_gemma":0.00012896724,"threshold_uncertainty_score":0.65783346},"labels":[],"label_agreement":null},{"id":"W4226342350","doi":"10.1109/tvt.2022.3163078","title":"Optimal Channel Selection in Hybrid RF/VLC Networks: A Multi-Armed Bandit Approach","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Waterloo; Thunder Bay Regional Research Institute","funders":"","keywords":"Selection (genetic algorithm); Visible light communication; Computer science; Channel (broadcasting); Throughput; Wireless; Energy consumption; Radio frequency; Electronic engineering; Mathematical optimization; Convergence (economics); Multi-armed bandit; Engineering; Telecommunications; Mathematics; Machine learning; Electrical engineering","score_opus":0.054139025851553946,"score_gpt":0.34304758940708596,"score_spread":0.288908563555532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226342350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071114294,0.00017029262,0.9263404,0.0006885988,0.00047360556,0.0007697646,0.00004241093,0.0003653906,0.00003526079],"genre_scores_gemma":[0.9895112,0.000040159422,0.007874417,0.00008193182,0.000044300836,0.001317518,0.000008354697,0.000050988852,0.0010711624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952892,0.0004054597,0.000734882,0.0012105609,0.0014791073,0.0008807565],"domain_scores_gemma":[0.9984466,0.00033450278,0.00018048022,0.0007030837,0.00021297042,0.00012235442],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017536927,0.00031461,0.00051478925,0.003184114,0.0008735736,0.00008227136,0.0012906156,0.00025852388,0.00044533305],"category_scores_gemma":[0.00013725863,0.0003034649,0.00021388968,0.005783956,0.0003435693,0.0002833534,0.000033469096,0.002290564,0.00011225039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012494824,0.00073599396,0.00004510932,0.0000027043825,0.000034577068,0.00009015449,0.000077509896,0.97400177,0.000541715,0.000014027744,0.00020370171,0.024127822],"study_design_scores_gemma":[0.0016742673,0.00046590096,0.00012243967,0.000006124972,0.000013583196,0.00038587995,0.0010401497,0.98471266,0.007458192,0.0007720107,0.0030197615,0.00032901697],"about_ca_topic_score_codex":0.000041203726,"about_ca_topic_score_gemma":0.000069720285,"teacher_disagreement_score":0.918466,"about_ca_system_score_codex":0.0005589354,"about_ca_system_score_gemma":0.0001298183,"threshold_uncertainty_score":0.99994177},"labels":[],"label_agreement":null},{"id":"W4230736957","doi":"10.2139/ssrn.3249069","title":"Optimal Exploration","year":2018,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Computer science; Geology; Geography","score_opus":0.0941705604698524,"score_gpt":0.4321125470547117,"score_spread":0.3379419865848593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230736957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06568665,0.00044818828,0.9298527,0.0018363893,0.0004451386,0.00009294164,0.0000012082277,0.000029882545,0.0016068975],"genre_scores_gemma":[0.982486,0.00053813204,0.0023103112,0.00006754446,0.0017877703,0.0000049542787,0.000001025019,0.000018749735,0.012785515],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949975,0.00020844859,0.0004494217,0.00031424413,0.0017783692,0.0022520344],"domain_scores_gemma":[0.9982308,0.00025012787,0.00019166278,0.00034761935,0.00084519555,0.000134551],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008244945,0.000115392184,0.00016312154,0.00034384883,0.0005037444,0.00032136324,0.0008927343,0.000060412298,0.00049515034],"category_scores_gemma":[0.0019168048,0.00008158297,0.00009682124,0.00080958434,0.00019390445,0.0013441757,0.00010231055,0.001366303,0.0022775617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032142168,0.0001204209,0.0006890663,7.2826816e-7,0.00009563494,0.000019051002,0.001048719,0.0022820963,0.0011687393,0.06442946,0.005611411,0.92421323],"study_design_scores_gemma":[0.0005106068,0.000867433,0.00021385505,0.0000036364809,0.000004239536,0.00039403158,0.0043099076,0.00510991,0.001186399,0.9551373,0.03211423,0.00014841901],"about_ca_topic_score_codex":0.000006874339,"about_ca_topic_score_gemma":0.00025567415,"teacher_disagreement_score":0.9275424,"about_ca_system_score_codex":0.00059452053,"about_ca_system_score_gemma":0.0017946237,"threshold_uncertainty_score":0.9984993},"labels":[],"label_agreement":null},{"id":"W4237856594","doi":"10.2139/ssrn.3948140","title":"Network Revenue Management with Nonparametric Demand Learning: \\sqrt{T}-regret and Polynomial Dimension Dependency","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Nonparametric statistics; Dimension (graph theory); Dependency (UML); Polynomial; Revenue; Revenue management; Economics; Mathematical economics; Microeconomics; Econometrics; Mathematics; Computer science; Combinatorics; Artificial intelligence; Statistics; Finance","score_opus":0.02380355728856963,"score_gpt":0.32879120736682316,"score_spread":0.3049876500782535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237856594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61255926,0.045944795,0.33627608,0.0024016686,0.0006537459,0.00054362725,0.0000052984174,0.00005899094,0.0015565486],"genre_scores_gemma":[0.96307164,0.009374121,0.0035314322,0.00006634839,0.0005078072,0.0000078689545,0.00000342662,0.00003783215,0.023399534],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99387115,0.0005683434,0.00052184804,0.0006446357,0.0019304215,0.0024635885],"domain_scores_gemma":[0.99806017,0.0006106931,0.0003123843,0.00039539122,0.0003912417,0.00023011868],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006086954,0.00022821255,0.0003758683,0.00039460466,0.00072680187,0.00040449647,0.0005023069,0.00009802623,0.000096142605],"category_scores_gemma":[0.00087757275,0.00016324519,0.0000904093,0.0020071398,0.00011827456,0.00042263963,0.00030996153,0.0025526057,0.000078212506],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010995353,0.00024844706,0.044355597,0.0000206473,0.00065661705,0.0017535717,0.00039702762,0.039388385,0.00031049733,0.011086676,0.005381606,0.8953014],"study_design_scores_gemma":[0.0069470853,0.002973641,0.022654492,0.0002222852,0.00021752462,0.01395754,0.008153412,0.006563865,0.00061708916,0.88495404,0.051494576,0.0012444353],"about_ca_topic_score_codex":0.000013047147,"about_ca_topic_score_gemma":0.00046121582,"teacher_disagreement_score":0.894057,"about_ca_system_score_codex":0.00049303606,"about_ca_system_score_gemma":0.0011155956,"threshold_uncertainty_score":0.9997485},"labels":[],"label_agreement":null},{"id":"W4242718810","doi":"10.1017/9781108571401.049","title":"Index","year":2020,"lang":"en","type":"paratext","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Index (typography); Computer science; World Wide Web","score_opus":0.10867711622926478,"score_gpt":0.3512632323008547,"score_spread":0.24258611607158992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242718810","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000043009033,0.0002430584,0.077798605,0.00012590851,0.0015560858,0.00051487173,0.0010840795,0.00008183737,0.9185525],"genre_scores_gemma":[0.0015967574,0.000117044314,0.00021585141,0.00014663633,0.0006221545,0.0000019267559,0.00008754374,0.000052156585,0.99715996],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99421465,0.0005252104,0.00047906057,0.0014624348,0.0026368154,0.0006817981],"domain_scores_gemma":[0.9958512,0.00090485206,0.00044603168,0.001414355,0.0007911766,0.000592341],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053737813,0.00047259295,0.0008667242,0.00063346926,0.00036856005,0.00037958068,0.0038351382,0.00054233044,0.00027527873],"category_scores_gemma":[0.00067524676,0.00045832002,0.000384763,0.00026922274,0.0004982936,0.00028900424,0.0021550462,0.0014154806,0.0091678165],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014709988,0.00001399186,0.000003060168,0.000024655808,0.00006352257,0.0003916183,0.000043703352,0.00021361219,0.000020856067,0.0023573798,0.99087775,0.00584278],"study_design_scores_gemma":[0.00063975604,0.000061914216,0.000034436503,0.00003380131,0.000024033514,0.000010192803,0.00022099358,0.0018915023,0.00049313164,0.000004565022,0.9961178,0.00046790447],"about_ca_topic_score_codex":0.00019972656,"about_ca_topic_score_gemma":0.0000018801317,"teacher_disagreement_score":0.07860739,"about_ca_system_score_codex":0.00031530854,"about_ca_system_score_gemma":0.0005603247,"threshold_uncertainty_score":0.99978685},"labels":[],"label_agreement":null},{"id":"W4281933381","doi":"10.3390/electronics11111782","title":"Cost-Aware Bandits for Efficient Channel Selection in Hybrid Band Networks","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; Thunder Bay Regional Research Institute","funders":"Japan Society for the Promotion of Science","keywords":"Throughput; Computer science; Heuristic; Energy consumption; Transmitter; Wireless; Channel (broadcasting); Selection (genetic algorithm); Efficient energy use; Convergence (economics); Multi-armed bandit; Energy (signal processing); Mathematical optimization; Computer network; Telecommunications; Computer engineering; Electronic engineering; Machine learning; Artificial intelligence; Engineering; Electrical engineering; Mathematics","score_opus":0.07562253431195153,"score_gpt":0.39552097523063184,"score_spread":0.3198984409186803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281933381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052528154,0.0050460408,0.9389626,0.0006801231,0.0006752202,0.0018317569,0.000072958814,0.00008188749,0.000121306584],"genre_scores_gemma":[0.9966307,0.00013704658,0.00014281065,0.00013183916,0.00021383491,0.00079754984,0.000044015094,0.00003561277,0.0018665558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607897,0.0002766534,0.00048074924,0.0006891722,0.0014407976,0.0010336671],"domain_scores_gemma":[0.9981186,0.0010783246,0.00015707237,0.00028156646,0.00025363432,0.00011079816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034414595,0.0001709491,0.00028754305,0.000478612,0.00066733867,0.000120586425,0.00071130396,0.00004885465,0.00033732745],"category_scores_gemma":[0.0006966641,0.00015978699,0.00011201166,0.0018162435,0.000045495577,0.00013005293,0.00018607211,0.0007435482,0.00002217028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020321907,0.000112746915,0.00013088128,0.0000019604176,0.000008320561,0.0000074551717,0.00010069628,0.95872784,0.00005003164,0.00006844618,0.007908438,0.032679975],"study_design_scores_gemma":[0.0010351003,0.00048106982,0.00035161985,0.0000027505162,0.0000035160435,0.000034031375,0.00016633632,0.8476321,0.0015993615,0.0041691763,0.14433579,0.00018911199],"about_ca_topic_score_codex":0.0000051671927,"about_ca_topic_score_gemma":0.00016090195,"teacher_disagreement_score":0.9441026,"about_ca_system_score_codex":0.00096779724,"about_ca_system_score_gemma":0.00035862665,"threshold_uncertainty_score":0.65159243},"labels":[],"label_agreement":null},{"id":"W4283217744","doi":"10.1109/infocom48880.2022.9796683","title":"Learning from Delayed Semi-Bandit Feedback under Strong Fairness Guarantees","year":2022,"lang":"en","type":"article","venue":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Regret; Computer science; Credibility; Online learning; Contrast (vision); Term (time); Mathematical optimization; State (computer science); Upper and lower bounds; Artificial intelligence; Mathematics; Algorithm; Machine learning","score_opus":0.21070162128076683,"score_gpt":0.40880948655989924,"score_spread":0.1981078652791324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283217744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07120218,0.00027836364,0.91484845,0.0057922346,0.0023316639,0.0010262551,0.00047653352,0.000404438,0.0036398873],"genre_scores_gemma":[0.9899699,0.00017504385,0.0056980215,0.0005889488,0.00027562797,0.00046642567,0.00027955268,0.00006050786,0.00248598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911503,0.0025034756,0.0013515988,0.0010998525,0.0030968462,0.00079791265],"domain_scores_gemma":[0.9874471,0.0058804876,0.00067902176,0.0048853154,0.00081976777,0.00028832196],"candidate_categories":["metaepi_narrow","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020791572,0.0004763193,0.00073835644,0.00076958316,0.002959029,0.0009736647,0.009178171,0.00014048886,0.003422446],"category_scores_gemma":[0.00022571381,0.00047372535,0.00029349377,0.0018942135,0.0007614341,0.0007643145,0.0028107152,0.0028676721,0.0009761369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024011957,0.000785189,0.0011844422,0.0000055820256,0.00028572907,0.000034995333,0.004435859,0.8385795,0.0012891607,0.0084995935,0.029030548,0.11562933],"study_design_scores_gemma":[0.001601072,0.00071414624,0.0024234434,0.000051690164,0.00002984184,0.00002428228,0.0054730396,0.90953535,0.00039737122,0.031039245,0.047880422,0.00083007605],"about_ca_topic_score_codex":0.00043305516,"about_ca_topic_score_gemma":0.0003686633,"teacher_disagreement_score":0.9187677,"about_ca_system_score_codex":0.00045929282,"about_ca_system_score_gemma":0.0005067711,"threshold_uncertainty_score":0.9998017},"labels":[],"label_agreement":null},{"id":"W4283778953","doi":"10.1111/poms.13786","title":"Bayesian dithering for learning: Asymptotically optimal policies in dynamic pricing","year":2022,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dither; Regret; Upper and lower bounds; Asymptotically optimal algorithm; Mathematical optimization; Computer science; Logarithm; Dynamic pricing; Parametric statistics; Bayesian probability; Order (exchange); Set (abstract data type); Mathematics; Economics; Artificial intelligence; Machine learning; Microeconomics; Statistics; Finance","score_opus":0.0443791077691186,"score_gpt":0.3906137799644066,"score_spread":0.34623467219528803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283778953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09400952,0.000101034704,0.893042,0.010338321,0.00039736,0.0012891953,0.0000043615564,0.00005848024,0.00075967197],"genre_scores_gemma":[0.9592415,0.00004498725,0.022464612,0.000060093822,0.000054908658,0.00046763677,0.0000075982775,0.000011993712,0.017646648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983382,0.0001321843,0.00030242832,0.00044831025,0.0005664874,0.00021234788],"domain_scores_gemma":[0.9995375,0.0000840645,0.000035496556,0.00020975557,0.00009388424,0.000039265407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017724475,0.0000790042,0.000110954636,0.0004955419,0.00087875983,0.00022921468,0.00019948701,0.000011316799,0.00013466108],"category_scores_gemma":[0.00073488185,0.000071621645,0.000025843092,0.0007399345,0.000048603106,0.00027525664,0.00031562042,0.00016832152,0.000006639289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019870678,0.000056997887,0.00046200442,0.000007092648,0.000008270787,0.0000015803836,0.0008623582,0.94642264,0.00011699786,0.0018929905,0.0001307034,0.050018493],"study_design_scores_gemma":[0.00037294725,0.00017397272,0.008011329,0.000007456997,0.000006958359,0.000010300177,0.012066293,0.944103,0.00008640784,0.0020358239,0.03296105,0.00016447477],"about_ca_topic_score_codex":0.000011705707,"about_ca_topic_score_gemma":0.00008339829,"teacher_disagreement_score":0.87057745,"about_ca_system_score_codex":0.00014059238,"about_ca_system_score_gemma":0.000018915036,"threshold_uncertainty_score":0.6758799},"labels":[],"label_agreement":null},{"id":"W4283836917","doi":"10.1287/msom.2022.1128","title":"Online Personalized Assortment Optimization with High-Dimensional Customer Contextual Data","year":2022,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Regret; Scalability; Set (abstract data type); Relevance (law); Optimization problem; Curse of dimensionality; Benchmark (surveying); Mathematical optimization; Data mining; Machine learning; Algorithm; Database","score_opus":0.09720745596710767,"score_gpt":0.3677456167158194,"score_spread":0.27053816074871173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283836917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30309874,0.00023607326,0.6386277,0.043615304,0.001544561,0.005852329,0.0034869448,0.0005579741,0.0029803796],"genre_scores_gemma":[0.7909303,0.000030719955,0.16188963,0.005631957,0.00031021424,0.0004486701,0.007891469,0.00010970812,0.032757334],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937331,0.00036321286,0.0006264572,0.0012046421,0.0036100885,0.00046247756],"domain_scores_gemma":[0.99725294,0.00021458043,0.0001523279,0.0018968871,0.000331663,0.00015162217],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015689078,0.00028526783,0.0003163136,0.0005340594,0.0015226129,0.0005054013,0.0021631876,0.000030908162,0.008370225],"category_scores_gemma":[0.000055736014,0.00022314931,0.00004487035,0.00093274785,0.00007076819,0.0009288339,0.0034417924,0.00035174732,0.00029057972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011032997,0.00043900928,0.000015990583,0.000008930356,0.000121551966,0.00006830971,0.00018831049,0.98920774,0.000007014086,0.0003584339,0.0036564092,0.0058179856],"study_design_scores_gemma":[0.002883332,0.00018084308,0.0022617541,0.00001630463,0.00008631307,0.000031744956,0.0049461923,0.86277026,0.00018781809,0.00018919585,0.12594384,0.00050240406],"about_ca_topic_score_codex":0.0003319202,"about_ca_topic_score_gemma":0.00048671634,"teacher_disagreement_score":0.48783156,"about_ca_system_score_codex":0.00037042992,"about_ca_system_score_gemma":0.00009875912,"threshold_uncertainty_score":0.99977726},"labels":[],"label_agreement":null},{"id":"W4285505943","doi":"10.1109/tnet.2022.3188285","title":"Delay-Tolerant OCO With Long-Term Constraints: Algorithm and Its Application to Network Resource Allocation","year":2022,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Networking","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada); University of Calgary; Ontario Tech University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centre of Innovation","keywords":"Regret; Computer science; Mathematical optimization; Convex function; Term (time); Convex optimization; Benchmark (surveying); Online algorithm; Algorithm; Regular polygon; Mathematics","score_opus":0.05761274990379705,"score_gpt":0.35392292111505874,"score_spread":0.2963101712112617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285505943","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008424963,0.00035704573,0.9878702,0.0010939955,0.0005432519,0.0013574003,0.000059856582,0.00014343107,0.00014985072],"genre_scores_gemma":[0.98198533,0.00006183836,0.014838126,0.00067641214,0.00066257664,0.0009410856,0.00003068924,0.00007130013,0.0007326657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99484164,0.00045785872,0.00068778277,0.0011415422,0.0021030835,0.00076807156],"domain_scores_gemma":[0.9967609,0.0013377393,0.00024677222,0.0010183504,0.00029089386,0.00034530976],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0021962707,0.0003175933,0.00038851332,0.00046130567,0.0018419707,0.00025309922,0.0010245618,0.000093549024,0.00028208754],"category_scores_gemma":[0.000044218872,0.00028838756,0.00009247177,0.002710549,0.00017527907,0.0003083668,0.000059713067,0.00081526086,0.000073024545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012123676,0.00006112013,0.0001128577,0.0000025134211,0.000028585864,0.000020684705,0.00022057135,0.4882105,0.00004498406,0.000013895225,0.00015458789,0.5110085],"study_design_scores_gemma":[0.00305386,0.001664502,0.0034469382,0.00023337704,0.00013158335,0.0008405926,0.0015526048,0.88785106,0.0007592536,0.0034766681,0.09541705,0.0015725141],"about_ca_topic_score_codex":0.000012960007,"about_ca_topic_score_gemma":0.00007820194,"teacher_disagreement_score":0.97356033,"about_ca_system_score_codex":0.0002864903,"about_ca_system_score_gemma":0.00012313983,"threshold_uncertainty_score":0.99995685},"labels":[],"label_agreement":null},{"id":"W4286375149","doi":"10.3982/ecta17664","title":"A Comment on “Using Randomization to Break the Curse of Dimensionality”","year":2022,"lang":"en","type":"article","venue":"Econometrica","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Mathematics; Curse of dimensionality; Fraction (chemistry); Class (philosophy); Sample (material); Combinatorics; Statistics; Discrete mathematics; Computer science; Artificial intelligence","score_opus":0.20650560890102532,"score_gpt":0.4499069444671524,"score_spread":0.24340133556612709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286375149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4936298,0.0009349683,0.32417214,0.16234246,0.0027733892,0.00455807,0.00063177117,0.00008144533,0.0108759375],"genre_scores_gemma":[0.9956908,0.0000029842847,0.0012240182,0.0024119786,0.0000419366,0.000056161574,0.000004133664,0.000008822726,0.00055914815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974575,0.00041605442,0.00047634216,0.0003004548,0.0011675908,0.00018207738],"domain_scores_gemma":[0.9946655,0.0043621087,0.00020467945,0.00053925894,0.00014700537,0.00008142429],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004078197,0.00007226515,0.00023598071,0.0011334508,0.00037243983,0.00005258825,0.0006829198,0.000012281336,0.0023180242],"category_scores_gemma":[0.0035611372,0.00004734098,0.00009044048,0.004214583,0.00005962649,0.00012101109,0.0005268553,0.00014029496,0.00011603157],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013401909,0.00063827453,0.0016137221,0.000003334323,0.0000635279,0.000009655418,0.0011655156,0.8244546,0.00008544698,0.0069144703,0.068499915,0.095211364],"study_design_scores_gemma":[0.004425621,0.00066208723,0.0049419263,0.00000636579,0.000011827915,0.000014342704,0.001759872,0.10037662,0.0008727759,0.026744155,0.8599191,0.0002653315],"about_ca_topic_score_codex":0.000037294514,"about_ca_topic_score_gemma":0.0000013059117,"teacher_disagreement_score":0.79141915,"about_ca_system_score_codex":0.000203598,"about_ca_system_score_gemma":0.000058782352,"threshold_uncertainty_score":0.998594},"labels":[],"label_agreement":null},{"id":"W4286713636","doi":"10.48550/arxiv.2108.00892","title":"Indexability and Rollout Policy for Multi-State Partially Observable\\n Restless Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Observable; Monte Carlo method; State (computer science); Index (typography); Mathematical optimization; Computation; Computer science; Mathematical economics; Mathematics; Algorithm; Physics; Statistics","score_opus":0.49956896987802035,"score_gpt":0.37506037072957504,"score_spread":0.12450859914844531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286713636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57660717,0.00013187982,0.42135364,0.00022545925,0.0003629879,0.0008661606,0.00027204107,0.00006910878,0.00011154542],"genre_scores_gemma":[0.9866697,0.0003174295,0.0035939708,0.00008243403,0.00018047851,0.000010335344,0.000047308793,0.000042744534,0.009055588],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947946,0.000625056,0.0006556481,0.002511505,0.00058516604,0.00082802813],"domain_scores_gemma":[0.99359703,0.0018989315,0.000477242,0.0019854049,0.0015148515,0.0005265456],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025502567,0.00047082716,0.0008779875,0.00063941005,0.0004172559,0.0006093936,0.001859276,0.00045255155,0.0001052891],"category_scores_gemma":[0.005842712,0.0004629053,0.0003746287,0.0014774466,0.0005561306,0.00064337964,0.0031881828,0.0009081228,0.000041019128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011435177,0.0006748048,0.1351406,0.00034183162,0.0003633349,0.0009109341,0.0017726715,0.8373627,0.00016503118,0.0031792056,0.00070824317,0.018237129],"study_design_scores_gemma":[0.003339518,0.00015080387,0.116001315,0.00012971715,0.00007996247,0.0000076281144,0.0011123953,0.73526585,0.0006414716,0.13823391,0.0039795726,0.0010578742],"about_ca_topic_score_codex":0.0006665835,"about_ca_topic_score_gemma":0.002352141,"teacher_disagreement_score":0.41775966,"about_ca_system_score_codex":0.0004141709,"about_ca_system_score_gemma":0.0014103639,"threshold_uncertainty_score":0.99978226},"labels":[],"label_agreement":null},{"id":"W4289655140","doi":"10.1109/isit50566.2022.9834636","title":"Multi-Environment Meta-Learning in Stochastic Linear Bandits","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Symposium on Information Theory (ISIT)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Task (project management); Computer science; Artificial intelligence; Meta learning (computer science); Machine learning; Multi-task learning; Task analysis; Mathematical optimization; Mathematics; Engineering","score_opus":0.0688220592948622,"score_gpt":0.36678422878665645,"score_spread":0.29796216949179427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289655140","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040853757,0.000117959986,0.9393944,0.0041643605,0.0045904764,0.001519368,0.0006164659,0.00022409394,0.008519077],"genre_scores_gemma":[0.98549074,0.000027103239,0.0008871653,0.0010253387,0.00018097863,0.0006699438,0.00021749259,0.000029808194,0.011471426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928707,0.0008515951,0.0012243635,0.00044842047,0.0042156978,0.0003892256],"domain_scores_gemma":[0.9967059,0.001921736,0.0005648921,0.00047201436,0.00020285537,0.00013260238],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006328962,0.000258781,0.00036428293,0.0010943763,0.0005255877,0.00024537276,0.0015424236,0.00006554343,0.014715769],"category_scores_gemma":[0.0013895555,0.00022133201,0.00025131882,0.0006948395,0.000099668505,0.0017432626,0.0005776795,0.0009747466,0.002607534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032392755,0.00013655363,0.00010146832,0.0000017349349,0.00013513681,0.000010860317,0.0014833652,0.99045056,0.00025561778,0.001817006,0.0007749851,0.004508755],"study_design_scores_gemma":[0.0024681147,0.00042120946,0.0012991495,0.000009806412,0.00004843988,0.00004724879,0.0040579196,0.87273145,0.00082458596,0.009697245,0.107877135,0.0005177107],"about_ca_topic_score_codex":0.000017174947,"about_ca_topic_score_gemma":0.0000036671279,"teacher_disagreement_score":0.944637,"about_ca_system_score_codex":0.0008641634,"about_ca_system_score_gemma":0.000076925375,"threshold_uncertainty_score":0.99816906},"labels":[],"label_agreement":null},{"id":"W4292330968","doi":"10.48550/arxiv.2202.12843","title":"Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Smoothness; Convexity; Mathematical optimization; Lipschitz continuity; Convex optimization; Convex function; Regularization (linguistics); Upper and lower bounds; Computer science; Function (biology); Bounded function; Mathematics; Regular polygon; Economics; Artificial intelligence; Mathematical analysis","score_opus":0.3304196183855856,"score_gpt":0.35242914424509725,"score_spread":0.02200952585951166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292330968","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25190705,0.00014562749,0.7385846,0.0003710758,0.0011957758,0.0021553256,0.0048156744,0.00010390632,0.0007209644],"genre_scores_gemma":[0.959218,0.00017958319,0.004611852,0.00003564475,0.000027194052,0.000014832364,0.00042626768,0.000048539423,0.035438064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960281,0.00043690513,0.0006839451,0.0016223136,0.0007065937,0.0005221006],"domain_scores_gemma":[0.99377644,0.0022620368,0.00089287525,0.0015998124,0.0012195945,0.00024923502],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014783667,0.00036491588,0.0007577128,0.0010058057,0.0004195031,0.00006411565,0.0021713874,0.00028779556,0.0016916365],"category_scores_gemma":[0.0019316723,0.00036771558,0.0005400712,0.0017143595,0.0005491616,0.0002979341,0.0022787198,0.0011642661,0.00008072273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002885645,0.0019171075,0.01868009,0.00024419263,0.000700325,0.0004292351,0.0008949512,0.9402561,0.0003545513,0.012426078,0.0072545903,0.013957143],"study_design_scores_gemma":[0.0029436692,0.00054664793,0.028316684,0.00013189187,0.00021271525,0.0000049446844,0.005435687,0.80712974,0.00008494751,0.09886728,0.055402856,0.0009229046],"about_ca_topic_score_codex":0.00013869276,"about_ca_topic_score_gemma":0.00041630305,"teacher_disagreement_score":0.7339727,"about_ca_system_score_codex":0.00087331166,"about_ca_system_score_gemma":0.00075149006,"threshold_uncertainty_score":0.99987745},"labels":[],"label_agreement":null},{"id":"W4294691466","doi":"10.23919/acc53348.2022.9867309","title":"Dynamic Regret Bounds without Lipschitz Continuity: Online Convex Optimization with Multiple Mirror Descent Steps","year":2022,"lang":"en","type":"article","venue":"2022 American Control Conference (ACC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Lipschitz continuity; Path (computing); Mathematical optimization; Convex optimization; Upper and lower bounds; Gradient descent; Mathematics; Path length; Sequence (biology); Regular polygon; Computer science; Artificial intelligence; Statistics; Mathematical analysis","score_opus":0.0478450906761866,"score_gpt":0.3652658143209036,"score_spread":0.317420723644717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294691466","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23089257,0.0002949944,0.7579706,0.0046013095,0.0006419172,0.0025941695,0.0020094316,0.0003547612,0.0006402944],"genre_scores_gemma":[0.97618365,0.00005744219,0.017700197,0.0010033821,0.000054189106,0.00047021935,0.00022781933,0.000088378045,0.0042147283],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99015653,0.0014995566,0.0011762261,0.0016765571,0.0043141926,0.001176944],"domain_scores_gemma":[0.9932284,0.0018599866,0.0012638523,0.0016050818,0.0015360618,0.0005066681],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022993633,0.00057997496,0.0014128314,0.0007238416,0.0010255185,0.0006654811,0.0022791587,0.00007256603,0.003801754],"category_scores_gemma":[0.0026065349,0.00047166843,0.00022071162,0.0026816095,0.0013488156,0.0006514722,0.00072341255,0.001259731,0.00008075182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012707849,0.0026830246,0.22175576,0.00004009984,0.00088907307,0.0006566171,0.0035813884,0.26129708,0.005180717,0.0007261221,0.002718933,0.48776335],"study_design_scores_gemma":[0.006247683,0.0017723637,0.017842857,0.000023090217,0.000067154084,0.0000739924,0.010922472,0.9400046,0.00003669673,0.00028553265,0.021958647,0.0007649071],"about_ca_topic_score_codex":0.0008757462,"about_ca_topic_score_gemma":0.0030581364,"teacher_disagreement_score":0.74529105,"about_ca_system_score_codex":0.0006065309,"about_ca_system_score_gemma":0.0012765754,"threshold_uncertainty_score":0.9997735},"labels":[],"label_agreement":null},{"id":"W4298085585","doi":"10.48550/arxiv.1001.4475","title":"X-Armed Bandits","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Alberta Innovates; Centre National de la Recherche Scientifique; Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Computer science","score_opus":0.2954986038164982,"score_gpt":0.318239257490027,"score_spread":0.022740653673528843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298085585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5182306,0.000094676514,0.46358383,0.00033373776,0.0032528043,0.00076724234,0.00017812531,0.0002807154,0.013278241],"genre_scores_gemma":[0.9647619,0.00011243111,0.0006996848,0.000061319064,0.00036297538,0.0000017359577,0.000026243491,0.000038405848,0.033935267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954556,0.000363495,0.0004929514,0.002109709,0.00085653574,0.00072167837],"domain_scores_gemma":[0.9939339,0.001447486,0.00047038274,0.002707644,0.0009511062,0.00048948923],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019088759,0.00043138745,0.0006503565,0.0009492183,0.00031979688,0.0003530058,0.0040615317,0.0007713751,0.0025607431],"category_scores_gemma":[0.0025217994,0.0004012319,0.0004185831,0.0015074016,0.00054028473,0.00046134082,0.0035168773,0.0025220132,0.0031239025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006514402,0.0006710099,0.017098075,0.000099919445,0.0003889392,0.004795046,0.0007672179,0.87109065,0.00066478184,0.030893395,0.033645317,0.0392342],"study_design_scores_gemma":[0.0012598573,0.000089078756,0.0076887435,0.00005673166,0.000065812514,0.000015180662,0.00039344688,0.30219445,0.00081587123,0.63300145,0.053320564,0.001098807],"about_ca_topic_score_codex":0.00008822111,"about_ca_topic_score_gemma":0.00024115838,"teacher_disagreement_score":0.60210806,"about_ca_system_score_codex":0.00022178685,"about_ca_system_score_gemma":0.0004987647,"threshold_uncertainty_score":0.99984396},"labels":[],"label_agreement":null},{"id":"W4300920027","doi":"10.1609/aaai.v29i1.9445","title":"Solving Games with Functional Regret Estimation","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures; Office of Naval Research; Multidisciplinary University Research Initiative; Compute Canada","keywords":"Regret; Generalization; Abstraction; Computer science; Corollary; Function (biology); Nash equilibrium; Mathematical optimization; Sequence (biology); Quality (philosophy); Artificial intelligence; Mathematical economics; Machine learning; Mathematics; Discrete mathematics","score_opus":0.28698360957141944,"score_gpt":0.4462518374060486,"score_spread":0.15926822783462918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300920027","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008412127,0.000040992043,0.9701722,0.0010820472,0.00015167859,0.00009968389,0.0000017372736,0.00006784738,0.019971654],"genre_scores_gemma":[0.8144083,0.0000014414563,0.14062318,0.0001424828,0.00015655285,0.000018373845,0.0000075405637,0.000013169886,0.044628937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968247,0.00006568057,0.0002210615,0.00031347983,0.0023698048,0.00020527682],"domain_scores_gemma":[0.9980414,0.0006017133,0.00007132389,0.0003464392,0.0007654931,0.00017361106],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016386857,0.00007918651,0.00011884015,0.000198214,0.00009095381,0.00021630502,0.00026418746,0.000032859625,0.0010595864],"category_scores_gemma":[0.0032919787,0.00004434547,0.000023756256,0.00064450194,0.000109603,0.00078859273,0.00008496675,0.00010771428,0.0012778044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038131498,0.00010116104,0.0113082165,0.0000032543762,0.000027779563,0.000048181573,0.0007264065,0.21586305,0.00010208789,0.0054700742,0.2571368,0.5088317],"study_design_scores_gemma":[0.0014376817,0.00037243284,0.017523415,0.000015458947,0.000004997267,0.00010241136,0.0028027922,0.7960553,0.0015172227,0.13859679,0.041271552,0.00029992402],"about_ca_topic_score_codex":0.000017140428,"about_ca_topic_score_gemma":0.000036115664,"teacher_disagreement_score":0.829549,"about_ca_system_score_codex":0.00007692218,"about_ca_system_score_gemma":0.00019408112,"threshold_uncertainty_score":0.99985355},"labels":[],"label_agreement":null},{"id":"W4306317496","doi":"10.1145/3511808.3557436","title":"Risk-Aware Bid Optimization for Online Display Advertisement","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 31st ACM International Conference on Information &amp; Knowledge Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Mitacs","keywords":"Bidding; Real-time bidding; Profit (economics); Budget constraint; Display advertising; Computer science; Common value auction; Lagrangian relaxation; Online advertising; Operations research; Mathematical optimization; Microeconomics; The Internet; Economics; Engineering; Mathematics","score_opus":0.1311048228999324,"score_gpt":0.41385315945114975,"score_spread":0.28274833655121734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306317496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06299778,0.00007391806,0.7413202,0.016583707,0.0075668152,0.008273478,0.0041820114,0.00031340087,0.1586887],"genre_scores_gemma":[0.9314655,0.00021044901,0.042188883,0.00037521133,0.0002298635,0.0014548389,0.00065489294,0.00003599803,0.023384359],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99575555,0.00003927346,0.0010522896,0.0003552727,0.002514256,0.00028335475],"domain_scores_gemma":[0.9953591,0.00025574092,0.001135747,0.00046187383,0.0027094053,0.00007811009],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019035873,0.00021548937,0.00022971809,0.0008174571,0.0005133985,0.00036175194,0.0035979392,0.000041794276,0.001485479],"category_scores_gemma":[0.0024215109,0.00016106901,0.00018542875,0.0008633451,0.000095462565,0.0012732054,0.002631045,0.0002968893,0.00015892951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00140195,0.0013035635,0.0028299042,0.00029606035,0.00045608156,2.5883787e-7,0.006235208,0.30160376,0.00009126233,0.20027041,0.104456,0.38105553],"study_design_scores_gemma":[0.0019145581,0.00018516649,0.0026586966,0.000109774344,0.000043077776,0.0000031308575,0.0065561035,0.44224134,0.0002427285,0.026199503,0.51949275,0.00035314885],"about_ca_topic_score_codex":0.000005310049,"about_ca_topic_score_gemma":0.000011777624,"teacher_disagreement_score":0.86846775,"about_ca_system_score_codex":0.00046222899,"about_ca_system_score_gemma":0.000052973555,"threshold_uncertainty_score":0.9994273},"labels":[],"label_agreement":null},{"id":"W4313350174","doi":"10.1016/j.orl.2022.12.006","title":"Gradient boosting for convex cone predict and optimize problems","year":2022,"lang":"en","type":"article","venue":"Operations Research Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; University of Toronto","funders":"","keywords":"Regret; Gradient boosting; Convex optimization; Mathematical optimization; Boosting (machine learning); Regular polygon; Computer science; Quadratic programming; Quadratic equation; Artificial intelligence; Mathematics; Machine learning; Random forest","score_opus":0.26017722015919637,"score_gpt":0.4724558772527916,"score_spread":0.21227865709359522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313350174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41761246,0.00083522056,0.4676271,0.10338343,0.0006923301,0.007876932,0.00081963395,0.00014331499,0.0010095632],"genre_scores_gemma":[0.94908446,0.00006940458,0.032830253,0.0014153883,0.00034679708,0.005919631,0.00012990205,0.00006789079,0.01013627],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936216,0.0009906302,0.000527558,0.00078439165,0.0032847568,0.00079109747],"domain_scores_gemma":[0.9948825,0.0033938782,0.000040716914,0.00059949467,0.00083129935,0.00025210285],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01077246,0.00013166816,0.00024494875,0.0007812734,0.003423869,0.00082353334,0.0008909745,0.000030783907,0.0007583722],"category_scores_gemma":[0.006502343,0.00011147725,0.000066754896,0.0013923409,0.0005774341,0.00051839434,0.00090833916,0.0007133725,0.000044602974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012764861,0.00015354437,0.0005908634,0.00001922732,0.00004660366,0.000035971585,0.0021629361,0.8696664,0.021093281,0.0014183805,0.08909677,0.015588402],"study_design_scores_gemma":[0.0016931541,0.0005765675,0.00045648142,0.000011974635,0.000004486992,0.000045662066,0.0032334456,0.84521055,0.00074733986,0.0016916875,0.14608434,0.0002443167],"about_ca_topic_score_codex":0.000111453286,"about_ca_topic_score_gemma":0.000053800988,"teacher_disagreement_score":0.531472,"about_ca_system_score_codex":0.0002506377,"about_ca_system_score_gemma":0.00022177295,"threshold_uncertainty_score":0.99787354},"labels":[],"label_agreement":null},{"id":"W4314946896","doi":"10.1109/cdc51059.2022.9992683","title":"A modified Thompson sampling-based learning algorithm for unknown linear systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Upper and lower bounds; Norm (philosophy); Algorithm; Thompson sampling; Combinatorics; Quadratic equation; Sampling (signal processing); Discrete mathematics; Mathematics; Computer science; Statistics; Mathematical analysis; Philosophy","score_opus":0.1707192101122855,"score_gpt":0.4198898418535795,"score_spread":0.24917063174129403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4314946896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007104216,0.0004876305,0.9870433,0.0008046731,0.0018023425,0.0016520502,0.0005219445,0.00014062716,0.00044317995],"genre_scores_gemma":[0.9804675,0.000074483025,0.009271104,0.00064363924,0.00042911974,0.0012983807,0.000056984194,0.00008227506,0.007676538],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.991274,0.0009327751,0.0012456289,0.001622129,0.0040140194,0.00091143383],"domain_scores_gemma":[0.9887778,0.00812705,0.00054782507,0.0009991669,0.0010919152,0.00045620717],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0060887113,0.00048012656,0.0010448773,0.0009301783,0.0018014902,0.0008499036,0.0015002477,0.00017326004,0.0011666836],"category_scores_gemma":[0.0034114036,0.00039004823,0.0003237433,0.0011675466,0.00019843521,0.00028096559,0.0002864593,0.0011713901,0.00012925432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014050093,0.0002083052,0.000058154452,0.000008736198,0.00004136377,0.000035952125,0.00012962152,0.24199793,0.00074011815,0.0015579652,0.0016534337,0.7521634],"study_design_scores_gemma":[0.005867977,0.0012632112,0.000110162895,0.00003638145,0.000021495287,0.000015884254,0.0009990607,0.87667656,0.0000719495,0.0060566394,0.108464465,0.00041622474],"about_ca_topic_score_codex":0.000040186806,"about_ca_topic_score_gemma":0.000018604294,"teacher_disagreement_score":0.97777224,"about_ca_system_score_codex":0.00020950532,"about_ca_system_score_gemma":0.00044388158,"threshold_uncertainty_score":0.99985516},"labels":[],"label_agreement":null},{"id":"W4314947473","doi":"10.1109/cdc51059.2022.9992636","title":"Achieving Logarithmic Regret via Hints in Online Learning of Noisy LQR Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Logarithm; Sublinear function; Matrix (chemical analysis); Computer science; Mathematical optimization; Limit (mathematics); Square root; Mathematics; Algorithm; Discrete mathematics; Machine learning","score_opus":0.08411755925804429,"score_gpt":0.38517055816339696,"score_spread":0.30105299890535264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4314947473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80422235,0.0007430475,0.18996112,0.00081503694,0.001637179,0.001157828,0.00027936843,0.00007021719,0.0011138482],"genre_scores_gemma":[0.99695045,0.00024643244,0.00032060297,0.00014825581,0.000096098534,0.000102621125,0.000014948204,0.000031984342,0.0020886185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915338,0.0014084795,0.001484586,0.001170082,0.0037646254,0.0006384285],"domain_scores_gemma":[0.9933896,0.0042572757,0.0006397472,0.00089572405,0.0005581902,0.00025945483],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054066414,0.00034878636,0.0010607914,0.0013024629,0.0005098413,0.00028711738,0.0014817844,0.00013628704,0.0015344459],"category_scores_gemma":[0.003693975,0.00028539434,0.00016457167,0.001515396,0.00022522925,0.00034770233,0.00053968304,0.0015088939,0.0000895908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019560228,0.0005031338,0.010711167,0.000018529696,0.000046409412,0.00025393814,0.0006585432,0.062629566,0.0104040485,0.00070789066,0.0007962201,0.91131455],"study_design_scores_gemma":[0.0077848164,0.0016607284,0.02517434,0.00019315137,0.000021139078,0.00010528342,0.0077184155,0.9342589,0.00013032558,0.005802156,0.016491555,0.0006592011],"about_ca_topic_score_codex":0.00020774709,"about_ca_topic_score_gemma":0.0001486654,"teacher_disagreement_score":0.9106553,"about_ca_system_score_codex":0.00021025864,"about_ca_system_score_gemma":0.0002052763,"threshold_uncertainty_score":0.9999598},"labels":[],"label_agreement":null},{"id":"W4315489038","doi":"10.1109/cdc51059.2022.9992898","title":"Partially observable restless bandits with restarts: indexability and computation of Whittle index","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reset (finance); Observable; Computation; Computer science; Index (typography); State (computer science); Markov process; Mathematical optimization; Markov decision process; Mathematics; Algorithm; Statistics; Economics","score_opus":0.11834800633433555,"score_gpt":0.386241167763421,"score_spread":0.2678931614290854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315489038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81274074,0.00024269134,0.18399937,0.0010491535,0.00034512876,0.00081060134,0.00018926611,0.000039499722,0.000583532],"genre_scores_gemma":[0.9985616,0.00006436556,0.0004634188,0.00024460637,0.000040473606,0.000106532796,0.000007701025,0.000020445093,0.0004908432],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99361676,0.0007756637,0.0008909835,0.0010387654,0.0032395788,0.00043822685],"domain_scores_gemma":[0.9947999,0.0029412196,0.0004359166,0.00073878263,0.00079686986,0.00028727017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035395324,0.00027577678,0.00069762283,0.0004411574,0.0006035073,0.0003165617,0.00067130796,0.00009460941,0.0008746223],"category_scores_gemma":[0.0014142249,0.00020622947,0.00007036781,0.00100082,0.0004434914,0.00041633015,0.00031484035,0.0006003109,0.000017602197],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016213354,0.0010017988,0.11191618,0.00004687638,0.00013615975,0.00018576771,0.0016562686,0.0909124,0.0031921505,0.00303169,0.0050129094,0.7666944],"study_design_scores_gemma":[0.015560534,0.0046067745,0.34925392,0.00015611286,0.000052511128,0.00007021158,0.0057722614,0.4872855,0.0006312923,0.12604657,0.009622244,0.00094209396],"about_ca_topic_score_codex":0.000104066516,"about_ca_topic_score_gemma":0.0004672753,"teacher_disagreement_score":0.7657524,"about_ca_system_score_codex":0.00008255326,"about_ca_system_score_gemma":0.00035226493,"threshold_uncertainty_score":0.95765007},"labels":[],"label_agreement":null},{"id":"W4315489128","doi":"10.1109/cdc51059.2022.9992906","title":"Bandit learning with regularized second-order mirror descent","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Huawei Technologies","keywords":"Descent (aeronautics); Computer science; Order (exchange); Gradient descent; Artificial intelligence; Mathematical optimization; Applied mathematics; Mathematics; Physics; Artificial neural network","score_opus":0.07159991721118657,"score_gpt":0.3584330874760927,"score_spread":0.2868331702649061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315489128","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54120094,0.0006829439,0.44139004,0.0046791798,0.0019287411,0.0025928204,0.00032230906,0.0003098477,0.0068931677],"genre_scores_gemma":[0.9737908,0.00007528987,0.002176002,0.000942906,0.00007263265,0.00028885403,0.000014514781,0.000053054395,0.022585904],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9908709,0.0010929761,0.00092873216,0.0015480524,0.004717293,0.0008420459],"domain_scores_gemma":[0.9940822,0.0030355894,0.00044470307,0.0010974988,0.000854492,0.00048551857],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038807685,0.00045605807,0.0008829482,0.0007835688,0.0015376798,0.00076483225,0.0013790743,0.0001225285,0.026091618],"category_scores_gemma":[0.0019223957,0.00033043165,0.00016912635,0.001550093,0.00031522982,0.00041159499,0.00041620602,0.0014782167,0.00041070083],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01613026,0.0008671801,0.004272534,0.000017202983,0.0002552529,0.00087399536,0.0014424248,0.0081559485,0.018244771,0.0032883864,0.01306698,0.9333851],"study_design_scores_gemma":[0.042270627,0.007891536,0.022715738,0.00016000262,0.000116158495,0.0004527163,0.012468721,0.35566306,0.0016055576,0.053003687,0.5011129,0.0025393204],"about_ca_topic_score_codex":0.000035546775,"about_ca_topic_score_gemma":0.00021301895,"teacher_disagreement_score":0.93084574,"about_ca_system_score_codex":0.00017797606,"about_ca_system_score_gemma":0.00041955357,"threshold_uncertainty_score":0.99991477},"labels":[],"label_agreement":null},{"id":"W4317036118","doi":"10.1145/3580491","title":"SEH: Size Estimate Hedging Scheduling of Queues","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Modeling and Computer Simulation","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scheduling (production processes); Computer science; Queue; Variance (accounting); Mathematical optimization; Mathematics; Computer network; Accounting; Economics","score_opus":0.16515148452082612,"score_gpt":0.44962101077759437,"score_spread":0.28446952625676825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317036118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27970895,0.000019513453,0.71974504,0.0001757288,0.00014981056,0.00008020788,0.0000042225793,0.00010863748,0.000007892149],"genre_scores_gemma":[0.9083734,0.000021429114,0.09141525,0.00002290142,0.000054310334,0.0000052016426,0.0000024046876,0.0000130725975,0.00009199326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981187,0.00008791891,0.00044599178,0.0003962788,0.00073876226,0.0002123646],"domain_scores_gemma":[0.99648833,0.0025941927,0.00007611391,0.00046600882,0.00030364658,0.000071690025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092347054,0.00011787504,0.00020747272,0.00042023955,0.00029553327,0.00012559444,0.0003017403,0.000064504435,0.000019082483],"category_scores_gemma":[0.0003732045,0.00010248623,0.00007480126,0.00087454444,0.000042247208,0.00035060282,0.00002677085,0.00017637634,0.000040939525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020325124,0.000015043317,0.000030938078,0.0000054213524,0.000008246017,0.0000011463908,0.00034132326,0.81574804,0.000046555764,0.000009724523,0.0000012784677,0.18377194],"study_design_scores_gemma":[0.0002975793,0.00005090602,0.00020051138,0.000041898165,0.000006271062,0.0000013453289,0.00013299008,0.97172105,0.000176364,0.027262364,0.000011667856,0.00009702582],"about_ca_topic_score_codex":0.00001876755,"about_ca_topic_score_gemma":0.0000028531736,"teacher_disagreement_score":0.6286645,"about_ca_system_score_codex":0.000020473217,"about_ca_system_score_gemma":0.000027443071,"threshold_uncertainty_score":0.4179267},"labels":[],"label_agreement":null},{"id":"W4318350404","doi":"10.48550/arxiv.2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; DeepMind","keywords":"Laplacian matrix; Computer science; Reinforcement learning; Eigenfunction; Scalability; Variety (cybernetics); Laplace operator; Artificial intelligence; Graph; Machine learning; Mathematical optimization; Theoretical computer science; Eigenvalues and eigenvectors; Mathematics","score_opus":0.459823302277091,"score_gpt":0.35417161248423545,"score_spread":0.10565168979285555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318350404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006209221,0.000039846174,0.9899802,0.0007572519,0.0009298949,0.0012252824,0.00021907927,0.00034646963,0.00029271777],"genre_scores_gemma":[0.9664865,0.00008335764,0.008251585,0.00006834607,0.00026447108,0.000040764076,0.00038386913,0.000078574434,0.024342539],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960252,0.00035437467,0.0005577599,0.0018274055,0.00064826163,0.00058696396],"domain_scores_gemma":[0.993933,0.0022065374,0.00050363183,0.0016876281,0.0013826406,0.0002865454],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020642872,0.00037310275,0.0005363923,0.0012888489,0.00048506958,0.0003450743,0.0020479625,0.00042622726,0.00020424493],"category_scores_gemma":[0.0026658892,0.0003811176,0.00048167864,0.0019237411,0.00026295494,0.0007251717,0.00084956014,0.00064993865,0.001147097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017480979,0.00009949427,0.00030534854,0.000030032987,0.00004577321,0.00010980862,0.00009284027,0.98854333,0.000015853466,0.0061738323,0.002731037,0.0016778222],"study_design_scores_gemma":[0.00066583516,0.000077252305,0.00049014686,0.000030001887,0.000031227857,4.1550402e-7,0.0006345942,0.67410564,0.00009924677,0.32103986,0.0025074685,0.0003183485],"about_ca_topic_score_codex":0.00006185233,"about_ca_topic_score_gemma":0.0005374281,"teacher_disagreement_score":0.9817287,"about_ca_system_score_codex":0.00038723787,"about_ca_system_score_gemma":0.00058259343,"threshold_uncertainty_score":0.9998641},"labels":[],"label_agreement":null},{"id":"W4318903797","doi":"10.48550/arxiv.2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Education, India; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Mathematical economics; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.30295243332312344,"score_gpt":0.3149585968044796,"score_spread":0.012006163481356136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318903797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09636006,0.000088239554,0.88745344,0.00036476328,0.009310709,0.0018997941,0.00049097894,0.0007345834,0.0032974654],"genre_scores_gemma":[0.9646007,0.00005457171,0.00026045652,0.00002708015,0.00064245285,0.0000070597093,0.00006837449,0.00008578156,0.03425354],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935119,0.0005658052,0.00074085646,0.0027446544,0.0013932791,0.0010434663],"domain_scores_gemma":[0.9925265,0.0025307417,0.00064893614,0.0024810932,0.0012408608,0.0005718672],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024794724,0.0006183969,0.00097294565,0.0013174225,0.00047506412,0.00044449765,0.0040232814,0.00070956565,0.0005891918],"category_scores_gemma":[0.0041194,0.00061178335,0.000482606,0.0029657525,0.0005449747,0.00054334913,0.004459955,0.0017821646,0.00604623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000293689,0.00017739326,0.000722504,0.00004194162,0.00014859554,0.0010293666,0.00019660073,0.9699215,0.000020256059,0.014799102,0.012030767,0.0006182642],"study_design_scores_gemma":[0.0014941434,0.0001447934,0.00093161786,0.00011956292,0.00007022563,0.0000064187584,0.00028598297,0.2318714,0.00005959549,0.7621259,0.002117891,0.0007724514],"about_ca_topic_score_codex":0.00014893003,"about_ca_topic_score_gemma":0.0000887453,"teacher_disagreement_score":0.88719296,"about_ca_system_score_codex":0.0006442738,"about_ca_system_score_gemma":0.00086419017,"threshold_uncertainty_score":0.9996334},"labels":[],"label_agreement":null},{"id":"W4321484040","doi":"10.1109/lcsys.2023.3247359","title":"An Online Newton’s Method for Time-Varying Linear Equality Constraints","year":2023,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Science and Engineering Research Council; Institut de Valorisation des Données","keywords":"Sublinear function; Regret; Hessian matrix; Convexity; Mathematical optimization; Smoothness; Constraint (computer-aided design); Function (biology); Online algorithm; Computer science; Mathematics; Applied mathematics; Discrete mathematics","score_opus":0.1808500052879728,"score_gpt":0.46985864577287056,"score_spread":0.28900864048489777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321484040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021431228,0.000048010945,0.96659833,0.0069795214,0.0018255267,0.0016834332,0.0010322358,0.00035793107,0.000043751676],"genre_scores_gemma":[0.96228945,0.0000048055817,0.022842774,0.00467487,0.00446452,0.0006135275,0.00018777701,0.0001578848,0.004764409],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99273825,0.0016791612,0.0013208996,0.001104145,0.0021392796,0.0010182406],"domain_scores_gemma":[0.9890007,0.008358256,0.00043815328,0.0011706838,0.000639409,0.000392846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011720788,0.00032037438,0.00092975324,0.00061566907,0.00035901868,0.0004298718,0.0013521211,0.00016712616,0.00008268282],"category_scores_gemma":[0.0032909235,0.00025579444,0.00029048155,0.0011378787,0.0002525747,0.0006001804,0.000057859248,0.00033082996,0.0010431572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034264504,0.00012284801,0.0003418843,0.0000663753,0.00019843828,0.00011927774,0.0005034811,0.46849102,0.43086922,0.00010680791,0.0509595,0.047878496],"study_design_scores_gemma":[0.0029278568,0.00012492544,0.000274853,0.000037376343,0.000020552765,0.000022436116,0.00033567508,0.9787224,0.00056985195,0.00035827624,0.016266897,0.00033893008],"about_ca_topic_score_codex":0.00015105534,"about_ca_topic_score_gemma":0.000015035106,"teacher_disagreement_score":0.94375557,"about_ca_system_score_codex":0.00016112064,"about_ca_system_score_gemma":0.00013871717,"threshold_uncertainty_score":0.99998945},"labels":[],"label_agreement":null},{"id":"W4365800375","doi":"10.1109/icc56513.2022.10093670","title":"Restless Bandits for Sensor Scheduling in Energy Constrained Networks","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Polytechnique Montréal","funders":"","keywords":"Markov decision process; Computer science; Scheduling (production processes); Partially observable Markov decision process; Mathematical optimization; Wireless sensor network; Channel (broadcasting); Observable; Job shop scheduling; Dynamic programming; Markov process; Energy consumption; Markov chain; Real-time computing; Markov model; Computer network; Algorithm; Mathematics; Engineering","score_opus":0.13562584791877827,"score_gpt":0.42956079650066964,"score_spread":0.2939349485818914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365800375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01882715,0.00020554634,0.97709787,0.0010859529,0.0005014214,0.00031294202,0.000038140366,0.000049718743,0.001881279],"genre_scores_gemma":[0.97174937,0.000014564276,0.018068224,0.00035830858,0.00019246193,0.00023999508,0.000017053895,0.000021607268,0.0093384255],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99677604,0.00028533358,0.00054386584,0.0005707339,0.0012946394,0.00052940584],"domain_scores_gemma":[0.9955683,0.0035827493,0.00010748377,0.00041146664,0.00021153288,0.00011850466],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030562193,0.00012016391,0.00027241424,0.00044610162,0.00036999764,0.00012367219,0.00071947265,0.000050584644,0.0017548556],"category_scores_gemma":[0.0018017552,0.00009867462,0.00009130234,0.0013379841,0.00011415248,0.00017836949,0.00038040866,0.00026900257,0.000012486823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001262022,0.000048868962,0.00065227255,0.0000010834088,0.0000058451765,0.000038763385,0.000060638264,0.94330776,0.000107995955,0.0048073344,0.002144477,0.048698742],"study_design_scores_gemma":[0.0011005438,0.00010538807,0.00034726516,0.0000031014315,0.000001278227,0.000017283084,0.0019394984,0.9308939,0.0002536507,0.018535716,0.046639588,0.000162774],"about_ca_topic_score_codex":0.00005021349,"about_ca_topic_score_gemma":0.00014976024,"teacher_disagreement_score":0.9590296,"about_ca_system_score_codex":0.000116321666,"about_ca_system_score_gemma":0.00014192182,"threshold_uncertainty_score":0.99915767},"labels":[],"label_agreement":null},{"id":"W4377078544","doi":"10.2139/ssrn.4448249","title":"Adaptive Neyman Allocation","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Computer science; Mathematics; Econometrics; Statistics","score_opus":0.09883633605555571,"score_gpt":0.4255126959982633,"score_spread":0.3266763599427076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377078544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10431366,0.0014808006,0.88037795,0.008522964,0.0009795005,0.00038876967,0.000007235223,0.00025161114,0.0036774955],"genre_scores_gemma":[0.9713864,0.0013640948,0.00025206574,0.000053727497,0.00047256556,0.000009443395,0.000003274354,0.000022567976,0.026435882],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943011,0.00025221665,0.0004469143,0.0003473454,0.0020597898,0.0025926454],"domain_scores_gemma":[0.9982333,0.00060203066,0.00018444947,0.0003479228,0.00048644998,0.00014581527],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010365211,0.00012365592,0.0001840741,0.00064763444,0.00041418825,0.0002051133,0.0009756348,0.00006471057,0.00015210916],"category_scores_gemma":[0.0020257363,0.00009113186,0.00012402599,0.0021820145,0.0000862416,0.0005965386,0.00013053135,0.0017103525,0.00365711],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013124388,0.00005282435,0.0007846774,8.675151e-7,0.000108219,0.00003794818,0.00048310062,0.006781128,0.00049430673,0.0939934,0.0073051485,0.88982713],"study_design_scores_gemma":[0.00038586732,0.00028442458,0.0021053154,0.0000043804334,0.0000041883372,0.00017519876,0.005739389,0.012841572,0.00013980041,0.969091,0.0091018565,0.00012702633],"about_ca_topic_score_codex":0.000018435554,"about_ca_topic_score_gemma":0.00035409088,"teacher_disagreement_score":0.8897001,"about_ca_system_score_codex":0.0007932318,"about_ca_system_score_gemma":0.0020736298,"threshold_uncertainty_score":0.99711865},"labels":[],"label_agreement":null},{"id":"W4378498571","doi":"10.48550/arxiv.2305.15383","title":"On the Minimax Regret for Online Learning with Feedback Graphs","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Combinatorics; Upper and lower bounds; Omega; Mathematics; Logarithm; Regret; Minimax; Independence number; Discrete mathematics; Graph; Statistics; Mathematical economics; Physics; Mathematical analysis","score_opus":0.3688545516703471,"score_gpt":0.32528310905810887,"score_spread":0.04357144261223822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378498571","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7868911,0.00003541605,0.20742732,0.0017506034,0.0006144487,0.0015785604,0.0003491362,0.0003131295,0.0010402526],"genre_scores_gemma":[0.93177634,0.00012584627,0.0010373663,0.00009770992,0.00012631576,0.000008110439,0.00007894426,0.000074555224,0.066674836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961608,0.00041166338,0.000354939,0.0017137666,0.000742261,0.0006165872],"domain_scores_gemma":[0.9896506,0.0072290455,0.00047108636,0.0016296826,0.00082563126,0.0001939727],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019772344,0.00039275526,0.000513842,0.0007409983,0.0005537768,0.00023524334,0.0027046797,0.0002746178,0.00020138321],"category_scores_gemma":[0.0037135568,0.00025449978,0.00035459938,0.0020532187,0.0004986644,0.00019121042,0.001350351,0.0015077945,0.0004928695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094153953,0.00013665589,0.0021172839,0.00003290612,0.00018467249,0.00032320392,0.00024136162,0.9521786,0.000008801823,0.031407204,0.009051413,0.0033763691],"study_design_scores_gemma":[0.0012389402,0.0006211997,0.0036212034,0.00021215636,0.000070368165,0.000004196844,0.0029290065,0.31486544,0.00007534894,0.6660542,0.009669953,0.0006379741],"about_ca_topic_score_codex":0.000054417702,"about_ca_topic_score_gemma":0.00024037893,"teacher_disagreement_score":0.6373131,"about_ca_system_score_codex":0.00017551288,"about_ca_system_score_gemma":0.00023671267,"threshold_uncertainty_score":0.9999907},"labels":[],"label_agreement":null},{"id":"W4378499052","doi":"10.48550/arxiv.2305.15653","title":"Alternating Subgradient Methods for Convex-Concave Saddle-Point Problems","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Subgradient method; Mathematics; Iterated function; Sequence (biology); Saddle point; Convex function; Mathematical optimization; Regular polygon; Convex optimization; Saddle; Bounded function; Linear matrix inequality; Rate of convergence; Applied mathematics; Mathematical analysis; Computer science; Geometry","score_opus":0.5393300625195931,"score_gpt":0.4107714676144865,"score_spread":0.12855859490510663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378499052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028155956,0.00015388794,0.9659954,0.00028792332,0.0021603452,0.0018739448,0.0001872785,0.00031204542,0.0008732728],"genre_scores_gemma":[0.9005832,0.00030483495,0.06099832,0.00009483217,0.00047268174,0.000052078125,0.0000918025,0.00016295548,0.03723927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936978,0.0008779826,0.0009307211,0.002790502,0.00064614695,0.0010568078],"domain_scores_gemma":[0.98799413,0.0070781265,0.000942056,0.0020821514,0.001446447,0.0004570701],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007588802,0.0005560964,0.0010279196,0.0012071066,0.0004424432,0.00042609536,0.0034959256,0.00045358652,0.00017366356],"category_scores_gemma":[0.0058568656,0.00053342385,0.00072837714,0.0016534831,0.00042532926,0.00044305465,0.0037167352,0.0011765986,0.00053633127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020334279,0.00015125902,0.0022984794,0.00021554962,0.00038112534,0.00034661024,0.0013239309,0.93833697,0.00021792136,0.017370319,0.0020923852,0.037062127],"study_design_scores_gemma":[0.0007762457,0.0001117362,0.0003508931,0.000098887045,0.00004951801,0.0000036638498,0.0006799025,0.57755566,0.0006624492,0.41265735,0.006562486,0.00049120426],"about_ca_topic_score_codex":0.00023475135,"about_ca_topic_score_gemma":0.00014276552,"teacher_disagreement_score":0.90499705,"about_ca_system_score_codex":0.00067087606,"about_ca_system_score_gemma":0.00039479314,"threshold_uncertainty_score":0.99971175},"labels":[],"label_agreement":null},{"id":"W4380088575","doi":"10.1017/apr.2022.77","title":"Conditions for indexability of restless bandits and an algorithm to compute whittle index – CORRIGENDUM","year":2023,"lang":"en","type":"erratum","venue":"Advances in Applied Probability","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mathematics; Index (typography); Minor (academic); Applied mathematics; Algorithm; Computer science; Humanities","score_opus":0.12686806210954524,"score_gpt":0.4554397477832125,"score_spread":0.32857168567366724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380088575","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060437243,0.0022428879,0.9030362,0.00078417885,0.037632067,0.023248414,0.015491509,0.00060844613,0.010912581],"genre_scores_gemma":[0.28723162,0.0036502257,0.5653807,0.0010705653,0.011503909,0.030118909,0.011038707,0.0016448993,0.088360466],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99072427,0.00046796704,0.0022365258,0.0029247904,0.002578697,0.0010677256],"domain_scores_gemma":[0.9908278,0.004148928,0.0008340941,0.0024830943,0.0011807142,0.0005253917],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0070454795,0.0006821842,0.00185677,0.0010529199,0.00032579436,0.00018637598,0.002145222,0.0007858821,0.00010109435],"category_scores_gemma":[0.0045814444,0.0006100267,0.00019642519,0.002988569,0.0013526416,0.0006696446,0.0010429847,0.0014359457,0.000047001482],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010090643,0.0014153416,0.006645383,0.0014192376,0.00008645582,0.000018030865,0.0014379442,0.02662788,0.000045668254,0.0046190573,0.14133587,0.81534004],"study_design_scores_gemma":[0.0012030756,0.00044502591,0.020009203,0.00014433317,0.000018789968,0.0000028839727,0.0004657954,0.021854734,0.00010827947,0.7527513,0.20220038,0.00079619634],"about_ca_topic_score_codex":0.00007838227,"about_ca_topic_score_gemma":0.0028734473,"teacher_disagreement_score":0.81454384,"about_ca_system_score_codex":0.00043135893,"about_ca_system_score_gemma":0.0007260372,"threshold_uncertainty_score":0.9996351},"labels":[],"label_agreement":null},{"id":"W4380136285","doi":"10.48550/arxiv.2306.04923","title":"Unconstrained Online Learning with Unbounded Losses","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Regret; Lipschitz continuity; Bounded function; Saddle point; Mathematics; Leverage (statistics); Domain (mathematical analysis); Combinatorics; Upper and lower bounds; Matching (statistics); Saddle; Mathematical optimization; Discrete mathematics; Computer science; Pure mathematics; Mathematical analysis","score_opus":0.35451916831325986,"score_gpt":0.32717478354327845,"score_spread":0.02734438476998141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380136285","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63125634,0.000037906168,0.3653558,0.0002995143,0.00049908296,0.0005215043,0.0001555852,0.000543246,0.0013310239],"genre_scores_gemma":[0.941581,0.000120614895,0.0009507027,0.000019971336,0.00017177852,0.0000014672654,0.000101335856,0.00006288779,0.05699021],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99533796,0.00054234517,0.0004688002,0.0020415736,0.0008904367,0.00071886],"domain_scores_gemma":[0.9941815,0.0025437302,0.0005160239,0.0014869373,0.0009263876,0.0003453857],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001531814,0.00048042124,0.00073930266,0.0010759209,0.00041652558,0.00040110448,0.002395417,0.0003614036,0.00046675236],"category_scores_gemma":[0.0026911136,0.0003958196,0.00026322203,0.0028645513,0.0008399286,0.0004133118,0.002285095,0.001876451,0.0010438465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028055295,0.000079940015,0.016130608,0.000031555217,0.00013959737,0.0019461483,0.00013689657,0.976816,0.000011780269,0.0012720772,0.00046851832,0.0026863543],"study_design_scores_gemma":[0.00384405,0.00086897187,0.012061655,0.00042915015,0.00021264193,0.000047208738,0.0080221575,0.6748186,0.00027041972,0.2883584,0.009038627,0.0020281565],"about_ca_topic_score_codex":0.00021724388,"about_ca_topic_score_gemma":0.00082580204,"teacher_disagreement_score":0.3644051,"about_ca_system_score_codex":0.00033275568,"about_ca_system_score_gemma":0.00063022214,"threshold_uncertainty_score":0.9998494},"labels":[],"label_agreement":null},{"id":"W4380788747","doi":"10.2196/39754","title":"Using Bandit Algorithms to Maximize SARS-CoV-2 Case-Finding: Evaluation and Feasibility Study","year":2023,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Drug Abuse; Ohio Department of Health; Ohio State University; National Center for Advancing Translational Sciences; Yale University","keywords":"Computer science; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Coronavirus disease 2019 (COVID-19); Algorithm; 2019-20 coronavirus outbreak; Medicine; Virology; Infectious disease (medical specialty)","score_opus":0.5841122104648553,"score_gpt":0.5754093158131417,"score_spread":0.008702894651713589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380788747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829136,0.00026482117,0.008182418,0.004604004,0.00035737723,0.00338958,0.00007208362,0.00012896802,0.000087161956],"genre_scores_gemma":[0.99757713,0.000035156754,0.0013739571,0.0004642849,0.0001506241,0.00020299961,0.000016141712,0.000025633293,0.00015404756],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9915985,0.0021566926,0.0010012592,0.0013830782,0.002721857,0.0011386079],"domain_scores_gemma":[0.9954357,0.0016837132,0.0002581479,0.0008437597,0.000922974,0.00085568277],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03064595,0.00025959732,0.0006398087,0.00088823284,0.00090977416,0.00073305884,0.0003851001,0.00009856443,0.00004293458],"category_scores_gemma":[0.009985424,0.00021146666,0.000050887713,0.003615178,0.00014786709,0.00057956093,0.00044458217,0.00030108602,0.00007074565],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121496,0.00028690865,0.4920065,0.00005324792,0.000026749703,0.00027577125,0.0057592154,0.00016267221,0.00007809882,0.000019602074,0.0057150437,0.4954947],"study_design_scores_gemma":[0.004276816,0.0013164544,0.6662185,0.000014841097,0.0000017807234,0.0006500889,0.014678803,0.28690466,0.000012261825,0.0030836884,0.022127347,0.00071474817],"about_ca_topic_score_codex":0.00033695827,"about_ca_topic_score_gemma":0.0011384838,"teacher_disagreement_score":0.49477994,"about_ca_system_score_codex":0.00035342385,"about_ca_system_score_gemma":0.00092041533,"threshold_uncertainty_score":0.9983539},"labels":[],"label_agreement":null},{"id":"W4381568467","doi":"10.48550/arxiv.2306.10835","title":"Online Dynamic Submodular Optimization","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Submodular set function; Regret; Mathematical optimization; Online algorithm; Computer science; Gradient descent; Function (biology); Optimization problem; Time horizon; Upper and lower bounds; Approximation algorithm; Mathematics; Artificial intelligence; Artificial neural network","score_opus":0.30933241769867287,"score_gpt":0.33002842229157897,"score_spread":0.020696004592906103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381568467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07894114,0.000051628722,0.9186133,0.00025056265,0.0009333426,0.0004196654,0.00028732265,0.00031294345,0.00019009931],"genre_scores_gemma":[0.9557642,0.0005877046,0.0052810446,0.00003586931,0.0001369788,0.0000015765509,0.00034466034,0.00007279304,0.037775185],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959151,0.0003652439,0.0004958763,0.0019233483,0.00074282323,0.00055759685],"domain_scores_gemma":[0.9955714,0.00083891285,0.0004149118,0.0020169371,0.00089056365,0.00026732523],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013265117,0.0003581491,0.0005350491,0.0012149184,0.00023497641,0.00023578189,0.002686712,0.00043214308,0.0005034986],"category_scores_gemma":[0.0019065551,0.00036195366,0.00031907862,0.0025178408,0.00027191493,0.00042230086,0.0029943788,0.0009883527,0.001240926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034497847,0.000091057744,0.00057460234,0.000012679671,0.000041119725,0.000407684,0.000039624367,0.99694353,0.000005969545,0.0003416149,0.0005001582,0.0010074646],"study_design_scores_gemma":[0.00035129997,0.000032498523,0.0021371758,0.00003634104,0.000026920829,0.0000022036234,0.00029912885,0.92859197,0.000012510299,0.06767393,0.00049276877,0.00034328306],"about_ca_topic_score_codex":0.00010179273,"about_ca_topic_score_gemma":0.0002316252,"teacher_disagreement_score":0.9133323,"about_ca_system_score_codex":0.0004664968,"about_ca_system_score_gemma":0.00030522837,"threshold_uncertainty_score":0.99988323},"labels":[],"label_agreement":null},{"id":"W4381664137","doi":"10.1098/rsos.230157","title":"Signal detection models as contextual bandits","year":2023,"lang":"en","type":"article","venue":"Royal Society Open Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristics; Computer science; Discriminative model; Exploit; Decision rule; Softmax function; Decision theory; Satisficing; Heuristic; Detection theory; Function (biology); Expected utility hypothesis; SIGNAL (programming language); Parametric statistics; Artificial intelligence; Machine learning; Mathematics; Mathematical economics; Statistics","score_opus":0.15742306652613147,"score_gpt":0.4586805725953694,"score_spread":0.3012575060692379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381664137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27082533,0.00009643161,0.6792311,0.0021451113,0.0014392836,0.001991232,0.000066973254,0.00046614022,0.04373841],"genre_scores_gemma":[0.97115636,0.000014638388,0.0016681994,0.00031349572,0.0001285571,0.0000622487,0.0000024868482,0.000015839792,0.026638184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916297,0.00014264976,0.00050968607,0.0013388786,0.005389268,0.0009897734],"domain_scores_gemma":[0.9963654,0.0012144677,0.00017075239,0.0008108948,0.0009983082,0.00044017597],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012856265,0.00019116762,0.00031304653,0.00021237088,0.002005196,0.0024663038,0.0065069036,0.00010341624,0.001016721],"category_scores_gemma":[0.0025530835,0.00014603105,0.00019662053,0.006608485,0.0014619019,0.0028230727,0.00333959,0.0003639698,0.0048838537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013821146,0.00015446618,0.00057009386,0.0000071038403,0.00003612741,0.00005554975,0.0071098385,0.3021114,0.014647889,0.0027111266,0.06955934,0.6028989],"study_design_scores_gemma":[0.00054203783,0.00015935683,0.002733843,0.000009448443,0.0000026268633,0.0000076129922,0.0038549197,0.9133366,0.00882623,0.063537486,0.0067289146,0.0002609717],"about_ca_topic_score_codex":0.00036406968,"about_ca_topic_score_gemma":0.00005786101,"teacher_disagreement_score":0.70033103,"about_ca_system_score_codex":0.00026135895,"about_ca_system_score_gemma":0.0007717775,"threshold_uncertainty_score":0.99989647},"labels":[],"label_agreement":null},{"id":"W4382239476","doi":"10.1609/aaai.v37i6.25886","title":"Opposite Online Learning via Sequentially Integrated Stochastic Gradient Descent Estimators","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China; Jinan Science and Technology Bureau","keywords":"Stochastic gradient descent; Estimator; Statistic; Computer science; Test statistic; Inference; Statistical hypothesis testing; Gradient descent; Construct (python library); Constant (computer programming); Artificial intelligence; Statistical inference; Machine learning; Mathematical optimization; Mathematics; Statistics; Artificial neural network","score_opus":0.241087663382757,"score_gpt":0.4270665249868488,"score_spread":0.18597886160409177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382239476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75180674,0.000025722871,0.24161795,0.0032391455,0.0011114582,0.0010694403,0.000047539765,0.00035355642,0.000728448],"genre_scores_gemma":[0.99673754,0.000025948157,0.0013656146,0.000053651882,0.00008931155,0.000033258886,0.000007078525,0.000034447043,0.0016531537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994455,0.000085149026,0.0012375778,0.0008966473,0.0025694703,0.0007561987],"domain_scores_gemma":[0.9954524,0.00072501804,0.00067213894,0.00040218452,0.002493884,0.00025436172],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024123746,0.00035241697,0.00049777166,0.00073570857,0.00049047853,0.0004770725,0.00259157,0.00013152706,0.00034586745],"category_scores_gemma":[0.0092041455,0.00023368523,0.0002276028,0.003953778,0.00071435195,0.00042722494,0.0007413324,0.0008963033,0.001051249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006679757,0.0006267925,0.0014523668,0.000058157017,0.00008978741,0.000015412139,0.0036962342,0.09828399,0.13036458,0.051120568,0.00088719174,0.71273696],"study_design_scores_gemma":[0.000057583246,0.00037027075,0.0008562168,0.00027640205,0.000019265206,0.000011269907,0.0033256463,0.73367983,0.12023414,0.14063537,0.00020266601,0.00033133445],"about_ca_topic_score_codex":0.0000734639,"about_ca_topic_score_gemma":0.000041613555,"teacher_disagreement_score":0.7124056,"about_ca_system_score_codex":0.00015837824,"about_ca_system_score_gemma":0.00020023828,"threshold_uncertainty_score":0.99972653},"labels":[],"label_agreement":null},{"id":"W4384157874","doi":"10.1109/netsoft57336.2023.10175461","title":"A Bandit Approach to Online Pricing for Heterogeneous Edge Resource Allocation","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Benchmark (surveying); Cloud computing; Enhanced Data Rates for GSM Evolution; Profit (economics); Resource allocation; Mathematical optimization; Greedy algorithm; Resource (disambiguation); Online algorithm; Thompson sampling; Edge computing; Algorithm; Artificial intelligence; Computer network; Mathematics","score_opus":0.2267947498082454,"score_gpt":0.45815091056837876,"score_spread":0.23135616076013335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384157874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03341436,0.00002915436,0.9607587,0.0018145955,0.00013405713,0.0010805054,0.000048028574,0.00024313442,0.0024774834],"genre_scores_gemma":[0.7011691,0.000014354374,0.1682277,0.0014251833,0.0011646644,0.0006528079,0.00033553853,0.000112501686,0.12689817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968484,0.000087169916,0.00046291825,0.0007059813,0.001383917,0.00051157986],"domain_scores_gemma":[0.9971845,0.0014985249,0.00007225186,0.0006546842,0.0003754155,0.00021463603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002225331,0.00013237829,0.0002307815,0.00064179866,0.00022989538,0.00018974856,0.00080796686,0.000066934044,0.000066354434],"category_scores_gemma":[0.0039652037,0.00009568477,0.00009881884,0.0023899768,0.000042437703,0.00016373905,0.00030005976,0.00010454358,0.0007358546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022515084,0.00033350542,0.00020307871,0.000031997955,0.00003883447,0.000012345639,0.0018789587,0.36896214,0.0030992685,0.0006562872,0.158509,0.46604943],"study_design_scores_gemma":[0.00068424863,0.00026048202,0.0010509042,0.000011027466,0.0000053497006,0.000016772285,0.0019277784,0.64471847,0.006067839,0.0068792547,0.33807263,0.00030522796],"about_ca_topic_score_codex":0.00000955016,"about_ca_topic_score_gemma":0.000026938433,"teacher_disagreement_score":0.79253095,"about_ca_system_score_codex":0.0000796989,"about_ca_system_score_gemma":0.000058270485,"threshold_uncertainty_score":0.94581676},"labels":[],"label_agreement":null},{"id":"W4384916830","doi":"10.1109/lsp.2023.3296913","title":"Effective Online Portfolio Selection for the Long-Short Market Using Mirror Gradient Descent","year":2023,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Regret; Portfolio; Mathematical optimization; Computer science; Stochastic gradient descent; Gradient descent; Online algorithm; Selection (genetic algorithm); Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.14173142515177545,"score_gpt":0.43425186841988433,"score_spread":0.2925204432681089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384916830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39208078,0.00009256342,0.605163,0.0009989428,0.00046022265,0.0010360219,0.000026746848,0.00013040882,0.000011336258],"genre_scores_gemma":[0.9938596,0.000007528801,0.003797202,0.0007512799,0.0005321826,0.00018219661,0.0000117213895,0.000060559538,0.0007977235],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99579287,0.00022716264,0.0005573338,0.0007771747,0.0018555486,0.0007899091],"domain_scores_gemma":[0.99666786,0.0021252197,0.00021211967,0.0002898875,0.00056022644,0.00014466858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003276737,0.00026408004,0.00031352878,0.0006471909,0.001142155,0.000625181,0.0007108415,0.00008054781,0.00007413707],"category_scores_gemma":[0.0006560532,0.00017318141,0.00019746266,0.0033058326,0.00023410852,0.00050677446,0.00008961453,0.00038077845,0.00002962152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005975925,0.0001756804,0.0046212957,0.00010077367,0.000120902216,0.000080857986,0.00069946324,0.07633201,0.07930995,0.0000010547162,0.039101627,0.7988588],"study_design_scores_gemma":[0.00051956065,0.00014132338,0.022434518,0.00010898524,0.00005363048,0.000057658584,0.00049283414,0.95820296,0.014826722,0.00075198454,0.0020617128,0.0003480865],"about_ca_topic_score_codex":0.000037432023,"about_ca_topic_score_gemma":0.00007240757,"teacher_disagreement_score":0.881871,"about_ca_system_score_codex":0.00029872477,"about_ca_system_score_gemma":0.00014447057,"threshold_uncertainty_score":0.8784649},"labels":[],"label_agreement":null},{"id":"W4385804701","doi":"10.1109/iccci59363.2023.10210156","title":"Multi-Armed Bandit-Aided Near-Optimal Over-The-Air Updates in Multi-Band V2X Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Japan Society for the Promotion of Science London","keywords":"Payload (computing); Computer science; Dissemination; Computer network; Heuristic; Cache; Base station; Real-time computing; Telecommunications; Network packet","score_opus":0.1863415444020136,"score_gpt":0.4592689362975821,"score_spread":0.27292739189556847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385804701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8730361,0.0005882341,0.11858657,0.0019894324,0.002114964,0.002278705,0.00013985897,0.0006814812,0.0005846899],"genre_scores_gemma":[0.9639814,0.00007407523,0.0063397107,0.0001467041,0.00015152892,0.00020206471,0.000028347991,0.000057693924,0.029018456],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933324,0.000577421,0.0011462503,0.0010727656,0.0027245493,0.0011466121],"domain_scores_gemma":[0.9938914,0.0039763944,0.00022031955,0.0012231503,0.0004010515,0.00028769486],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051469603,0.0003421316,0.00060597697,0.00074193766,0.00048070226,0.0007954522,0.0018200903,0.00019093936,0.00076386996],"category_scores_gemma":[0.0048342864,0.00020506825,0.00017839002,0.00408189,0.0005161036,0.0007788512,0.00052216765,0.0005579462,0.0049798274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048397877,0.0009610603,0.12271,0.00008357919,0.00018551933,0.001183393,0.005343867,0.6927415,0.007151233,0.00028833296,0.14398661,0.024880894],"study_design_scores_gemma":[0.0027608052,0.00007250176,0.15475287,0.00003041348,0.0000044881185,0.000014587617,0.0030573457,0.81451124,0.0012194044,0.00026107155,0.022959951,0.00035531397],"about_ca_topic_score_codex":0.00082083873,"about_ca_topic_score_gemma":0.00085167977,"teacher_disagreement_score":0.12176972,"about_ca_system_score_codex":0.00016141101,"about_ca_system_score_gemma":0.00020494123,"threshold_uncertainty_score":0.9957949},"labels":[],"label_agreement":null},{"id":"W4386245216","doi":"10.1109/infocom53939.2023.10228986","title":"Constrained Bandit Learning with Switching Costs for Wireless Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Regret; Wireless network; Block (permutation group theory); Wireless; Constraint (computer-aided design); Selection (genetic algorithm); Mathematical optimization; Computer network; Sublinear function; Distributed computing; Artificial intelligence; Machine learning; Mathematics; Telecommunications","score_opus":0.09346752566879607,"score_gpt":0.4246086438738163,"score_spread":0.33114111820502024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386245216","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04230591,0.000016869106,0.95332885,0.00069022033,0.00018467642,0.00048125884,0.0000051803704,0.00030758407,0.0026794437],"genre_scores_gemma":[0.9778126,0.000015128344,0.004198161,0.00007494121,0.00020959324,0.000079901336,0.00001740426,0.000033104534,0.017559193],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688894,0.0001310823,0.00039184038,0.0005923687,0.0013195364,0.00067624304],"domain_scores_gemma":[0.99346507,0.00543452,0.00012913533,0.00034843167,0.00043733924,0.00018553616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033353146,0.0001605309,0.00030214776,0.00035433914,0.00049603183,0.0003768151,0.0005739344,0.00008097868,0.00032368116],"category_scores_gemma":[0.0019154372,0.00010134101,0.00008047869,0.0018112753,0.00013037496,0.00040412313,0.00015593054,0.00034461945,0.00028792757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028920686,0.000027859009,0.006429518,0.0000074558693,0.00005033912,0.00008335575,0.00032555527,0.26103684,0.0004212,0.0019393066,0.011402005,0.71798736],"study_design_scores_gemma":[0.0011866621,0.00024605345,0.0015278781,0.000025993868,0.0000044684602,0.000015842588,0.0027116446,0.98000085,0.0003160382,0.0030581513,0.010678827,0.00022758952],"about_ca_topic_score_codex":0.000018463952,"about_ca_topic_score_gemma":0.000089819725,"teacher_disagreement_score":0.9491307,"about_ca_system_score_codex":0.000060538438,"about_ca_system_score_gemma":0.000101834165,"threshold_uncertainty_score":0.41325665},"labels":[],"label_agreement":null},{"id":"W4387164682","doi":"10.1109/tsc.2023.3320674","title":"Offloading Dependent Tasks in Edge Computing With Unknown System-Side Information","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Leverage (statistics); Dependency (UML); Task (project management); Artificial intelligence; Theoretical computer science; Machine learning; Algorithm","score_opus":0.04869230615834702,"score_gpt":0.3553354334982302,"score_spread":0.3066431273398832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387164682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31131828,0.000010497387,0.68645716,0.00010279393,0.0006678229,0.0003738105,0.000015023867,0.00039482614,0.0006597693],"genre_scores_gemma":[0.9967448,0.00000432452,0.0029019369,0.00010315128,0.000092200375,0.000012776132,0.00000934493,0.00002843755,0.00010302966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950759,0.00029143266,0.0011437031,0.00060755236,0.0021092137,0.0007722368],"domain_scores_gemma":[0.9965525,0.0018503391,0.00037480405,0.0006049734,0.00044107236,0.00017628439],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00295028,0.00028580942,0.00044941012,0.0018422778,0.00074365793,0.000606995,0.00094565214,0.00012712022,0.00001968242],"category_scores_gemma":[0.000034366487,0.0002434459,0.000100864774,0.004497803,0.000061081315,0.0014397788,0.000027580938,0.00066332216,0.0011570347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049627997,0.000030135358,0.00027297245,0.000101500525,0.000019189494,0.00003384308,0.0023640043,0.8339481,0.00009148943,0.000028384291,0.000008162059,0.16305262],"study_design_scores_gemma":[0.00096820336,0.00009567379,0.00303521,0.0005016696,0.000009295578,0.00004832287,0.009673544,0.9829802,0.0019824458,0.00008376901,0.00033021267,0.00029146788],"about_ca_topic_score_codex":0.00031666437,"about_ca_topic_score_gemma":0.0008577079,"teacher_disagreement_score":0.68542653,"about_ca_system_score_codex":0.00033431232,"about_ca_system_score_gemma":0.00010542093,"threshold_uncertainty_score":0.9996207},"labels":[],"label_agreement":null},{"id":"W4387341621","doi":"10.1287/opre.2023.0017","title":"Learning and Optimization with Seasonal Patterns","year":2023,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Computer science; Exploit; Mathematical optimization; Horizon; Time horizon; Upper and lower bounds; Operations research; Artificial intelligence; Machine learning; Mathematics","score_opus":0.21259826416806105,"score_gpt":0.5232147028851709,"score_spread":0.31061643871710987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387341621","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44585532,0.000082204366,0.54417425,0.0060290154,0.00007543716,0.0007991742,0.000040409323,0.00019486906,0.0027493343],"genre_scores_gemma":[0.9430463,0.00026063583,0.010957213,0.000015407255,0.00012961253,0.00015257532,0.00006521819,0.00002823539,0.045344826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99514866,0.00066317164,0.0002192392,0.0005069264,0.0029803182,0.00048170993],"domain_scores_gemma":[0.9966159,0.0014437842,0.000013417453,0.00029490687,0.0014508952,0.00018111346],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0050200345,0.00008481279,0.00012386679,0.000876897,0.0012727631,0.0010339114,0.00035317338,0.00005141902,0.0012872046],"category_scores_gemma":[0.004362111,0.00005862987,0.000018207613,0.0035529984,0.0002446575,0.00058491,0.00033480054,0.0005316315,0.000802046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021342825,0.000017053075,0.010570079,0.000003385716,0.0000066756115,0.000028324072,0.00042325645,0.95978165,0.000119197175,0.00019120469,0.0007707302,0.02806713],"study_design_scores_gemma":[0.00029090975,0.00020586504,0.007749316,0.000012411572,8.7039245e-7,0.000012381116,0.0029591396,0.98255503,0.00014688492,0.00023696315,0.005739568,0.00009067238],"about_ca_topic_score_codex":0.000057052734,"about_ca_topic_score_gemma":0.00019268574,"teacher_disagreement_score":0.533217,"about_ca_system_score_codex":0.000052640396,"about_ca_system_score_gemma":0.00020650687,"threshold_uncertainty_score":0.9999759},"labels":[],"label_agreement":null},{"id":"W4387869921","doi":"10.1109/icc45041.2023.10279145","title":"Reservation of Virtualized Resources with Optimistic Online Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"National Natural Science Foundation of China; Science Foundation Ireland; European Commission; Santa Fe Institute","keywords":"Reservation; Computer science; Regret; Service (business); Lease; Key (lock); Network virtualization; Virtualization; Computer network; Operations research; Machine learning; Computer security; Mathematics","score_opus":0.20999103032942962,"score_gpt":0.4727449675016023,"score_spread":0.26275393717217266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387869921","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8757817,0.000023741046,0.11889065,0.00095447287,0.00004704126,0.00018902906,0.000012784503,0.00019630558,0.0039042481],"genre_scores_gemma":[0.8720261,0.000031577994,0.021173557,0.00003511724,0.000076083634,0.000011972964,0.000034814395,0.000024115696,0.10658666],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966111,0.00021738876,0.00044061613,0.0003459418,0.002135118,0.00024983645],"domain_scores_gemma":[0.99596596,0.0027778985,0.00017043448,0.0003971545,0.00061059947,0.00007793362],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002271953,0.00008666511,0.00023168126,0.0005224979,0.00012908493,0.00007442706,0.0005369777,0.000042158863,0.0007280132],"category_scores_gemma":[0.009178261,0.000052451356,0.000039736526,0.0031281568,0.00016401295,0.00025370708,0.00019369535,0.00018459206,0.00025946888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001022248,0.00019003541,0.022906575,0.00003061815,0.000064622494,0.000093115406,0.0031839493,0.839027,0.006685073,0.0011003565,0.01033594,0.11536046],"study_design_scores_gemma":[0.0020853064,0.0010200182,0.08845677,0.000070834336,0.000010337453,0.000008333006,0.015917622,0.8080235,0.0039036851,0.01322976,0.06692902,0.0003448011],"about_ca_topic_score_codex":0.000051946783,"about_ca_topic_score_gemma":0.00006405837,"teacher_disagreement_score":0.11501566,"about_ca_system_score_codex":0.00001897638,"about_ca_system_score_gemma":0.000043182492,"threshold_uncertainty_score":0.99916786},"labels":[],"label_agreement":null},{"id":"W4387914395","doi":"10.1109/codit58514.2023.10284153","title":"On Parameter Selection for First-Order Methods: A Matrix Analysis Approach","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convexity; Rate of convergence; Convergence (economics); Mathematical optimization; Computer science; Stability (learning theory); Applied mathematics; Selection (genetic algorithm); Range (aeronautics); Matrix (chemical analysis); Mathematics; Artificial intelligence; Machine learning","score_opus":0.23487230915963445,"score_gpt":0.5631011984125778,"score_spread":0.32822888925294336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387914395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026661057,0.000011419073,0.9945281,0.0006988478,0.00010362075,0.00049883913,0.000013958113,0.00018206537,0.0012970564],"genre_scores_gemma":[0.027086424,0.000011921269,0.9122175,0.000115576375,0.00009495086,0.00043219552,0.000031139185,0.000027154321,0.059983168],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965602,0.00031453313,0.00046546521,0.00081545603,0.0013615476,0.00048277862],"domain_scores_gemma":[0.9869663,0.011673648,0.00010566743,0.00055697624,0.0005789051,0.000118463126],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005687404,0.00015035726,0.0003941821,0.0019378676,0.00029820224,0.00027493096,0.00055245834,0.00010348444,0.000918491],"category_scores_gemma":[0.011282267,0.00009794725,0.00033547168,0.014036153,0.000057625606,0.00024077702,0.00011693811,0.00016023408,0.00075171015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003306065,0.000248653,0.0024657273,0.000019856694,0.00086409174,0.0000026537255,0.0004908247,0.68925464,0.00018131216,0.0042592357,0.09413561,0.20774677],"study_design_scores_gemma":[0.00026959294,0.000111796544,0.0009561958,8.144493e-7,0.00005073782,9.743421e-7,0.0002696086,0.9139251,0.0004681764,0.06756539,0.016250063,0.00013153355],"about_ca_topic_score_codex":0.000029173509,"about_ca_topic_score_gemma":0.000068830755,"teacher_disagreement_score":0.22467047,"about_ca_system_score_codex":0.00006731293,"about_ca_system_score_gemma":0.000040382565,"threshold_uncertainty_score":0.9999948},"labels":[],"label_agreement":null},{"id":"W4388082363","doi":"10.1109/africon55910.2023.10293356","title":"Bandit Algorithms Applied in Online Advertisement to Evaluate Click-Through Rates","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; John Abbott College","funders":"","keywords":"Click-through rate; Computer science; Algorithm; Advertising; World Wide Web; Business","score_opus":0.24434533584965396,"score_gpt":0.524817116986591,"score_spread":0.280471781136937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388082363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53793734,0.0002688903,0.4058641,0.021044517,0.002304449,0.0057211644,0.00034784654,0.0012154485,0.02529623],"genre_scores_gemma":[0.79201746,0.0004388055,0.10260616,0.0044361893,0.001041522,0.0010998237,0.00028469047,0.00017999127,0.09789538],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929985,0.00019600728,0.001090963,0.0011431654,0.003574875,0.0009965315],"domain_scores_gemma":[0.99689317,0.0014874205,0.00010640584,0.0009548791,0.00027398774,0.0002841438],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0041044233,0.00027094313,0.0005023394,0.00095903815,0.00016292714,0.00020467139,0.0012716586,0.00010073356,0.0029180392],"category_scores_gemma":[0.0018582437,0.00019419078,0.00010029087,0.0059482786,0.00010380346,0.00040447316,0.00083845074,0.00029961584,0.010887009],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027528123,0.00047759226,0.0036652803,0.00001308429,0.000046905025,0.00021141871,0.0025317708,0.07771799,0.0032389546,0.0007244273,0.109399125,0.80169815],"study_design_scores_gemma":[0.007287731,0.00076991244,0.15102704,0.00008078026,0.000017197037,0.000011877856,0.0125309415,0.29871705,0.02688978,0.16908064,0.33190465,0.0016823733],"about_ca_topic_score_codex":0.00015476834,"about_ca_topic_score_gemma":0.0005607645,"teacher_disagreement_score":0.8000158,"about_ca_system_score_codex":0.00020792095,"about_ca_system_score_gemma":0.0001449555,"threshold_uncertainty_score":0.9979934},"labels":[],"label_agreement":null},{"id":"W4388685754","doi":"10.48550/arxiv.2311.07565","title":"Exploration via linearly perturbed loss minimisation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Regret; Minimisation (clinical trials); Perturbation (astronomy); Mathematics; Mathematical optimization; Applied mathematics; Computer science; Linear programming; Simple (philosophy); Algorithm; Statistics; Physics","score_opus":0.47377980120383045,"score_gpt":0.33473689470705636,"score_spread":0.1390429064967741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388685754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11455917,0.000024441468,0.8820753,0.0008098495,0.001246683,0.0005399146,0.00006832813,0.00030137706,0.00037493187],"genre_scores_gemma":[0.9643141,0.0001936863,0.0008375053,0.00004986145,0.0003804411,0.0000047153667,0.0001238232,0.000051083876,0.03404479],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99580157,0.00045913545,0.00055890024,0.0018010972,0.0008825313,0.00049678865],"domain_scores_gemma":[0.9949974,0.0014260815,0.0004955607,0.0016685546,0.0011467588,0.00026564853],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017251198,0.00035993362,0.0004871711,0.0010569415,0.00029131223,0.0003722809,0.0019383008,0.0004699841,0.00032512797],"category_scores_gemma":[0.002275386,0.00035628717,0.00031031267,0.0020185502,0.00027476656,0.0011286483,0.0016846367,0.00087377767,0.003949187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022258173,0.000115748684,0.0024427993,0.000033381104,0.00008657186,0.00071609934,0.0010215737,0.9804346,0.000090167676,0.0013679098,0.0046860366,0.008782529],"study_design_scores_gemma":[0.00051153224,0.00007030285,0.0025409588,0.000039246657,0.000031332456,0.0000027339877,0.0007905017,0.6875276,0.00025818855,0.30451575,0.003270266,0.00044157685],"about_ca_topic_score_codex":0.00017594158,"about_ca_topic_score_gemma":0.000176334,"teacher_disagreement_score":0.8812378,"about_ca_system_score_codex":0.0003855352,"about_ca_system_score_gemma":0.0002921142,"threshold_uncertainty_score":0.9998889},"labels":[],"label_agreement":null},{"id":"W4388740203","doi":"10.1109/tcns.2023.3333402","title":"On Learning Whittle Index Policy for Restless Bandits With Scalable Regret","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Scalability; Notation; Discrete mathematics; Mathematics; Computer science; Artificial intelligence; Machine learning; Arithmetic","score_opus":0.0682088884693561,"score_gpt":0.3776760523188988,"score_spread":0.30946716384954265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388740203","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043854374,0.000081952705,0.9917307,0.0006520635,0.0010718732,0.0012119177,0.0001107452,0.00015908456,0.0005962281],"genre_scores_gemma":[0.98672855,0.000023922119,0.00012127938,0.00004916799,0.0005681025,0.0003786308,0.0000040806117,0.000055766912,0.012070519],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99549454,0.0004680472,0.00076595513,0.0006392722,0.0018704821,0.0007616786],"domain_scores_gemma":[0.9913106,0.0067807105,0.0003630807,0.0006917206,0.0006533468,0.0002005164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028454955,0.00025547764,0.0007076779,0.0008712414,0.0005421899,0.00018585126,0.00058371626,0.00017136063,0.000044461733],"category_scores_gemma":[0.00037208345,0.00018243415,0.00019141621,0.0030202896,0.000155622,0.00024166306,0.0000028228444,0.00046751296,0.00020997382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011634165,0.00005234851,0.00019656341,0.000021177015,0.000086469336,0.000010468631,0.00006972167,0.98497784,0.00004511598,0.00019566937,0.0050546504,0.008126573],"study_design_scores_gemma":[0.0052775727,0.0016601029,0.00071589474,0.00042291483,0.000033418444,0.00001836919,0.00042371944,0.97424185,0.00023169488,0.0018612406,0.014764931,0.00034828982],"about_ca_topic_score_codex":0.00010681845,"about_ca_topic_score_gemma":0.000112480324,"teacher_disagreement_score":0.9916094,"about_ca_system_score_codex":0.00013698684,"about_ca_system_score_gemma":0.00023959325,"threshold_uncertainty_score":0.7439449},"labels":[],"label_agreement":null},{"id":"W4389262778","doi":"10.1016/j.peva.2023.102394","title":"Two families of indexable partially observable restless bandits and Whittle index computation","year":2023,"lang":"en","type":"article","venue":"Performance Evaluation","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Observability; Observable; Computation; State space; State (computer science); Mathematical optimization; Index (typography); Computer science; Mathematics; Space (punctuation); Applied mathematics; Algorithm; Statistics","score_opus":0.26607368673150594,"score_gpt":0.48535070565636956,"score_spread":0.21927701892486362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389262778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98655903,0.00010404993,0.011515549,0.00016573745,0.00027328279,0.00042762066,0.000009041623,0.000050938077,0.0008947432],"genre_scores_gemma":[0.99843943,0.00015943112,0.0006095709,0.000015204578,0.00008079878,0.00006248015,0.000041800755,0.000012342545,0.0005789297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955756,0.00024601535,0.0005757788,0.00039249734,0.0029035113,0.00030661275],"domain_scores_gemma":[0.9974915,0.0007227014,0.0002508168,0.00031306868,0.0011502405,0.00007167183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072902995,0.000118926226,0.00024055617,0.000535915,0.00023396347,0.00011734399,0.00028245954,0.00006243857,0.00015041932],"category_scores_gemma":[0.0017506108,0.00009828048,0.000031285042,0.00198002,0.00014822348,0.0010857909,0.00016258619,0.00013598488,0.00024489078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007512296,0.000024448724,0.14685334,0.000022752913,0.000009765451,7.0619717e-7,0.00079553976,0.58767986,0.000730489,0.000027184855,0.0011255706,0.26265523],"study_design_scores_gemma":[0.00061003264,0.00006399362,0.38103688,0.000019833651,0.000005332641,9.625368e-7,0.00039012678,0.61169404,0.0020003063,0.0038463448,0.00026111808,0.00007100448],"about_ca_topic_score_codex":0.000051461644,"about_ca_topic_score_gemma":0.00011441628,"teacher_disagreement_score":0.2625842,"about_ca_system_score_codex":0.00006602677,"about_ca_system_score_gemma":0.00022327279,"threshold_uncertainty_score":0.40077615},"labels":[],"label_agreement":null},{"id":"W4389891511","doi":"10.32920/24625161.v1","title":"Financial Bandits - Development of Thompson Sampling for Financial Data","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Class (philosophy); Artificial intelligence; Focus (optics); Bayesian probability; Thompson sampling; Machine learning; Financial market; Parametric statistics; Bayesian inference; Sampling (signal processing); Finance; Economics; Mathematics","score_opus":0.7430885098891811,"score_gpt":0.5754503766900538,"score_spread":0.16763813319912724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389891511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005465349,0.00012553867,0.98740625,0.0003781205,0.0030359176,0.0013100471,0.0019671284,0.00010956051,0.00020208898],"genre_scores_gemma":[0.020077987,0.00006743254,0.959272,0.000078153615,0.0019603919,0.0004274771,0.0019725983,0.00011416327,0.016029743],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99212784,0.00010776301,0.0019118972,0.0020152503,0.0031061643,0.00073106715],"domain_scores_gemma":[0.9909853,0.00398209,0.0007218848,0.0029779808,0.0011890245,0.00014371763],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00826909,0.00039085103,0.0010029621,0.00076558575,0.00034433944,0.0002574091,0.0058200243,0.0004913178,0.0003289896],"category_scores_gemma":[0.036823835,0.0003077129,0.00020554097,0.0008330786,0.00015463303,0.000306978,0.010457492,0.0006786065,0.0002629055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037022476,0.00020717812,0.000394645,0.00035258377,0.00006849225,0.000014923823,0.0011696923,0.011297149,0.00017143023,0.00095969066,0.1262845,0.8587095],"study_design_scores_gemma":[0.0017786367,0.00015349862,0.02945464,0.00054041494,0.000042268704,0.0000034826119,0.00037948095,0.059825443,0.007061584,0.42550856,0.47373813,0.0015138608],"about_ca_topic_score_codex":0.000029443338,"about_ca_topic_score_gemma":0.00061234226,"teacher_disagreement_score":0.8571956,"about_ca_system_score_codex":0.00014031817,"about_ca_system_score_gemma":0.0041874913,"threshold_uncertainty_score":0.9999375},"labels":[],"label_agreement":null},{"id":"W4389891535","doi":"10.32920/24625161","title":"Financial Bandits - Development of Thompson Sampling for Financial Data","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Class (philosophy); Artificial intelligence; Focus (optics); Bayesian probability; Machine learning; Parametric statistics; Financial market; Bayesian inference; Mathematical finance; Finance; Economics; Mathematics","score_opus":0.7430885098891811,"score_gpt":0.5754503766900538,"score_spread":0.16763813319912724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389891535","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005465349,0.00012553867,0.98740625,0.0003781205,0.0030359176,0.0013100471,0.0019671284,0.00010956051,0.00020208898],"genre_scores_gemma":[0.020077987,0.00006743254,0.959272,0.000078153615,0.0019603919,0.0004274771,0.0019725983,0.00011416327,0.016029743],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99212784,0.00010776301,0.0019118972,0.0020152503,0.0031061643,0.00073106715],"domain_scores_gemma":[0.9909853,0.00398209,0.0007218848,0.0029779808,0.0011890245,0.00014371763],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00826909,0.00039085103,0.0010029621,0.00076558575,0.00034433944,0.0002574091,0.0058200243,0.0004913178,0.0003289896],"category_scores_gemma":[0.036823835,0.0003077129,0.00020554097,0.0008330786,0.00015463303,0.000306978,0.010457492,0.0006786065,0.0002629055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037022476,0.00020717812,0.000394645,0.00035258377,0.00006849225,0.000014923823,0.0011696923,0.011297149,0.00017143023,0.00095969066,0.1262845,0.8587095],"study_design_scores_gemma":[0.0017786367,0.00015349862,0.02945464,0.00054041494,0.000042268704,0.0000034826119,0.00037948095,0.059825443,0.007061584,0.42550856,0.47373813,0.0015138608],"about_ca_topic_score_codex":0.000029443338,"about_ca_topic_score_gemma":0.00061234226,"teacher_disagreement_score":0.8571956,"about_ca_system_score_codex":0.00014031817,"about_ca_system_score_gemma":0.0041874913,"threshold_uncertainty_score":0.9999375},"labels":[],"label_agreement":null},{"id":"W4389974594","doi":"10.48550/arxiv.2312.11348","title":"Monte Carlo Tree Search in the Presence of Transition Uncertainty","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Monte Carlo tree search; Computer science; Regret; Context (archaeology); Monte Carlo method; Tree (set theory); Suite; Algorithm; Mathematical optimization; Machine learning; Mathematics; Statistics","score_opus":0.35889327179290864,"score_gpt":0.33277038649446816,"score_spread":0.02612288529844048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389974594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9260553,0.00006680425,0.070827484,0.0007959372,0.00031762684,0.0009500625,0.00019442504,0.00006316396,0.000729186],"genre_scores_gemma":[0.99658364,0.00022088969,0.00009030402,0.000017858269,0.00006116878,0.0000038497496,0.000009130224,0.000019080448,0.0029940824],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99530685,0.001267504,0.0005166953,0.0012442518,0.0011523017,0.000512423],"domain_scores_gemma":[0.9938743,0.003400405,0.0002294011,0.0017448667,0.0006359716,0.00011503485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004365759,0.0002562089,0.000497231,0.00097197335,0.00013839037,0.00011244804,0.003611705,0.000276168,0.00008079243],"category_scores_gemma":[0.0012035909,0.00019784611,0.00030069938,0.003127796,0.0005365051,0.00032631162,0.0010431429,0.0012070722,0.00013428375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014506478,0.000073248964,0.0012160416,0.000030171712,0.000022718035,0.00038575844,0.002280997,0.9930764,0.000021663835,0.00069272454,0.00042323105,0.0016319677],"study_design_scores_gemma":[0.0006274084,0.00009370063,0.014986429,0.00010921209,0.000022226943,0.0000028237396,0.0086703105,0.9056959,0.00008501547,0.06924966,0.00019132505,0.00026595814],"about_ca_topic_score_codex":0.0026325525,"about_ca_topic_score_gemma":0.002781394,"teacher_disagreement_score":0.087380484,"about_ca_system_score_codex":0.00021627426,"about_ca_system_score_gemma":0.00034230936,"threshold_uncertainty_score":0.80679303},"labels":[],"label_agreement":null},{"id":"W4391539883","doi":"10.1177/10591478241231858","title":"A Nonparametric Learning Algorithm for a Stochastic Multi-echelon Inventory Problem","year":2024,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Nonparametric statistics; Computer science; Decision maker; Time horizon; Mathematical optimization; Sequence (biology); Product (mathematics); Matching (statistics); A priori and a posteriori; Inventory control; Mathematical economics; Mathematics; Operations research; Econometrics; Statistics","score_opus":0.10217860712911685,"score_gpt":0.41911980975443025,"score_spread":0.3169412026253134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391539883","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037143283,0.0012430176,0.9942414,0.0015967628,0.00072517747,0.0015178103,0.0000067885408,0.00014278054,0.00015482999],"genre_scores_gemma":[0.10379023,0.0005184666,0.70926607,0.00008115408,0.00071085367,0.002218531,0.000046574565,0.000058631045,0.1833095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786067,0.00009970214,0.00036843744,0.0007764241,0.0006514973,0.00024329463],"domain_scores_gemma":[0.99918246,0.00014343012,0.000032015665,0.00025727574,0.0003017372,0.000083049155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021091027,0.00013066146,0.00014264285,0.0010497501,0.0005182772,0.0008098515,0.00018437936,0.000036490146,0.000071908515],"category_scores_gemma":[0.0011118547,0.00010407865,0.000056182103,0.0016578456,0.00007930729,0.00057849067,0.00014610602,0.00019508132,0.0001630117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060510947,0.000081398735,0.000009336609,0.000048209786,0.000044351997,0.0000033549345,0.00045556284,0.1432928,0.00003333413,0.0012756068,0.0026433945,0.85210663],"study_design_scores_gemma":[0.00021084918,0.00008520927,0.000075321856,0.000036665748,0.000022139273,0.000009186849,0.000865716,0.93271965,0.00005602087,0.0016444008,0.06414298,0.00013186964],"about_ca_topic_score_codex":0.000008006592,"about_ca_topic_score_gemma":0.000022065798,"teacher_disagreement_score":0.8519747,"about_ca_system_score_codex":0.00010368279,"about_ca_system_score_gemma":0.000038966533,"threshold_uncertainty_score":0.78094167},"labels":[],"label_agreement":null},{"id":"W4392044436","doi":"10.1287/msom.2021.0135","title":"Feature-Based Inventory Control with Censored Demand","year":2024,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Inventory control; Feature (linguistics); Computer science; Regret; Mathematical optimization; Inventory theory; Operations research; Mathematics; Machine learning","score_opus":0.035355270218556556,"score_gpt":0.34184070000304223,"score_spread":0.3064854297844857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392044436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052521218,0.0005601714,0.9076006,0.030619869,0.00067528296,0.0020326804,0.000060659877,0.0005201591,0.0054093897],"genre_scores_gemma":[0.96581537,0.000016642236,0.015626084,0.0020981692,0.00017270392,0.0002939892,0.000043818734,0.000054460772,0.015878772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962654,0.00019043376,0.0003604558,0.00089972996,0.0017947139,0.00048923615],"domain_scores_gemma":[0.99828064,0.0002859348,0.00004431242,0.000972929,0.00023819033,0.00017799508],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011662884,0.00028679564,0.00026951116,0.0007167649,0.00048151196,0.0017822275,0.00087489927,0.00006613802,0.00057049823],"category_scores_gemma":[0.000043474178,0.00019504246,0.0000882481,0.0009194445,0.00006809574,0.0006876922,0.00018435069,0.00031570162,0.0012092527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011500233,0.000106851556,0.00012691366,0.00018956895,0.00022566265,0.00039337354,0.00032682982,0.96919554,0.00008348728,0.002119492,0.007742413,0.01937484],"study_design_scores_gemma":[0.0021839761,0.00015367146,0.007972245,0.0002198572,0.00012049348,0.000015112012,0.00088363804,0.6614196,0.0070649856,0.0018852501,0.3174676,0.0006136319],"about_ca_topic_score_codex":0.000052159226,"about_ca_topic_score_gemma":0.0006744444,"teacher_disagreement_score":0.91329414,"about_ca_system_score_codex":0.00019612389,"about_ca_system_score_gemma":0.00008108073,"threshold_uncertainty_score":0.9995684},"labels":[],"label_agreement":null},{"id":"W4392270931","doi":"10.48550/arxiv.2402.17235","title":"Stochastic Gradient Succeeds for Bandits","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Mathematical economics; Computer science; Economics; Econometrics; Mathematics","score_opus":0.29064790336143387,"score_gpt":0.3273040213724201,"score_spread":0.03665611801098623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392270931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09335161,0.00035574267,0.89959896,0.00031727113,0.002981715,0.0012940316,0.00048494525,0.00022394735,0.0013917623],"genre_scores_gemma":[0.96894175,0.00004068928,0.000459383,0.000030778825,0.0003828408,0.000010859513,0.000039273804,0.00005620845,0.03003824],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956967,0.00016325821,0.0005091618,0.0022179985,0.0006575713,0.00075528567],"domain_scores_gemma":[0.99491906,0.0019953393,0.00028421526,0.0015566509,0.0008505707,0.00039415233],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016901415,0.00045018853,0.0006509728,0.0012851583,0.00028034262,0.00043097915,0.002491319,0.00039359534,0.0003429545],"category_scores_gemma":[0.0016191041,0.00041042245,0.00060685544,0.001613307,0.0003413768,0.0002158019,0.0034287705,0.0011048053,0.001392925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022085311,0.000107228705,0.00011623028,0.00011328978,0.00018335685,0.0003695086,0.00028360673,0.943674,0.000014659133,0.03868845,0.011658823,0.0045699487],"study_design_scores_gemma":[0.00040461152,0.00009108979,0.00012696839,0.00007639341,0.000078363184,0.0000047864105,0.0002475828,0.4306867,0.000040784525,0.56399435,0.0038852259,0.0003631312],"about_ca_topic_score_codex":0.000050063583,"about_ca_topic_score_gemma":0.000090442365,"teacher_disagreement_score":0.8991396,"about_ca_system_score_codex":0.000502352,"about_ca_system_score_gemma":0.000455291,"threshold_uncertainty_score":0.9998348},"labels":[],"label_agreement":null},{"id":"W4392487808","doi":"10.48550/arxiv.2403.01315","title":"Near-optimal Per-Action Regret Bounds for Sleeping Bandits","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Action (physics); Mathematical economics; Economics; Computer science; Mathematics; Econometrics; Statistics; Physics","score_opus":0.35036165592399393,"score_gpt":0.35515225202680634,"score_spread":0.0047905961028124056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392487808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.325005,0.000297674,0.66805756,0.0003938386,0.002943968,0.0009167823,0.0002579395,0.00028093497,0.0018463016],"genre_scores_gemma":[0.96668905,0.00013717193,0.003191523,0.000039482435,0.0005445229,0.000008730726,0.000059822672,0.00006772307,0.029261984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955472,0.00023648863,0.00052425143,0.0022652063,0.0006818373,0.0007450564],"domain_scores_gemma":[0.99571115,0.0012786449,0.00036120907,0.001471557,0.00086338405,0.00031403906],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019368075,0.00045093038,0.0006297451,0.00081567036,0.0006148466,0.0010221247,0.0018436671,0.0005378354,0.00051722204],"category_scores_gemma":[0.0012123864,0.00044309217,0.00060154544,0.0012920204,0.00043351,0.00051874714,0.002608434,0.0014009388,0.001241071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047967167,0.00009695974,0.0006135456,0.00019662287,0.00024122084,0.00041376654,0.0005244391,0.9633,0.00008992613,0.0067947214,0.011718593,0.015530536],"study_design_scores_gemma":[0.0005339085,0.00013515532,0.0003529891,0.00010347533,0.000092924325,0.000011524534,0.00055948074,0.7641208,0.00019907994,0.19224864,0.041110545,0.00053148664],"about_ca_topic_score_codex":0.00008161943,"about_ca_topic_score_gemma":0.00008811442,"teacher_disagreement_score":0.66486603,"about_ca_system_score_codex":0.00069077016,"about_ca_system_score_gemma":0.000642009,"threshold_uncertainty_score":0.9998021},"labels":[],"label_agreement":null},{"id":"W4392847906","doi":"10.2196/52688","title":"New Approach to Equitable Intervention Planning to Improve Engagement and Outcomes in a Digital Health Program: Simulation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Diabetes","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Verily Life Sciences","keywords":"Psychological intervention; Dropout (neural networks); Intervention (counseling); Digital health; Outcome (game theory); Resource allocation; Computer science; Resource (disambiguation); Process management; Medicine; Business; Health care; Nursing; Machine learning; Economics; Microeconomics","score_opus":0.15457686544406057,"score_gpt":0.516135049651501,"score_spread":0.36155818420744046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392847906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89397633,0.00028112944,0.099809945,0.0005812322,0.00020769204,0.00476214,0.000021270895,0.00014440308,0.00021583657],"genre_scores_gemma":[0.9929535,2.8935045e-7,0.0040068524,0.00005235515,0.000062744715,0.00064127444,0.0000069678026,0.000018047522,0.0022579874],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969989,0.00012425955,0.0005556719,0.0007364074,0.0009876593,0.0005971014],"domain_scores_gemma":[0.9983964,0.0009084771,0.00005533932,0.00030335083,0.00007504687,0.000261365],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032616055,0.00015443741,0.00031741703,0.00073263113,0.00011240988,0.0015441714,0.0003087156,0.000031257656,0.000023192835],"category_scores_gemma":[0.0013063439,0.00011561075,0.000055780543,0.0012336522,0.000014759237,0.00084552803,0.0006526801,0.00020459622,0.00011519747],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015454767,0.0004737472,0.0834106,0.000042996024,0.000021022215,0.0000027309443,0.0049422197,0.014623558,0.000013781016,0.000018339566,0.00083063234,0.8956049],"study_design_scores_gemma":[0.0026103407,0.006710842,0.5318321,0.0004883611,0.000011723625,5.494023e-7,0.020751085,0.40154192,0.00010680808,0.01393472,0.021204036,0.0008075382],"about_ca_topic_score_codex":0.000026875952,"about_ca_topic_score_gemma":0.000013587216,"teacher_disagreement_score":0.8947974,"about_ca_system_score_codex":0.0001632251,"about_ca_system_score_gemma":0.000061148196,"threshold_uncertainty_score":0.99949235},"labels":[],"label_agreement":null},{"id":"W4393146897","doi":"10.1609/aaai.v38i19.30182","title":"Responsible Bandit Learning via Privacy-Protected Mean-Volatility Utility","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Volatility (finance); Computer science; Internet privacy; Computer security; Artificial intelligence; Business; Econometrics; Economics","score_opus":0.23644016349401392,"score_gpt":0.4303859763608097,"score_spread":0.1939458128667958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393146897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7312461,0.00033850168,0.23167604,0.012087218,0.0019657402,0.0026054615,0.000059175247,0.00072115136,0.019300599],"genre_scores_gemma":[0.9950562,0.000030097954,0.0015297711,0.000032489384,0.00013547354,0.000047039193,9.740359e-7,0.000028932562,0.0031389997],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993507,0.00019852057,0.0013620738,0.0013064657,0.0029495207,0.0006764176],"domain_scores_gemma":[0.9942891,0.001895123,0.00043361544,0.0007568269,0.0024120656,0.00021324196],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006627342,0.00035644489,0.0005185211,0.0005431432,0.0005267726,0.00095717126,0.0031468899,0.00019778695,0.0022805005],"category_scores_gemma":[0.020441165,0.0002328263,0.0002946122,0.0034031065,0.0009137788,0.00086048443,0.0009839268,0.0014154225,0.0008652479],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011781075,0.00026367995,0.0011496444,0.00013667894,0.00006245491,0.000007704026,0.004713302,0.00035156612,0.11644496,0.06610196,0.00094901887,0.8086409],"study_design_scores_gemma":[0.000018798646,0.00017206816,0.00062000006,0.00015730312,0.000008808023,0.00000509652,0.00076768745,0.29460397,0.27187985,0.4299971,0.0015914859,0.00017782487],"about_ca_topic_score_codex":0.00007427278,"about_ca_topic_score_gemma":0.000032724023,"teacher_disagreement_score":0.8084631,"about_ca_system_score_codex":0.00013679855,"about_ca_system_score_gemma":0.0004402265,"threshold_uncertainty_score":0.9999127},"labels":[],"label_agreement":null},{"id":"W4393157138","doi":"10.1609/aaai.v38i14.29443","title":"Learning Not to Regret","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Grantová Agentura České Republiky","keywords":"Regret; Psychology; Computer science; Machine learning","score_opus":0.2905248091849463,"score_gpt":0.4733330005536306,"score_spread":0.18280819136868431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393157138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73950016,0.00016567911,0.10148308,0.068461604,0.004377055,0.0025045646,0.00006044125,0.0006937751,0.08275362],"genre_scores_gemma":[0.98869807,0.000023795797,0.0010582109,0.00018007398,0.00017877115,0.000025952395,2.5426905e-7,0.000023184733,0.009811721],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9953471,0.000043461885,0.000836392,0.0008514376,0.0024322227,0.0004893966],"domain_scores_gemma":[0.99681836,0.0009681633,0.00019268556,0.00035397903,0.0014756542,0.00019114287],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029883473,0.00022749734,0.00032688348,0.00051776407,0.00027234032,0.0009801476,0.0024404547,0.000096432865,0.00087694504],"category_scores_gemma":[0.011348607,0.00014124143,0.00018366653,0.0026552256,0.0003556325,0.0004748167,0.0006203851,0.0007375239,0.0030261464],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017824846,0.000053578475,0.000108313885,0.000028637836,0.000016491033,0.0000037050393,0.0032596088,0.0012730078,0.055029534,0.29589304,0.0023657759,0.64179003],"study_design_scores_gemma":[0.000012713428,0.0003909591,0.00018154255,0.00032619818,0.0000075782727,0.0000072759035,0.0035173944,0.07766184,0.5865977,0.32287034,0.00818055,0.00024592716],"about_ca_topic_score_codex":0.000020851263,"about_ca_topic_score_gemma":0.000008365019,"teacher_disagreement_score":0.6415441,"about_ca_system_score_codex":0.0000823079,"about_ca_system_score_gemma":0.00015504801,"threshold_uncertainty_score":0.9977501},"labels":[],"label_agreement":null},{"id":"W4393160289","doi":"10.1609/aaai.v38i15.29558","title":"Multiobjective Lipschitz Bandits under Lexicographic Ordering","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; City University of Hong Kong","keywords":"Lexicographical order; Lipschitz continuity; Mathematics; Mathematical economics; Mathematical optimization; Applied mathematics; Combinatorics; Pure mathematics","score_opus":0.2554005872919155,"score_gpt":0.44457654767578736,"score_spread":0.18917596038387186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393160289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6532605,0.0008768606,0.21948563,0.025856895,0.010231115,0.0031815448,0.00012312173,0.00092140964,0.08606288],"genre_scores_gemma":[0.9969802,0.0001150568,0.00075405824,0.00008574947,0.0002318175,0.000041548472,4.8956133e-7,0.00002958565,0.0017614965],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99541664,0.000043197382,0.00088593684,0.0009739451,0.0021448683,0.0005354356],"domain_scores_gemma":[0.9968126,0.0008397541,0.00025979974,0.00041854967,0.0015201843,0.00014911639],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019820328,0.0002942657,0.0003617003,0.0007204199,0.00032569474,0.0011029494,0.002497873,0.00014149997,0.00076186383],"category_scores_gemma":[0.0036214308,0.00018688623,0.0002687299,0.0030746972,0.0007447302,0.0008070608,0.00054148893,0.0007345237,0.00071385084],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024946986,0.00020824118,0.00030843454,0.000050520095,0.00009268428,0.000005308226,0.0029667066,0.0021704247,0.05578538,0.3899572,0.00079427235,0.5474114],"study_design_scores_gemma":[0.000029706833,0.00016283822,0.00046946926,0.00029560042,0.000013980819,0.000009448137,0.00542635,0.08653226,0.30988556,0.5957065,0.0011899722,0.00027829706],"about_ca_topic_score_codex":0.000038299757,"about_ca_topic_score_gemma":0.000038757655,"teacher_disagreement_score":0.5471331,"about_ca_system_score_codex":0.00008368034,"about_ca_system_score_gemma":0.00018117667,"threshold_uncertainty_score":0.999934},"labels":[],"label_agreement":null},{"id":"W4393277074","doi":"10.54254/2755-2721/54/20241586","title":"Assessing the robustness of Multi-Armed Bandit algorithms against biased initialization","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Initialization; Robustness (evolution); Adaptability; Computer science; Recommender system; Thompson sampling; Greedy algorithm; Upper and lower bounds; Commit; Machine learning; Algorithm; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.101806615478968,"score_gpt":0.405559755997657,"score_spread":0.30375314051868896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393277074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021503257,0.0003160054,0.97746825,0.00010494239,0.00026590063,0.00015445227,0.000010533142,0.00006848317,0.000108164204],"genre_scores_gemma":[0.9756388,0.000010875269,0.024089612,0.000019300507,0.00015059028,0.00002338973,0.000028453063,0.000017029404,0.00002196774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983503,0.00002890281,0.00036431197,0.00028524897,0.0008091539,0.00016207987],"domain_scores_gemma":[0.9976436,0.0019667957,0.00005536381,0.00012312976,0.00015741322,0.000053682423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081449654,0.00011433584,0.00015885032,0.00026606407,0.00013467795,0.00042496785,0.00021141033,0.000043829445,0.000018254206],"category_scores_gemma":[0.0002524476,0.00007858108,0.000040333423,0.0008465434,0.000083579915,0.00029508487,0.000080263795,0.00015524619,0.0000078101075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017704613,0.00001007879,0.0000075760395,0.000019184192,0.000015299207,0.0000036451488,0.00014678693,0.9321075,0.00034921005,0.0017314488,0.000026173422,0.06558134],"study_design_scores_gemma":[0.00022375389,0.0000060124385,0.0020714968,0.000035110545,0.0000047125313,0.000005795252,0.0002456867,0.9949982,0.00027728282,0.0014637302,0.000574765,0.00009344728],"about_ca_topic_score_codex":0.0000016742831,"about_ca_topic_score_gemma":5.8731956e-7,"teacher_disagreement_score":0.95413554,"about_ca_system_score_codex":0.000026498536,"about_ca_system_score_gemma":0.00006199832,"threshold_uncertainty_score":0.40979746},"labels":[],"label_agreement":null},{"id":"W4393335276","doi":"10.1287/mnsc.2022.00893","title":"On Statistical Discrimination as a Failure of Social Learning: A Multiarmed Bandit Approach","year":2024,"lang":"en","type":"article","venue":"Management Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Social learning; Statistical learning; Machine learning; Knowledge management","score_opus":0.06935144906801434,"score_gpt":0.4468491803035057,"score_spread":0.37749773123549135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393335276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019796472,0.000020855952,0.9240705,0.0013167406,0.00032097343,0.0005752432,0.000017306287,0.00010755689,0.05377437],"genre_scores_gemma":[0.98135275,0.0000031030909,0.0091970945,0.000028957045,0.000041476374,0.00003804137,0.000006571602,0.000009645114,0.009322368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938111,0.00013913089,0.00036415464,0.0008645179,0.0044023213,0.0004188298],"domain_scores_gemma":[0.9986118,0.00072440325,0.00008087951,0.00030328307,0.00017377778,0.00010584131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039127683,0.00012836837,0.00017859896,0.0010260235,0.00041444539,0.0005824665,0.0011047838,0.000034156103,0.0005116808],"category_scores_gemma":[0.0022348186,0.000091351045,0.00005997375,0.0030082355,0.0009564207,0.0005889987,0.0004511373,0.0002565929,0.00056453503],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074060226,0.00026750632,0.00010667086,0.00013036728,0.000026851443,0.000102029495,0.0037066524,0.0077825594,0.0006030485,0.7248739,0.009863542,0.2524628],"study_design_scores_gemma":[0.00080184895,0.00052694575,0.023172842,0.000075714386,0.000035772006,0.000008865895,0.012390563,0.72804284,0.0011128277,0.18772958,0.045645006,0.00045716183],"about_ca_topic_score_codex":0.0000066133357,"about_ca_topic_score_gemma":0.0000023146738,"teacher_disagreement_score":0.96155626,"about_ca_system_score_codex":0.00013529531,"about_ca_system_score_gemma":0.00007453473,"threshold_uncertainty_score":0.7256144},"labels":[],"label_agreement":null},{"id":"W4394775968","doi":"10.48550/arxiv.2404.06516","title":"Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Regret; Nash equilibrium; Mathematical optimization; Best response; Correlated equilibrium; Computer science; Sublinear function; Epsilon-equilibrium; Convergence (economics); Markov chain; Stackelberg competition; Markov decision process; Flexibility (engineering); Mathematical economics; Mathematics; Markov process; Game theory; Equilibrium selection; Repeated game; Economics; Statistics; Discrete mathematics","score_opus":0.12614915939140928,"score_gpt":0.29944468377243866,"score_spread":0.17329552438102938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394775968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9621145,0.00044660192,0.031034758,0.00044542315,0.0023646906,0.00075752963,0.00018415863,0.00011997076,0.002532332],"genre_scores_gemma":[0.9755773,0.0002735084,0.00051395444,0.00007642157,0.00017797052,0.0000030177628,0.000009532142,0.000037348276,0.023330973],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952278,0.00033519143,0.00055843004,0.0024251854,0.0007262318,0.0007271328],"domain_scores_gemma":[0.99694854,0.0006034766,0.00018385178,0.0013719456,0.0005677819,0.00032442785],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015689526,0.00044930755,0.00068385026,0.0014598372,0.000080942984,0.00040895902,0.0021560397,0.0003785679,0.0005453353],"category_scores_gemma":[0.0012410103,0.00043304058,0.00023843559,0.0020741732,0.00041861567,0.0003729008,0.007428267,0.0012761015,0.0023603726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022059048,0.00039610965,0.017821178,0.00048171348,0.00037801982,0.013140737,0.0020421068,0.886158,0.002372586,0.009817934,0.042286713,0.02289902],"study_design_scores_gemma":[0.0009496717,0.00018838064,0.005605635,0.0003702878,0.00005546968,0.000027172053,0.0006957266,0.7101499,0.00040472022,0.2751499,0.005347722,0.0010554141],"about_ca_topic_score_codex":0.00024066035,"about_ca_topic_score_gemma":0.0002158986,"teacher_disagreement_score":0.26533198,"about_ca_system_score_codex":0.00027868696,"about_ca_system_score_gemma":0.0003685936,"threshold_uncertainty_score":0.9998121},"labels":[],"label_agreement":null},{"id":"W4394780679","doi":"10.48550/arxiv.2404.07266","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Prior probability; Machine learning; Reinforcement learning; Artificial intelligence; Regret; Bayesian probability; Principle of maximum entropy; Posterior probability; Task (project management); Entropy (arrow of time); Engineering","score_opus":0.35285953384187685,"score_gpt":0.360209135595926,"score_spread":0.00734960175404914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394780679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4107872,0.00020157668,0.58700687,0.00011758806,0.00060719915,0.00036485188,0.0000711835,0.00015158711,0.0006919246],"genre_scores_gemma":[0.9916701,0.00009807396,0.006196828,0.00007235805,0.00020139043,0.0000042886927,0.000020952742,0.000056316894,0.001679708],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950293,0.0003937551,0.00057278463,0.002347714,0.0010243722,0.00063210435],"domain_scores_gemma":[0.99544597,0.0012400652,0.00032396897,0.0019520494,0.0007453622,0.0002925847],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011631801,0.0005031634,0.0005749387,0.00090736785,0.0004407441,0.0008009024,0.002176431,0.00045307368,0.00047390693],"category_scores_gemma":[0.00040362542,0.00041917013,0.00041118124,0.0020024313,0.0004810685,0.00046739975,0.0036455705,0.0013455941,0.00071698485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032397537,0.0001095937,0.0016574927,0.000022943184,0.0002167533,0.0012775277,0.00014368656,0.9814504,0.00011134328,0.0074573276,0.0008603495,0.006368625],"study_design_scores_gemma":[0.0007082699,0.00012347105,0.0024386293,0.0004244893,0.000108071,0.000042569358,0.00087306445,0.4304192,0.00056926627,0.5625678,0.0008832715,0.0008419322],"about_ca_topic_score_codex":0.00008734201,"about_ca_topic_score_gemma":0.0012216433,"teacher_disagreement_score":0.58088285,"about_ca_system_score_codex":0.0005850625,"about_ca_system_score_gemma":0.0007724993,"threshold_uncertainty_score":0.999826},"labels":[],"label_agreement":null},{"id":"W4396780329","doi":"10.1016/j.jfranklin.2024.106884","title":"Online composite optimization with time-varying regularizers","year":2024,"lang":"en","type":"article","venue":"Journal of the Franklin Institute","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Regret; Metric (unit); Path (computing); Convex optimization; Upper and lower bounds; Function (biology); Regular polygon; Variation (astronomy); Convex function; Mathematical optimization; Mathematics; Computer science; Optimization problem; Online algorithm; Combinatorics; Statistics; Mathematical analysis; Physics; Engineering","score_opus":0.0543017719601523,"score_gpt":0.3727089263373512,"score_spread":0.3184071543771989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396780329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02653936,0.0012814873,0.9625371,0.0058127074,0.0028106726,0.0002696004,0.000023713426,0.000036069658,0.0006893072],"genre_scores_gemma":[0.4941504,0.00037970516,0.47797915,0.00091024453,0.0034628608,0.00000994545,0.000015381704,0.0001154918,0.022976832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99656934,0.00015545858,0.0006918674,0.0002206278,0.0021530776,0.0002096578],"domain_scores_gemma":[0.9980612,0.00045013562,0.00032304376,0.00042162865,0.0006312439,0.00011277976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018141445,0.00013396081,0.00028584033,0.0004076995,0.00024133037,0.0004482064,0.0011828605,0.000064524575,0.00018322215],"category_scores_gemma":[0.0008571236,0.00006417077,0.00019443227,0.0014871176,0.00029072122,0.0012717873,0.00016583204,0.00060721854,0.000077689525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001373829,0.00005139953,0.000082493665,0.0000070801834,0.00007704291,0.0001603724,0.0001335117,0.9824434,0.00079121615,0.000057480866,0.002338749,0.013719901],"study_design_scores_gemma":[0.00108664,0.00022272966,0.0007557162,0.00066382525,0.00008442142,0.001171534,0.0000767114,0.89458525,0.0019213258,0.0048147407,0.09439013,0.00022699298],"about_ca_topic_score_codex":0.0000043802147,"about_ca_topic_score_gemma":0.000004372917,"teacher_disagreement_score":0.48455793,"about_ca_system_score_codex":0.000113367816,"about_ca_system_score_gemma":0.00033518605,"threshold_uncertainty_score":0.43220648},"labels":[],"label_agreement":null},{"id":"W4396982365","doi":"10.1109/tdsc.2024.3401836","title":"A Differentially Private Approach for Budgeted Combinatorial Multi-Armed Bandits","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Mathematical economics; Operations research; Economics; Mathematics","score_opus":0.08362743912680343,"score_gpt":0.38310144994046785,"score_spread":0.2994740108136644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396982365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031405695,0.00026882338,0.96454126,0.00009910651,0.0025501798,0.0007521314,0.00009939645,0.00021865881,0.00006476354],"genre_scores_gemma":[0.97627395,0.000025422696,0.022622922,0.000029074065,0.00025891975,0.000048543377,0.000012668081,0.00004591605,0.0006825601],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966487,0.00017515071,0.0006100475,0.00097428204,0.001009746,0.00058204],"domain_scores_gemma":[0.9971464,0.0019342488,0.00008662096,0.0003649315,0.0002518112,0.0002159381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012717027,0.0002894265,0.0004255082,0.0005215984,0.0007494877,0.00083048607,0.00047936718,0.00018237665,0.00006753177],"category_scores_gemma":[0.00013907887,0.00022492965,0.00021690819,0.00086964556,0.000112620684,0.0003526081,0.00001339579,0.0005986264,0.000032739557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087564543,0.0014162536,0.000054267202,0.0005019448,0.00060138886,0.00013273036,0.003883914,0.2139733,0.006813416,0.0020816869,0.001616593,0.7680489],"study_design_scores_gemma":[0.0018267926,0.00022183062,0.000052809206,0.00006201648,0.000037860373,0.000035300476,0.0001828996,0.9820612,0.008303257,0.0032705604,0.0036450778,0.00030038314],"about_ca_topic_score_codex":0.000014245918,"about_ca_topic_score_gemma":0.000014014433,"teacher_disagreement_score":0.94486827,"about_ca_system_score_codex":0.00007258184,"about_ca_system_score_gemma":0.0001083847,"threshold_uncertainty_score":0.9172365},"labels":[],"label_agreement":null},{"id":"W4399452441","doi":"10.2139/ssrn.4851778","title":"LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Content (measure theory); Online learning; Algorithm; Artificial intelligence; Multimedia; Mathematics","score_opus":0.18847935546344036,"score_gpt":0.4652270319985441,"score_spread":0.27674767653510374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399452441","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0126134,0.028157094,0.9519025,0.0017486144,0.00376095,0.0011843807,0.00023898619,0.00016865108,0.00022544277],"genre_scores_gemma":[0.5381346,0.023578553,0.09526119,0.00035043515,0.01634931,0.0009025557,0.0007491248,0.00096943683,0.32370484],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9876735,0.0005767925,0.001801504,0.0015503078,0.0036960754,0.0047017974],"domain_scores_gemma":[0.994971,0.0011290715,0.0009707944,0.00083539507,0.0017071078,0.00038665815],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011248045,0.000677076,0.001112378,0.0011666508,0.0006402345,0.0013500509,0.0026210095,0.00051816803,0.00014066136],"category_scores_gemma":[0.0030241099,0.00051189546,0.0010137442,0.0007263587,0.00018999264,0.00026217592,0.002216902,0.014964615,0.00028602517],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00011727376,0.00024219966,0.00003391056,0.00002006623,0.00065577857,0.00003880047,0.0002651927,0.0017571112,0.00030765735,0.0010690454,0.0011512437,0.99434173],"study_design_scores_gemma":[0.0020783632,0.0013915647,0.00014336659,0.00026905062,0.00012364276,0.00064584846,0.011240931,0.09869276,0.0005509637,0.84900934,0.034998346,0.0008558173],"about_ca_topic_score_codex":0.00005646952,"about_ca_topic_score_gemma":0.00017630671,"teacher_disagreement_score":0.9934859,"about_ca_system_score_codex":0.0042277155,"about_ca_system_score_gemma":0.006825887,"threshold_uncertainty_score":0.99973327},"labels":[],"label_agreement":null},{"id":"W4399486984","doi":"10.1109/tnnls.2024.3373749","title":"Off-Policy Prediction Learning: An Empirical Study of Online Algorithms","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"DeepMind; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Machine learning; Artificial intelligence; Empirical research; Algorithm; Mathematics; Statistics","score_opus":0.09340242677426551,"score_gpt":0.42801860975608086,"score_spread":0.33461618298181534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399486984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46723002,0.00078882946,0.52947205,0.00015687894,0.0015113265,0.00051848695,0.000021492464,0.00027282754,0.000028068785],"genre_scores_gemma":[0.9951555,0.0001688565,0.00004962661,0.000013293851,0.0008075853,0.000046516918,0.000008019598,0.000048705428,0.0037018892],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99445766,0.0017945841,0.000923955,0.00088650157,0.0014899703,0.00044732718],"domain_scores_gemma":[0.99703777,0.0018518617,0.00016936738,0.0003934352,0.00027901572,0.00026854244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020328497,0.0002793233,0.00051247794,0.00087054604,0.0006397011,0.0005285898,0.00034986917,0.00018619157,0.00004339329],"category_scores_gemma":[0.0001765909,0.00020855556,0.0001311642,0.001993496,0.0001479665,0.00058047986,0.0000083263085,0.0020549071,0.000013452684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005313836,0.0002876486,0.00084903324,0.000012780583,0.00004234428,0.000024844194,0.0010496307,0.75909466,0.000019055919,0.0000013812637,0.000059207585,0.2385063],"study_design_scores_gemma":[0.0004809122,0.003249633,0.0022797096,0.00006717521,0.00002992663,0.00007626433,0.0065704295,0.9823655,0.0000066308908,0.000014544745,0.0046879454,0.00017134225],"about_ca_topic_score_codex":0.00028548972,"about_ca_topic_score_gemma":0.00007008317,"teacher_disagreement_score":0.52942246,"about_ca_system_score_codex":0.00007729546,"about_ca_system_score_gemma":0.00007404546,"threshold_uncertainty_score":0.8927663},"labels":[],"label_agreement":null},{"id":"W4399688013","doi":"10.1145/3673660.3655074","title":"Online Conversion with Switching Costs: Robust and Learning-Augmented Algorithms","year":2024,"lang":"en","type":"article","venue":"ACM SIGMETRICS Performance Evaluation Review","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Universitas Brawijaya","keywords":"Computer science; Online algorithm; Purchasing; Maximization; Competitive analysis; Function (biology); Minification; Time horizon; Intersection (aeronautics); Baseline (sea); Benchmark (surveying); Mathematical optimization; Algorithm; Mathematics; Economics","score_opus":0.19324229646391108,"score_gpt":0.45433722490865697,"score_spread":0.2610949284447459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399688013","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2177005,0.594833,0.17458428,0.0061478135,0.0011751741,0.004243607,0.0000420726,0.0004185754,0.00085497723],"genre_scores_gemma":[0.39482087,0.56162715,0.037829682,0.0013487099,0.00047300544,0.00027989323,0.00032902992,0.0001254802,0.0031661731],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919566,0.00069781416,0.00090288604,0.0009403543,0.005072608,0.00042973057],"domain_scores_gemma":[0.9932671,0.0036097034,0.00030246092,0.00087254867,0.001739742,0.00020841195],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017163066,0.00029209157,0.0005373379,0.001268525,0.00044138427,0.0004690802,0.00083538477,0.00008987322,0.0010074071],"category_scores_gemma":[0.023574684,0.0001914881,0.00008759495,0.0078940205,0.00010872411,0.001494931,0.0004113133,0.00090016634,0.00046926187],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001445437,0.000041483185,0.0018102963,0.0005022275,0.000030234503,0.000009026334,0.000066691726,0.0031973524,0.000013741842,0.000009416299,0.0018143632,0.9924907],"study_design_scores_gemma":[0.00071075076,0.00047868004,0.0055437293,0.0034139454,0.0001420822,0.00006529512,0.00026176375,0.9053827,0.00007781352,0.00013120112,0.083452806,0.00033925823],"about_ca_topic_score_codex":0.000012708567,"about_ca_topic_score_gemma":0.000004711107,"teacher_disagreement_score":0.99215144,"about_ca_system_score_codex":0.00044194597,"about_ca_system_score_gemma":0.00035256112,"threshold_uncertainty_score":0.9999058},"labels":[],"label_agreement":null},{"id":"W4401813859","doi":"10.1007/s10107-024-02130-y","title":"Machine learning augmented branch and bound for mixed integer linear programming","year":2024,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canada Excellence Research Chairs, Government of Canada; Horizon 2020 Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Government of Canada; Polytechnique Montréal","keywords":"Integer programming; Mathematics; Branch and bound; Branch and cut; Branch and price; Linear programming; Integer (computer science); Mathematical optimization; Numerical analysis; Computer science; Mathematical analysis","score_opus":0.09935322029303427,"score_gpt":0.4338918460942113,"score_spread":0.334538625801177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401813859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076703005,0.0019658797,0.9871525,0.0008860202,0.00023805862,0.0014210591,0.0000091999555,0.0004330818,0.0002238632],"genre_scores_gemma":[0.69011396,0.00002660469,0.29966635,0.000041870844,0.00042614312,0.0007866555,0.000034145105,0.00014259048,0.008761718],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99584675,0.00016398843,0.00087992137,0.00088234677,0.0013974812,0.00082951254],"domain_scores_gemma":[0.9944247,0.0045153396,0.000107924134,0.0003755609,0.00028826456,0.0002882086],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004689695,0.00029953118,0.000517189,0.00039072704,0.00043499598,0.0017086942,0.00046546198,0.00013872139,0.00021498429],"category_scores_gemma":[0.008875505,0.00020760343,0.00020946335,0.0010583197,0.0003565878,0.0004855813,0.00034305966,0.000633122,0.00026026333],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039693074,0.000110849796,0.00010606727,0.00038320696,0.000056966714,0.00002915133,0.0008313985,0.00007751289,0.00014426172,0.0051239044,0.00013173233,0.9929653],"study_design_scores_gemma":[0.0004926023,0.00033188905,0.000013745005,0.00026521066,0.000034931167,0.00007378535,0.0007277663,0.5682186,0.00045551444,0.12410764,0.30496255,0.0003158214],"about_ca_topic_score_codex":0.000006136193,"about_ca_topic_score_gemma":0.000008477436,"teacher_disagreement_score":0.99264944,"about_ca_system_score_codex":0.00007729228,"about_ca_system_score_gemma":0.00006374123,"threshold_uncertainty_score":0.99947315},"labels":[],"label_agreement":null},{"id":"W4401879294","doi":"10.1109/tnet.2024.3444593","title":"Game-Theoretic Bandits for Network Optimization With High-Probability Swap-Regret Upper Bounds","year":2024,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Networking","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Regret; Swap (finance); Computer science; Mathematical optimization; Mathematical economics; Upper and lower bounds; Mathematics; Economics; Machine learning","score_opus":0.0798903136994101,"score_gpt":0.37092698617727515,"score_spread":0.291036672477865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401879294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002726146,0.00059238664,0.98931193,0.0011630827,0.004328113,0.0011490675,0.00007120568,0.00038054824,0.00027752045],"genre_scores_gemma":[0.92172533,0.00019077028,0.073547654,0.00014473098,0.0019479749,0.0004170436,0.000033819462,0.00012314471,0.0018695431],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946058,0.0003502157,0.00083992846,0.001406179,0.0017427794,0.0010551079],"domain_scores_gemma":[0.99270195,0.0049942844,0.00015341285,0.0014005022,0.00048929156,0.00026055545],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0028928118,0.00043856882,0.0005334827,0.00046769704,0.0008473676,0.0011075127,0.0010262628,0.00024817552,0.00056267955],"category_scores_gemma":[0.00020184147,0.00032288476,0.00030256147,0.0029474809,0.00048700674,0.00071101903,0.000015103955,0.0007317307,0.000109591456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003209011,0.00006393555,0.00006017033,0.00003310445,0.0000783832,0.0000129758655,0.00014847972,0.90580064,0.0000054447187,0.0005257528,0.00096237956,0.09198785],"study_design_scores_gemma":[0.0009284607,0.0006090906,0.000083024934,0.00048030072,0.000107429245,0.000038045284,0.000073025585,0.78214055,0.00039972807,0.1856615,0.028899787,0.0005790685],"about_ca_topic_score_codex":0.000015262916,"about_ca_topic_score_gemma":0.00009403623,"teacher_disagreement_score":0.9189992,"about_ca_system_score_codex":0.00036300614,"about_ca_system_score_gemma":0.00026347916,"threshold_uncertainty_score":0.9999294},"labels":[],"label_agreement":null},{"id":"W4402027991","doi":"10.2139/ssrn.4939739","title":"Efficient Task Scheduling in Cloud Computing Using a Cnn-Enhanced Sine Cosine Harris Hawk Optimization Algorithm","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"","keywords":"Cloud computing; Computer science; Trigonometric functions; Sine; Algorithm; Scheduling (production processes); Discrete cosine transform; Mathematical optimization; Artificial intelligence; Mathematics; Operating system; Geometry","score_opus":0.04720138436569951,"score_gpt":0.39270563365660033,"score_spread":0.34550424929090084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402027991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10364308,0.0098236,0.88276565,0.0005311739,0.0023524705,0.00067951134,0.00003276725,0.00010123956,0.000070507944],"genre_scores_gemma":[0.86076796,0.0013085908,0.13437901,0.000050309074,0.0026263427,0.00001526517,0.000035877827,0.00017763223,0.00063901214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.986326,0.000830212,0.0024674144,0.0017930927,0.0039062074,0.0046770917],"domain_scores_gemma":[0.99529225,0.0008212159,0.0012677173,0.00091526343,0.0013850398,0.00031851258],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.017284997,0.0007546455,0.0012285798,0.0024632597,0.0006115356,0.0015888332,0.002056542,0.00055412523,0.00011346282],"category_scores_gemma":[0.0022799007,0.0006533816,0.0004921995,0.0030271544,0.00022959514,0.00019935075,0.0026027241,0.013883783,0.00013153341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000059828857,0.000111460235,0.000015715395,0.000024559848,0.000114953364,0.00006730282,0.00038500322,0.9037488,0.00031852868,0.00021540013,0.000014441916,0.094923995],"study_design_scores_gemma":[0.00092591596,0.00012596851,0.000010946909,0.0007448544,0.000045672423,0.00036104396,0.0016812867,0.87700427,0.00021772432,0.11828788,0.00004210851,0.00055230496],"about_ca_topic_score_codex":0.00014934418,"about_ca_topic_score_gemma":0.00016126459,"teacher_disagreement_score":0.7571249,"about_ca_system_score_codex":0.007104756,"about_ca_system_score_gemma":0.009155537,"threshold_uncertainty_score":0.99959177},"labels":[],"label_agreement":null},{"id":"W4402158975","doi":"10.1109/icc51166.2024.10623091","title":"Online Optimization for Network Resource Allocation and Comparison with Reinforcement Learning Techniques","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Resource allocation; Resource management (computing); Resource (disambiguation); Artificial intelligence; Distributed computing; Computer network","score_opus":0.08962090951805965,"score_gpt":0.4361140075983547,"score_spread":0.34649309808029505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402158975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040331803,0.00029203374,0.9965726,0.0010960023,0.000030268862,0.00047429855,0.0000013060583,0.00019536287,0.0009347875],"genre_scores_gemma":[0.27837008,0.000089875466,0.7030767,0.00012246128,0.00035795133,0.000113506496,0.00012646063,0.00003403639,0.01770893],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983292,0.000061987324,0.0003417037,0.00036363,0.000692517,0.00021095143],"domain_scores_gemma":[0.9984914,0.0009526976,0.000068715184,0.00017672675,0.00024931537,0.00006114934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014352719,0.00009434725,0.00015207595,0.00017552054,0.00019068301,0.0003693638,0.00016314654,0.000047427195,0.000112245296],"category_scores_gemma":[0.00046365877,0.000060126753,0.000022611574,0.0006466854,0.00006679102,0.00031390504,0.000081138875,0.00015421322,0.000005930411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004566037,0.000009508681,0.00013656588,0.000008714026,0.0000075317002,6.989887e-7,0.00010465134,0.875971,0.000012988085,0.0006608339,0.0036758357,0.119366005],"study_design_scores_gemma":[0.00010149012,0.00029944204,0.00003971742,0.00004388716,0.000004789165,0.0000028227005,0.00043243577,0.8502237,0.00048375738,0.00075804995,0.14753222,0.00007765336],"about_ca_topic_score_codex":0.0000071768286,"about_ca_topic_score_gemma":0.000020499305,"teacher_disagreement_score":0.29349592,"about_ca_system_score_codex":0.0000458254,"about_ca_system_score_gemma":0.00004186659,"threshold_uncertainty_score":0.35617837},"labels":[],"label_agreement":null},{"id":"W4402177679","doi":"10.1007/978-3-031-71033-9_23","title":"Matroid Bayesian Online Selection","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Matroid; Selection (genetic algorithm); Bayesian probability; Artificial intelligence; Machine learning; Mathematics; Discrete mathematics","score_opus":0.055674133154967324,"score_gpt":0.3871011574410021,"score_spread":0.33142702428603477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402177679","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000044733653,0.000720092,0.9911602,0.0014092368,0.0023795087,0.0003770136,0.000041186915,0.0001495247,0.0037184902],"genre_scores_gemma":[0.14214747,0.00023763264,0.75690216,0.0020834825,0.007973533,0.000032567896,0.00005307604,0.00032526164,0.090244815],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915204,0.0000481252,0.0009050429,0.0023101943,0.0043898625,0.00082635117],"domain_scores_gemma":[0.9959714,0.0016346447,0.000249687,0.0011725151,0.0007138847,0.0002579036],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025966158,0.00052053906,0.0006441081,0.0027265328,0.0002901179,0.001201931,0.0030668299,0.00038171088,0.0005579578],"category_scores_gemma":[0.0009726637,0.00039212705,0.00021204705,0.0022969877,0.001077477,0.0005611827,0.0012823897,0.0017814395,0.0009020692],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013326846,0.000025182291,0.000034018143,0.00001756269,0.000009911858,0.00014607857,0.00018612298,0.07798156,0.00011588924,0.001838201,0.00021607689,0.91941607],"study_design_scores_gemma":[0.00009405409,0.00012860254,0.000056912904,0.00014190354,0.000004880616,0.00009798406,4.4308933e-7,0.43834868,0.00038274212,0.54687095,0.013534934,0.00033788927],"about_ca_topic_score_codex":0.000019225225,"about_ca_topic_score_gemma":0.00043619107,"teacher_disagreement_score":0.9190782,"about_ca_system_score_codex":0.0006089478,"about_ca_system_score_gemma":0.00072144775,"threshold_uncertainty_score":0.99987584},"labels":[],"label_agreement":null},{"id":"W4403321765","doi":"10.1007/s11432-023-4086-5","title":"Improved dynamic regret of distributed online multiple Frank-Wolfe convex optimization","year":2024,"lang":"en","type":"article","venue":"Science China Information Sciences","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Computer science; Regular polygon; Mathematical optimization; Mathematics; Machine learning; Geometry","score_opus":0.04907183590157569,"score_gpt":0.41944849127908757,"score_spread":0.37037665537751185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403321765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08207818,0.00017946157,0.913223,0.0012948761,0.001233065,0.00049127196,0.0005393353,0.00016169822,0.0007991054],"genre_scores_gemma":[0.9738846,0.00006441535,0.025715534,0.000066754284,0.000033342367,0.000014497608,0.00007719261,0.000005742101,0.00013794353],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923412,0.000094258234,0.0013557416,0.000670734,0.0048765196,0.0006615121],"domain_scores_gemma":[0.9963303,0.00095078006,0.0004881277,0.0006363839,0.0013517808,0.000242579],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.009440686,0.00021989094,0.00033741636,0.0020420905,0.0009261813,0.0018985438,0.0028511956,0.000086768414,0.00035224177],"category_scores_gemma":[0.01273531,0.00014641293,0.00011715353,0.013477808,0.0042476133,0.0143007515,0.0004543095,0.0002898544,0.00013415593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049448023,0.00009891127,0.0014377922,0.000069453934,0.000011912885,0.0000032884116,0.004148272,0.77278435,0.003931997,0.0016876756,0.00096567377,0.2148112],"study_design_scores_gemma":[0.00022566304,0.0001598519,0.0061709583,0.000046130346,0.0000031431996,0.000011551577,0.0021901669,0.9841859,0.0022684576,0.0026347272,0.0019171112,0.00018634935],"about_ca_topic_score_codex":0.00008483313,"about_ca_topic_score_gemma":0.000025180005,"teacher_disagreement_score":0.8918064,"about_ca_system_score_codex":0.00019427665,"about_ca_system_score_gemma":0.0013547455,"threshold_uncertainty_score":0.99948573},"labels":[],"label_agreement":null},{"id":"W4403712928","doi":"10.2139/ssrn.4997308","title":"Diversified Learning: Bayesian Control with Multiple Biased Information Sources","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayesian probability; Control (management); Computer science; Bayesian inference; Econometrics; Artificial intelligence; Machine learning; Economics","score_opus":0.029570063751934193,"score_gpt":0.33137014164052725,"score_spread":0.30180007788859303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403712928","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089374736,0.002831468,0.9022487,0.002656069,0.00085885386,0.0008429778,0.00006270031,0.00020385618,0.0009206734],"genre_scores_gemma":[0.9943391,0.0007125978,0.00034989882,0.00006229406,0.0004943857,0.000028690683,0.00003096831,0.000044930137,0.0039371164],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9910522,0.0005843717,0.0010481392,0.0006488799,0.0037048631,0.002961555],"domain_scores_gemma":[0.9958385,0.001301982,0.0009411931,0.0005960964,0.0010341317,0.0002880632],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009145707,0.000465477,0.00066963176,0.001439707,0.0006470574,0.0019421784,0.0018332896,0.00034916587,0.00017397788],"category_scores_gemma":[0.003526781,0.00030997366,0.000366867,0.00085782836,0.00021263876,0.0008201322,0.00082614046,0.013470738,0.0007681501],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028280276,0.00016058618,0.021676928,0.00010393293,0.002045443,0.00015046213,0.0055849724,0.5220098,0.00006425637,0.0040505608,0.0019462344,0.4393788],"study_design_scores_gemma":[0.0048592854,0.0013091039,0.0010154785,0.00023890036,0.00015055318,0.00062838255,0.024467472,0.19235657,0.0001201977,0.7486276,0.025228642,0.0009978355],"about_ca_topic_score_codex":0.00016427587,"about_ca_topic_score_gemma":0.0008143458,"teacher_disagreement_score":0.9049644,"about_ca_system_score_codex":0.0016754011,"about_ca_system_score_gemma":0.006765695,"threshold_uncertainty_score":0.9999352},"labels":[],"label_agreement":null},{"id":"W4403918350","doi":"10.1109/sm63044.2024.10733530","title":"A Contextual Multi-armed Bandit Approach to Personalized Trip Itinerary Planning","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"General Motors (Canada); University of Toronto","funders":"","keywords":"Computer science; Operations research; Artificial intelligence; Engineering","score_opus":0.31925255590611645,"score_gpt":0.49861399214305346,"score_spread":0.179361436236937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403918350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010257182,0.0015129874,0.9586776,0.0010369337,0.0005128447,0.0006646174,0.000058673613,0.00036246778,0.026916705],"genre_scores_gemma":[0.65923494,0.000011342698,0.09894297,0.0010540754,0.00067934324,0.00023399164,0.00003452421,0.00007069003,0.2397381],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99503016,0.00024423917,0.00061379035,0.0011081449,0.0023237308,0.00067993137],"domain_scores_gemma":[0.9963675,0.002394513,0.000044478635,0.00050938776,0.00025751864,0.00042660945],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027333107,0.0002453716,0.0004228601,0.0008127883,0.00022950217,0.0008857555,0.00094275386,0.00010566133,0.0021471474],"category_scores_gemma":[0.0034079337,0.00016017907,0.00016562552,0.0019056356,0.0001880986,0.0005730904,0.00030569168,0.00042160958,0.0025065925],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009428779,0.000686097,0.00081053504,0.000103505554,0.00027547125,0.0010492697,0.024158526,0.009153832,0.0069584646,0.009601294,0.5564799,0.38978022],"study_design_scores_gemma":[0.0025716498,0.00025591793,0.0013077515,0.0000808744,0.000016942668,0.00012853819,0.011674559,0.5498037,0.0011059016,0.0028386437,0.42955536,0.0006602005],"about_ca_topic_score_codex":0.000024344918,"about_ca_topic_score_gemma":0.0000031516513,"teacher_disagreement_score":0.8597346,"about_ca_system_score_codex":0.00009953791,"about_ca_system_score_gemma":0.00020412466,"threshold_uncertainty_score":0.99876505},"labels":[],"label_agreement":null},{"id":"W4404342998","doi":"10.48550/arxiv.2410.23029","title":"Risk-Aware Decision Making in Restless Bandits: Theory and Algorithms for Planning and Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Institut de Valorisation des Données","keywords":"Computer science; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.1995701599587951,"score_gpt":0.36146541367314483,"score_spread":0.16189525371434973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404342998","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42383602,0.0013501465,0.57368237,0.000021788643,0.00033482758,0.00045960772,0.00008523448,0.000068163696,0.00016185122],"genre_scores_gemma":[0.99472004,0.0005062266,0.0028601536,0.000014177639,0.00013094404,0.0000054727334,0.000010742305,0.00004936488,0.0017028495],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955611,0.00094049214,0.0004983265,0.0020171942,0.00043657434,0.0005462885],"domain_scores_gemma":[0.98543036,0.013093314,0.00036829914,0.0006396015,0.00028548986,0.00018296258],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0074198097,0.00038457388,0.00063115754,0.0014510355,0.00046205882,0.0005263821,0.00086799625,0.00042689542,0.000039316827],"category_scores_gemma":[0.0057951235,0.00035580908,0.00014632424,0.0010254795,0.0003189028,0.0003212943,0.0034793285,0.0022000202,0.000027448474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012472585,0.00004612645,0.036029354,0.00020498424,0.00010483798,0.0012611453,0.0023797965,0.7844131,0.0000058756787,0.005664194,0.0003032584,0.16834007],"study_design_scores_gemma":[0.0005761408,0.0000672892,0.006535707,0.0006398101,0.000039329614,0.000009038597,0.0028148291,0.4673073,0.0000078014045,0.52108353,0.00060238637,0.00031680104],"about_ca_topic_score_codex":0.000043254357,"about_ca_topic_score_gemma":0.00007304913,"teacher_disagreement_score":0.57088405,"about_ca_system_score_codex":0.00021460204,"about_ca_system_score_gemma":0.0001562346,"threshold_uncertainty_score":0.9998894},"labels":[],"label_agreement":null},{"id":"W4405974431","doi":"10.1109/pimrc59610.2024.10817426","title":"Edge Selection Non-Cooperative Game in IoT Edge Computing","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Edge computing; Selection (genetic algorithm); Internet of Things; Human–computer interaction; Artificial intelligence; Computer security","score_opus":0.10095882738346541,"score_gpt":0.46636873714286897,"score_spread":0.3654099097594036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405974431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.121888705,0.00031449518,0.8573077,0.0008380197,0.0009666215,0.00040424356,0.0000047124945,0.0001721562,0.018103393],"genre_scores_gemma":[0.97570914,0.0000077768,0.0038734507,0.000080583864,0.00030898736,0.000009654196,0.000001622198,0.000016213196,0.019992564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971955,0.00016737761,0.0004757977,0.00066844,0.0010792172,0.0004136565],"domain_scores_gemma":[0.99768895,0.0016329167,0.000032558233,0.0002262459,0.0003210633,0.00009828268],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0022229156,0.00013840554,0.00023437715,0.00069222855,0.00010965383,0.00055350515,0.00042483592,0.00007979197,0.0014128544],"category_scores_gemma":[0.0012831723,0.00009568829,0.00006371988,0.0033001078,0.000092636015,0.00039190514,0.0002080924,0.00046308417,0.0024700095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005292922,0.00015450334,0.00334388,0.00002517381,0.000033111675,0.0001914138,0.005120564,0.057551656,0.0064186803,0.0022892714,0.038771663,0.8860472],"study_design_scores_gemma":[0.00025207788,0.00010243136,0.0057527553,0.000042872907,0.0000013336648,0.000020852034,0.0007410084,0.96084803,0.0075702784,0.0045096274,0.019984793,0.0001739642],"about_ca_topic_score_codex":0.0000730865,"about_ca_topic_score_gemma":0.00028509847,"teacher_disagreement_score":0.90329635,"about_ca_system_score_codex":0.00020019109,"about_ca_system_score_gemma":0.00020837216,"threshold_uncertainty_score":0.9995},"labels":[],"label_agreement":null},{"id":"W4406033644","doi":"10.1287/opre.2021.0445","title":"Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback","year":2025,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Monotone polygon; Computer science; Mathematical optimization; Online learning; Mathematical economics; Operations research; Mathematics; Multimedia; Machine learning","score_opus":0.13094003215085015,"score_gpt":0.4967886970957619,"score_spread":0.36584866494491175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406033644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91012293,0.00044719214,0.06828206,0.0066633765,0.00017546405,0.0016500375,0.00007939858,0.00009507373,0.0124844685],"genre_scores_gemma":[0.81883943,0.00010665399,0.01594081,0.00002873793,0.00015425742,0.0002399601,0.00007421832,0.00002960339,0.1645863],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9927244,0.0010853088,0.0007218516,0.0010152342,0.0034394325,0.0010137522],"domain_scores_gemma":[0.99380004,0.0020047375,0.00003740195,0.0009623161,0.0029828472,0.00021267991],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0056183697,0.00022310179,0.0004107132,0.0022192777,0.0009160912,0.0012450446,0.001413979,0.00014473584,0.0017187184],"category_scores_gemma":[0.0073364717,0.00015983664,0.00006585428,0.0057356814,0.00065440574,0.0010027295,0.0006266047,0.0019077084,0.0012087555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043190506,0.00036460036,0.008941095,0.000009515364,0.000030564035,0.00007209141,0.00048474423,0.953804,0.0008446257,0.00069471454,0.004533287,0.02978885],"study_design_scores_gemma":[0.0033351018,0.000913176,0.041373443,0.0001698528,0.0000050692133,0.000011995296,0.0063447854,0.88103634,0.0016140523,0.00045029007,0.06435054,0.0003953791],"about_ca_topic_score_codex":0.00059353234,"about_ca_topic_score_gemma":0.004296392,"teacher_disagreement_score":0.15210183,"about_ca_system_score_codex":0.00035317318,"about_ca_system_score_gemma":0.0011925889,"threshold_uncertainty_score":0.99979174},"labels":[],"label_agreement":null},{"id":"W4406610289","doi":"10.1109/tac.2025.3532181","title":"Model Approximation in MDPs With Unbounded Per-Step Cost","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Innovation for Defence Excellence and Security","keywords":"Computer science; Mathematical optimization; Mathematics; Applied mathematics","score_opus":0.05376352359343873,"score_gpt":0.3732842671564823,"score_spread":0.31952074356304355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406610289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01110723,0.000017381464,0.9847388,0.0012180463,0.00018897979,0.0014598243,0.000037882754,0.00015305051,0.0010787853],"genre_scores_gemma":[0.9771931,0.0000045048905,0.01861213,0.00025857534,0.000009277078,0.0005756628,0.0000012543654,0.000018198856,0.0033272582],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967366,0.00026706484,0.0007587632,0.00056671316,0.0012387037,0.00043218944],"domain_scores_gemma":[0.9968254,0.0018552595,0.00013778177,0.00076477736,0.00030893047,0.00010786333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013711385,0.00023239161,0.0004788059,0.0011292907,0.00026845673,0.00026681964,0.00057071866,0.0001155592,0.00027011184],"category_scores_gemma":[0.00018971309,0.00017139592,0.00011538631,0.0016241688,0.00016493883,0.0003942808,0.0000022959914,0.00034690052,0.00022617316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016956478,0.00026749782,0.000024410616,0.000016238228,0.00003793978,0.0000060636453,0.00022038168,0.59581983,0.0002734851,0.0002044613,0.000079253354,0.40288088],"study_design_scores_gemma":[0.003840285,0.000106712614,0.00034168232,0.000075432894,0.000025484542,0.0000052007076,0.0003059525,0.9858029,0.00066744915,0.008536443,0.00012655961,0.00016591146],"about_ca_topic_score_codex":0.000044723194,"about_ca_topic_score_gemma":0.0009539617,"teacher_disagreement_score":0.9661267,"about_ca_system_score_codex":0.00032750927,"about_ca_system_score_gemma":0.00039433557,"threshold_uncertainty_score":0.6989323},"labels":[],"label_agreement":null},{"id":"W4407666409","doi":"10.1051/itmconf/20257301011","title":"Application of Multi-Armed Bandit Algorithm in Quantitative Finance","year":2025,"lang":"en","type":"article","venue":"ITM Web of Conferences","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Algorithm","score_opus":0.1175976055207516,"score_gpt":0.4653464346115648,"score_spread":0.34774882909081317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407666409","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05614067,0.0009773537,0.93575656,0.00048735706,0.0002268171,0.00060015277,0.00008909058,0.000019252713,0.005702728],"genre_scores_gemma":[0.9750097,0.00016410457,0.023793457,0.000014894813,0.000009271947,0.00005851207,0.00000470137,0.0000039467163,0.00094142806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972687,0.00019653131,0.00088959065,0.00044540237,0.0009633766,0.0002364501],"domain_scores_gemma":[0.9958827,0.002312856,0.00040336908,0.0004510832,0.00091656303,0.00003344229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015249881,0.00013088693,0.0004990839,0.00075354875,0.00004465769,0.00003553362,0.000944039,0.00009085649,0.00010835386],"category_scores_gemma":[0.002247974,0.000102138554,0.00007607184,0.0018666895,0.0005561745,0.0002584336,0.00013664216,0.00016921641,0.000031610554],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114470204,0.00035116042,0.044777956,0.000034765566,0.000032052274,0.000004261948,0.0006084769,0.0019808547,0.0029904814,0.034386523,0.0003887152,0.9143303],"study_design_scores_gemma":[0.0019536135,0.00024130326,0.17370865,0.00017460457,0.000009047409,6.8150285e-7,0.0030594498,0.6717855,0.035990037,0.094169065,0.018662905,0.00024515588],"about_ca_topic_score_codex":0.00032653476,"about_ca_topic_score_gemma":0.00050665846,"teacher_disagreement_score":0.918869,"about_ca_system_score_codex":0.000029418396,"about_ca_system_score_gemma":0.0010064901,"threshold_uncertainty_score":0.41650894},"labels":[],"label_agreement":null},{"id":"W4407727497","doi":"10.2139/ssrn.5123355","title":"Online Learning for Dynamic Service Mode Control","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Service (business); Mode (computer interface); Control (management); Process management; Business; Artificial intelligence; Human–computer interaction; Marketing","score_opus":0.044638952952109144,"score_gpt":0.4428699914955502,"score_spread":0.39823103854344105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407727497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011506165,0.0046697278,0.97558445,0.005948353,0.00094799895,0.0008638095,0.0002586528,0.00007542887,0.00014540722],"genre_scores_gemma":[0.90782285,0.007619958,0.006378785,0.00067814556,0.0015413263,0.00017862473,0.00021447073,0.00012435917,0.075441465],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9906719,0.00063817407,0.0013062785,0.0010687672,0.002263227,0.004051709],"domain_scores_gemma":[0.99296427,0.0025763498,0.00094269135,0.0008305599,0.0024742216,0.0002119086],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010171335,0.00047604184,0.00096734107,0.0009881564,0.0006518833,0.0005557473,0.0032416482,0.00045892253,0.00006765533],"category_scores_gemma":[0.0053583444,0.0003838266,0.0005853933,0.0008135414,0.00007645314,0.00028707375,0.0008304848,0.012671356,0.0000611641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004815589,0.00018768845,0.0002052947,0.000050209313,0.00053273316,0.000007741784,0.00020124967,0.7142484,0.00006816174,0.0027854508,0.00023462182,0.2809969],"study_design_scores_gemma":[0.0012844111,0.00016050843,0.00009032122,0.00006765356,0.000048258677,0.00006357483,0.0011480056,0.44890323,0.0000061255882,0.5428687,0.005116712,0.0002425074],"about_ca_topic_score_codex":0.00010367326,"about_ca_topic_score_gemma":0.0052415594,"teacher_disagreement_score":0.9692057,"about_ca_system_score_codex":0.0029359453,"about_ca_system_score_gemma":0.011707148,"threshold_uncertainty_score":0.99986136},"labels":[],"label_agreement":null},{"id":"W4408818067","doi":"10.1016/j.ejor.2025.03.011","title":"The multi-armed bandit problem under the mean-variance setting","year":2025,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Actua; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Variance (accounting); Computer science; Mathematical optimization; Mathematics; Statistics; Econometrics; Economics","score_opus":0.23597087264581235,"score_gpt":0.5101706528117763,"score_spread":0.27419978016596397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408818067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014770206,0.0045847245,0.74995077,0.18640475,0.0014809994,0.0013793552,0.000025325959,0.000026866323,0.041376986],"genre_scores_gemma":[0.91289824,0.00037456217,0.015272261,0.00076658657,0.0010566043,0.0000174902,0.0000023024256,0.000040116596,0.06957184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9839002,0.0077276663,0.0013117146,0.0003857359,0.0060195355,0.0006551803],"domain_scores_gemma":[0.9795485,0.013628357,0.0002764408,0.00066691067,0.0057097925,0.0001700051],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06914407,0.00014068147,0.00020448676,0.0004587345,0.0028429558,0.0021141593,0.0034124604,0.000028227674,0.0002930494],"category_scores_gemma":[0.01746732,0.00006324543,0.00014777579,0.0019114567,0.0008737456,0.00059109356,0.0007124274,0.0017113968,0.0004576506],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010786166,0.00048150937,0.0019211228,0.000022132317,0.000477686,0.00070373167,0.0036369069,0.14391619,0.0072662137,0.07279627,0.42159826,0.34610137],"study_design_scores_gemma":[0.0030277306,0.00043353744,0.055218667,0.00023107967,0.000012789184,0.00020638615,0.009538206,0.036959168,0.0016123593,0.042368177,0.8501132,0.00027870192],"about_ca_topic_score_codex":0.000004694528,"about_ca_topic_score_gemma":0.000029013316,"teacher_disagreement_score":0.89812803,"about_ca_system_score_codex":0.00019590155,"about_ca_system_score_gemma":0.0012898933,"threshold_uncertainty_score":0.99892175},"labels":[],"label_agreement":null},{"id":"W4409365726","doi":"10.1609/aaai.v39i13.33507","title":"Every Bit Helps: Achieving the Optimal Distortion with a Few Queries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bit (key); Distortion (music); Computer science; Arithmetic; Algorithm; Theoretical computer science; Mathematics; Computer security; Telecommunications","score_opus":0.15755457449808338,"score_gpt":0.41326942252001436,"score_spread":0.255714848021931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409365726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7265221,0.00024108078,0.21926169,0.028511923,0.0010585545,0.0018721127,0.00002812963,0.0001547263,0.022349693],"genre_scores_gemma":[0.99469876,0.000043187207,0.0009828429,0.00017877224,0.000073502604,0.0000682221,4.0210008e-7,0.00001318633,0.0039411257],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99618787,0.00006297763,0.00081733556,0.00066116994,0.0018221578,0.00044846698],"domain_scores_gemma":[0.9961916,0.00090494554,0.0005142476,0.0005313517,0.0017795893,0.000078232784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002161511,0.00025757088,0.0003589875,0.00029874523,0.00067894836,0.0006484342,0.0026475305,0.00008987509,0.00019337567],"category_scores_gemma":[0.004952565,0.00012631112,0.00014668985,0.002251963,0.0012713234,0.0006326297,0.00056420837,0.0005509849,0.000129312],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018930457,0.0003998813,0.003597591,0.00008730507,0.00011037179,0.0000030309554,0.0045165042,0.003563253,0.023165163,0.5300729,0.002089544,0.43050137],"study_design_scores_gemma":[0.00011620405,0.0007185385,0.0067786463,0.0010397116,0.000063076775,0.000014227193,0.02192076,0.037569266,0.5659605,0.3604424,0.004769191,0.0006074602],"about_ca_topic_score_codex":0.000060584476,"about_ca_topic_score_gemma":0.00007144841,"teacher_disagreement_score":0.54279536,"about_ca_system_score_codex":0.00010612114,"about_ca_system_score_gemma":0.00028220282,"threshold_uncertainty_score":0.6252866},"labels":[],"label_agreement":null},{"id":"W4410602017","doi":"10.6000/1929-6029.2025.14.28","title":"Response Adaptive Randomization Using Biomarkers with Exponentially Decreasing Probability Sequence","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sequence (biology); Randomization; Exponential growth; Statistics; Mathematics; Computer science; Econometrics; Applied mathematics; Biology; Bioinformatics; Mathematical analysis; Clinical trial; Genetics","score_opus":0.2564553604632724,"score_gpt":0.5629981862205483,"score_spread":0.3065428257572759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410602017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13911285,0.000072696654,0.8569276,0.0029868144,0.00038909973,0.00025017175,0.000039345407,0.000003563482,0.00021790862],"genre_scores_gemma":[0.8100128,0.000098182376,0.18953672,0.000077592435,0.00010948257,0.0000081957805,0.0000033154467,0.000011067237,0.00014261162],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9797202,0.0040585487,0.0014795688,0.00039144565,0.013915625,0.00043461012],"domain_scores_gemma":[0.95659703,0.031833287,0.00040484828,0.00027995557,0.010566847,0.0003180219],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051208243,0.000121635334,0.00036480374,0.0023809678,0.00014196584,0.0003092347,0.0019474467,0.00011769224,0.00053604343],"category_scores_gemma":[0.21698362,0.00008435464,0.000059693124,0.001931188,0.0012101792,0.00046097225,0.00037664283,0.0011086423,0.0000081198],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.18481922,0.0011230482,0.016005307,0.000032959553,0.00067681796,0.010770343,0.0011082514,0.022182252,0.0039934884,0.025398955,0.002923318,0.73096603],"study_design_scores_gemma":[0.013680924,0.00070748094,0.020952974,0.0016785647,0.000015620853,0.0004703812,0.0017888406,0.45975283,0.0012520442,0.49711576,0.0023420623,0.00024254876],"about_ca_topic_score_codex":0.00013617802,"about_ca_topic_score_gemma":0.00018942388,"teacher_disagreement_score":0.7307235,"about_ca_system_score_codex":0.0011462916,"about_ca_system_score_gemma":0.005290315,"threshold_uncertainty_score":0.9769808},"labels":[],"label_agreement":null},{"id":"W4410845474","doi":"10.1017/9780511820809.007","title":"Toppling conjectures","year":2015,"lang":"en","type":"other","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Geology; Geography","score_opus":0.29098476486513714,"score_gpt":0.5337833791020361,"score_spread":0.24279861423689897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410845474","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.473304e-7,0.0011950613,0.056932226,0.00013280276,0.0005288902,0.00020267995,0.000047564172,0.00019741022,0.9407631],"genre_scores_gemma":[0.00002195827,0.0000222413,0.007140825,0.00011125478,0.00074299827,0.000008061647,0.000011269325,0.00021223626,0.99172914],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962169,0.00007990458,0.00028486448,0.00055002526,0.0025702831,0.00029801225],"domain_scores_gemma":[0.998137,0.00043440703,0.00014553589,0.0008377695,0.00025738106,0.00018792429],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012369335,0.0001851347,0.00037614783,0.00062041165,0.0000319833,0.00017424744,0.0010669354,0.00024139327,0.06672503],"category_scores_gemma":[0.002506598,0.00011084773,0.00006629553,0.0005406794,0.00011803291,0.000050137405,0.00026856878,0.0002554035,0.010803131],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024267576,0.000005426744,0.000004649711,0.0000013483802,0.000008383746,0.000012652843,0.000016320208,0.000048411748,0.0000010229819,0.00009172406,0.97812766,0.021679955],"study_design_scores_gemma":[0.00013544013,0.00001699486,0.0000026900411,0.000010294827,0.0000018293543,0.0000042445354,0.00010485375,0.00023505112,0.000023164373,0.01630941,0.9829988,0.00015722078],"about_ca_topic_score_codex":0.000095254734,"about_ca_topic_score_gemma":0.0002730134,"teacher_disagreement_score":0.055921897,"about_ca_system_score_codex":0.00003818339,"about_ca_system_score_gemma":0.00019171833,"threshold_uncertainty_score":0.98996705},"labels":[],"label_agreement":null},{"id":"W4411921768","doi":"10.1137/23m1592559","title":"Unsynchronized Decentralized Q-Learning: Two Timescale Analysis by Persistence","year":2025,"lang":"en","type":"article","venue":"SIAM Journal on Control and Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Toronto","funders":"","keywords":"Persistence (discontinuity); Mathematics; Q-learning; Artificial intelligence; Computer science; Engineering; Geotechnical engineering","score_opus":0.023443965379088803,"score_gpt":0.36435067225376544,"score_spread":0.3409067068746766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411921768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017662259,0.0018463791,0.99220186,0.0028581412,0.00015806385,0.00017186391,0.000009416698,0.000025668352,0.00096234947],"genre_scores_gemma":[0.97603124,0.0012888585,0.011595421,0.0006262615,0.000081649145,0.000010093372,0.000016879445,0.0000138682535,0.010335741],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969326,0.00061166554,0.0005983423,0.00041128113,0.0010967602,0.00034930164],"domain_scores_gemma":[0.9973791,0.0011893888,0.00030521586,0.00022334246,0.00068621384,0.00021669483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019849706,0.00016444114,0.00046614945,0.0007814349,0.00059906364,0.00067438895,0.0003794504,0.00007540995,0.00081575516],"category_scores_gemma":[0.0025084403,0.00011747927,0.00022009204,0.0020669424,0.0001193307,0.0003996379,0.000042905212,0.0004180418,0.00002317717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030521012,0.00005096601,0.0029848898,0.00000124606,0.00024481417,0.000008384911,0.00004974774,0.9751493,0.00009550466,0.00006430805,0.0016378859,0.019407755],"study_design_scores_gemma":[0.0046969904,0.00013441441,0.0010189803,0.000015954283,0.00019009024,0.000008490541,0.00018407218,0.9846611,0.000059197377,0.0008716692,0.008030058,0.0001289929],"about_ca_topic_score_codex":0.000004018386,"about_ca_topic_score_gemma":0.0000051119946,"teacher_disagreement_score":0.9806065,"about_ca_system_score_codex":0.00011629365,"about_ca_system_score_gemma":0.00011510824,"threshold_uncertainty_score":0.89319474},"labels":[],"label_agreement":null},{"id":"W4411946019","doi":"10.1145/3736252.3742659","title":"No-Regret Incentive-Compatible Online Learning under Exact Truthfulness with Non-Myopic Experts","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Leonard N. Stern School of Business, New York University","keywords":"Regret; Incentive; Computer science; Incentive compatibility; Machine learning; Microeconomics; Economics","score_opus":0.06397387203485884,"score_gpt":0.4264049429812383,"score_spread":0.3624310709463795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411946019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2854987,0.00009664955,0.6814582,0.00093929836,0.00047582568,0.00041093802,0.0000073423066,0.0001464747,0.030966576],"genre_scores_gemma":[0.8480699,0.00002009706,0.0065900004,0.0002981837,0.00011057775,0.00003733655,0.000016509479,0.000023988223,0.1448334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958623,0.0002633277,0.0004936942,0.0008791215,0.0018895073,0.00061204855],"domain_scores_gemma":[0.99580836,0.0024095648,0.00015460004,0.0007685683,0.0006880859,0.00017078865],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009489061,0.00027437042,0.00048441134,0.00064501545,0.00041317855,0.00036502496,0.0010541974,0.00010329751,0.002623148],"category_scores_gemma":[0.0017131398,0.00016773675,0.000093080555,0.002240336,0.00027351518,0.00069045456,0.00038246615,0.0004491385,0.0005345344],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014291246,0.0017611104,0.17136219,0.00008535283,0.0003948522,0.00024326555,0.001907118,0.06836362,0.0018850893,0.0028484103,0.047583994,0.70213586],"study_design_scores_gemma":[0.009460871,0.0015018268,0.17097734,0.0005233167,0.000046746358,0.00003201874,0.030389989,0.37286994,0.021828376,0.022876414,0.36755618,0.001936995],"about_ca_topic_score_codex":0.00012320736,"about_ca_topic_score_gemma":0.00025698807,"teacher_disagreement_score":0.7001989,"about_ca_system_score_codex":0.00014837427,"about_ca_system_score_gemma":0.00025715478,"threshold_uncertainty_score":0.9982886},"labels":[],"label_agreement":null},{"id":"W4411950882","doi":"10.1109/infocom55648.2025.11044606","title":"Faster Convergence for Unknown-Game Bandits","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Convergence (economics); Computer science; Mathematical optimization; Artificial intelligence; Mathematics; Economics","score_opus":0.15792765889689803,"score_gpt":0.519286465163955,"score_spread":0.361358806267057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411950882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036835265,0.00011444843,0.97138387,0.0023570121,0.00097233936,0.00046471698,0.000016989068,0.000054542077,0.020952566],"genre_scores_gemma":[0.51267684,0.000017124466,0.008419479,0.0008535975,0.00011608245,0.00010365573,0.000003746063,0.000010617229,0.47779888],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976724,0.00006558901,0.00043647387,0.00053596875,0.0009019687,0.00038763348],"domain_scores_gemma":[0.9962252,0.0023860638,0.00005995548,0.0005792008,0.00065027195,0.0000993285],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013328913,0.00011560002,0.00022806086,0.00033284613,0.00012667506,0.00018490938,0.0009046202,0.00006844989,0.0025367637],"category_scores_gemma":[0.0035020367,0.0000765719,0.000111084715,0.0010023224,0.00013471181,0.00034448414,0.00022715768,0.000106912354,0.0009959005],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026787497,0.00015552757,0.004946495,0.000031978645,0.00006720164,0.000012463491,0.00031000635,0.0015762545,0.0014721636,0.058087222,0.4368219,0.4962509],"study_design_scores_gemma":[0.0007693953,0.00006851097,0.002678969,0.000011558908,0.000004306038,0.000001443796,0.0002447619,0.033503298,0.010189674,0.14103042,0.8113466,0.00015104968],"about_ca_topic_score_codex":0.000006411621,"about_ca_topic_score_gemma":0.000039250568,"teacher_disagreement_score":0.96296436,"about_ca_system_score_codex":0.000042105385,"about_ca_system_score_gemma":0.00013902533,"threshold_uncertainty_score":0.99978197},"labels":[],"label_agreement":null},{"id":"W4413143600","doi":"10.1016/j.automatica.2025.112499","title":"Distributed mirror descent for online bandit saddle point problem","year":2025,"lang":"en","type":"article","venue":"Automatica","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Saddle point; Descent (aeronautics); Saddle; Computer science; Mathematical optimization; Point (geometry); Mathematics; Control theory (sociology); Distributed computing; Artificial intelligence; Engineering; Geometry; Control (management); Aerospace engineering","score_opus":0.10802154007385688,"score_gpt":0.46627725848189344,"score_spread":0.35825571840803655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413143600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022206996,0.00013554223,0.96139354,0.012034879,0.00037979535,0.0018362259,0.0008294301,0.00029945697,0.00088412],"genre_scores_gemma":[0.50027466,0.000016340355,0.47767088,0.0008214907,0.00011813057,0.00057875755,0.00039690905,0.000051692896,0.020071121],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968393,0.00012198614,0.0008494235,0.0005551641,0.001079206,0.00055495114],"domain_scores_gemma":[0.99579173,0.0025136808,0.00016443976,0.0007820253,0.0005938379,0.00015427277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014890322,0.00018483354,0.00041619557,0.00031471538,0.0002583589,0.00023801751,0.00092809426,0.000093685114,0.00049977197],"category_scores_gemma":[0.005245214,0.00013255018,0.00016746945,0.0012309318,0.00015229757,0.000255587,0.00027568368,0.00017148507,0.0002896986],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042927827,0.0026169114,0.0020980418,0.00039484692,0.00034630377,0.000060124712,0.0007930165,0.001287559,0.0032321445,0.011898098,0.47897595,0.49786773],"study_design_scores_gemma":[0.002482706,0.00030989174,0.030136507,0.000209282,0.00004365306,0.0000091503925,0.00061519165,0.36789882,0.0057218173,0.36379823,0.22835669,0.00041804468],"about_ca_topic_score_codex":0.000012476503,"about_ca_topic_score_gemma":0.00007462293,"teacher_disagreement_score":0.4974497,"about_ca_system_score_codex":0.0001699666,"about_ca_system_score_gemma":0.00023881155,"threshold_uncertainty_score":0.627939},"labels":[],"label_agreement":null},{"id":"W4414165913","doi":"10.1109/tcns.2025.3608004","title":"One-Point Sampling for Distributed Bandit Convex Optimization With Time-Varying Constraints","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Regret; Sublinear function; Upper and lower bounds; Convex function; Constraint (computer-aided design); Convex optimization; Benchmark (surveying); Projection (relational algebra)","score_opus":0.05865261333941649,"score_gpt":0.3494235832352155,"score_spread":0.290770969895799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414165913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001238087,0.00020387223,0.99551046,0.00030969386,0.0009877228,0.0019514174,0.0005766391,0.00008423556,0.0002521297],"genre_scores_gemma":[0.9894567,0.000013937009,0.009359595,0.000057907557,0.00015908205,0.00031387448,0.000023334718,0.000026855954,0.00058871583],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639827,0.00030445136,0.0011208488,0.00060706126,0.0010393173,0.00053003634],"domain_scores_gemma":[0.9918698,0.0058161495,0.00043425945,0.00058611773,0.0011590194,0.00013464624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002043708,0.0002463585,0.00085270667,0.00038416378,0.00045161828,0.00022098311,0.00047549352,0.00016284462,0.0001505204],"category_scores_gemma":[0.00020670037,0.00020362223,0.00020237397,0.0012492569,0.0003021648,0.00030699957,0.000002571804,0.0002684405,0.000022125716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009063807,0.000098510645,0.000028700186,0.00003747937,0.0002569436,0.0000016496354,0.000027420154,0.9876174,0.00017090734,0.00009270055,0.00035647347,0.0104054855],"study_design_scores_gemma":[0.004377356,0.00032829746,0.000043520755,0.00045464243,0.00010383427,0.0000067386054,0.00013090539,0.99294096,0.00043509583,0.00044211664,0.0005292601,0.00020724186],"about_ca_topic_score_codex":0.000018426617,"about_ca_topic_score_gemma":0.000011272168,"teacher_disagreement_score":0.9893329,"about_ca_system_score_codex":0.00016014218,"about_ca_system_score_gemma":0.00024744173,"threshold_uncertainty_score":0.83034736},"labels":[],"label_agreement":null},{"id":"W4414213966","doi":"10.1007/s10479-025-06821-3","title":"On the sensitivity of restless bandits solutions to uncertainty in the models of the arms","year":2025,"lang":"en","type":"article","venue":"Annals of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Heuristic; Theory of computation; Equivalence (formal languages); Sensitivity (control systems); Scheduling (production processes); Markov process; Job shop scheduling; Dynamic programming","score_opus":0.601241179788179,"score_gpt":0.5791320940734874,"score_spread":0.022109085714691612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414213966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82773393,0.0001519997,0.025414199,0.13951433,0.00009955824,0.0018760273,0.00024229004,0.000004755155,0.0049628885],"genre_scores_gemma":[0.9981487,0.00005504646,0.00009746288,0.00030793724,0.000017464248,0.00009240259,0.0000017478425,0.000004621874,0.0012746473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99115825,0.00423601,0.00065271533,0.0003289193,0.0031960164,0.00042808361],"domain_scores_gemma":[0.98023325,0.014501608,0.000059672988,0.0016280139,0.003528174,0.00004925059],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027204912,0.000092411625,0.00024846054,0.0007105215,0.0006245401,0.00010831387,0.0017382979,0.00006203326,0.00006483022],"category_scores_gemma":[0.024211496,0.000040451992,0.00012295194,0.005498659,0.000907054,0.00021078721,0.0006061152,0.00058464304,0.000018059549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074758645,0.00023885854,0.000111022666,0.000006270561,0.000015129156,0.0000014466505,0.0021288502,0.87488437,0.0022592414,0.102458596,0.014331733,0.0034897327],"study_design_scores_gemma":[0.0003950965,0.00030984572,0.030660754,0.00028356048,0.000004646257,0.0000022217932,0.012402679,0.64804924,0.036224164,0.27017707,0.0013535823,0.00013713016],"about_ca_topic_score_codex":0.0014380221,"about_ca_topic_score_gemma":0.0052122017,"teacher_disagreement_score":0.22683509,"about_ca_system_score_codex":0.00003528325,"about_ca_system_score_gemma":0.0006501639,"threshold_uncertainty_score":0.984008},"labels":[],"label_agreement":null},{"id":"W4416250108","doi":"10.1002/sta4.70119","title":"Matrix Freedman Inequality for Sub‐Weibull Martingales","year":2025,"lang":"en","type":"article","venue":"Stat","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hermitian matrix; Upper and lower bounds; Eigenvalues and eigenvectors; Covariance matrix; Freedman; Matrix (chemical analysis); Range (aeronautics); Inequality","score_opus":0.1491050896707326,"score_gpt":0.5308173076417018,"score_spread":0.38171221797096916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416250108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10877063,0.00041222875,0.88284975,0.0037809794,0.00065463054,0.0006794182,0.00027836344,0.00009903567,0.0024749716],"genre_scores_gemma":[0.9324498,0.00002616528,0.027200863,0.00037364464,0.00022775956,0.00014824817,0.000028521512,0.000025514531,0.039519437],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99735576,0.0001676323,0.0005675231,0.00050282065,0.00096027646,0.0004460033],"domain_scores_gemma":[0.9954282,0.0031756528,0.00012368879,0.00065511995,0.000520433,0.00009692557],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003357981,0.00012349105,0.0002658525,0.00030266467,0.00024837046,0.00021512243,0.00074072863,0.000063843756,0.00021407501],"category_scores_gemma":[0.008384766,0.000093190094,0.00011948871,0.00087883906,0.00015572348,0.00024296007,0.0002731794,0.00015389176,0.00026437375],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006016903,0.00024224767,0.035246577,0.00012964408,0.00007993349,0.000028140517,0.0007386197,0.0011874986,0.005903406,0.024285927,0.41178674,0.5197696],"study_design_scores_gemma":[0.0011337542,0.000135233,0.01530182,0.0000264731,0.000009394794,0.0000014421419,0.00097282766,0.012149266,0.015167045,0.61739045,0.33745697,0.00025531658],"about_ca_topic_score_codex":0.00003371386,"about_ca_topic_score_gemma":0.00015903547,"teacher_disagreement_score":0.8556489,"about_ca_system_score_codex":0.00007457127,"about_ca_system_score_gemma":0.00014022944,"threshold_uncertainty_score":0.99996805},"labels":[],"label_agreement":null},{"id":"W4416251985","doi":"10.1109/ijcnn64981.2025.11227713","title":"Upper confidence bound multi-armed bandits for partially observed Hawkes processes","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Point process; Regret; Event (particle physics); Process (computing); Set (abstract data type); Point (geometry); Upper and lower bounds; Ranking (information retrieval)","score_opus":0.2590586033651935,"score_gpt":0.47764199471521024,"score_spread":0.21858339135001675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416251985","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006616879,0.0071101007,0.9708106,0.0061782487,0.0029591527,0.00432915,0.0002575918,0.00018881403,0.0015494798],"genre_scores_gemma":[0.6252061,0.0018267028,0.049472786,0.0016325968,0.00049956044,0.0014163691,0.000038084512,0.00009916248,0.3198086],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9890056,0.0004562881,0.0025040957,0.0027090693,0.0031270776,0.0021978263],"domain_scores_gemma":[0.9754951,0.014652494,0.00056639436,0.0017817485,0.0068703997,0.00063388096],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0045905686,0.00083906093,0.0013597517,0.0009388875,0.0017730049,0.0030514533,0.0036981057,0.0005159553,0.003851886],"category_scores_gemma":[0.052118182,0.0006564741,0.00047183566,0.0045189653,0.0016436838,0.0023666031,0.0009446274,0.0006224689,0.0007519521],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010268693,0.008969338,0.05416867,0.0076634316,0.0025946375,0.00033660524,0.00909183,0.019355372,0.014915792,0.028038591,0.24572691,0.5988701],"study_design_scores_gemma":[0.014688839,0.0013524086,0.020134691,0.0015262293,0.00028548762,0.000018818655,0.009261029,0.25078443,0.17108285,0.104101434,0.4240961,0.002667678],"about_ca_topic_score_codex":0.00014886937,"about_ca_topic_score_gemma":0.0023004645,"teacher_disagreement_score":0.9213378,"about_ca_system_score_codex":0.0002662647,"about_ca_system_score_gemma":0.0065727327,"threshold_uncertainty_score":0.99958867},"labels":[],"label_agreement":null},{"id":"W4416566621","doi":"10.1017/eec.2025.10027","title":"Strategies in the multi-armed bandit","year":2025,"lang":"en","type":"article","venue":"Experimental Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Baylor University; University of Toronto; Purdue University","keywords":"Reinforcement learning; Probabilistic logic; Selection (genetic algorithm); Multi-armed bandit; Set (abstract data type)","score_opus":0.13607813791203105,"score_gpt":0.48556625018957017,"score_spread":0.3494881122775391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416566621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9390361,0.0014179692,0.016348891,0.0018967884,0.0010398686,0.00072049955,0.000022067283,0.000038439222,0.039479375],"genre_scores_gemma":[0.9962892,0.00002617444,0.0015830667,0.0004006473,0.000046720066,0.00007097164,0.0000032258495,0.0000063915177,0.0015735914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9985895,0.00012673308,0.00042555836,0.0003759172,0.00021461285,0.00026765428],"domain_scores_gemma":[0.9987092,0.00066134223,0.00006623109,0.00050000986,0.00002716664,0.000036040125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010465867,0.00011539152,0.00018612521,0.00024272453,0.00013074464,0.0004757766,0.001071785,0.000051386894,0.00034235345],"category_scores_gemma":[0.00016877809,0.000078307305,0.000069089205,0.00035399478,0.0001968279,0.00052521855,0.00019215184,0.00017074759,0.00026533776],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012500442,0.0058090943,0.03145074,0.00003147033,0.00027304608,0.0002800999,0.06772568,0.13071953,0.017350188,0.4879798,0.080245204,0.1768851],"study_design_scores_gemma":[0.006491988,0.00027297775,0.033717178,0.000028466342,0.000005258805,0.000021338605,0.36755556,0.11942238,0.09109954,0.13270903,0.24786974,0.00080654793],"about_ca_topic_score_codex":0.000051467418,"about_ca_topic_score_gemma":0.00015383762,"teacher_disagreement_score":0.35527077,"about_ca_system_score_codex":0.00017749821,"about_ca_system_score_gemma":0.00013824296,"threshold_uncertainty_score":0.45879248},"labels":[],"label_agreement":null},{"id":"W4417297121","doi":"10.48550/arxiv.2512.10906","title":"Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Cornell Atkinson Center for Sustainability, Cornell University; David R. Atkinson Center for a Sustainable Future , Cornell University","keywords":"Subgradient method; Semidefinite programming; Convex optimization; Optimal control; Regret; Minimax; Convexity; Probability distribution; Ambiguity; Stochastic control","score_opus":0.1950033316790077,"score_gpt":0.29831358147250475,"score_spread":0.10331024979349704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417297121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039350547,0.00017003095,0.9480064,0.0015343871,0.0014931484,0.0017832612,0.005818948,0.00018986333,0.0016533952],"genre_scores_gemma":[0.96940535,0.00024429493,0.0022156246,0.0003541417,0.00016816215,0.000011242991,0.00047427468,0.00004717921,0.027079722],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9874143,0.0018854025,0.0015479227,0.005024911,0.0020361207,0.0020913703],"domain_scores_gemma":[0.98634815,0.004011628,0.0012969631,0.0035967713,0.0035615861,0.0011849112],"candidate_categories":["metaepi_narrow","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0039950623,0.0013775333,0.0018453174,0.001594034,0.0015540868,0.0007848347,0.005589632,0.0013175163,0.0037862058],"category_scores_gemma":[0.0017735402,0.0014867072,0.0013752077,0.004637663,0.002151005,0.0010512131,0.003585371,0.0030123054,0.0010449865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016352037,0.0006803949,0.0025909771,0.00008421352,0.0004504118,0.00073486904,0.000032793792,0.9754928,0.000019130097,0.015062088,0.0016779221,0.0015392469],"study_design_scores_gemma":[0.0064650904,0.0002637149,0.008666747,0.0003164489,0.0003488981,0.000007005239,0.000543217,0.9471438,0.00019410242,0.029859575,0.0047913715,0.0014000572],"about_ca_topic_score_codex":0.00030084047,"about_ca_topic_score_gemma":0.0001302159,"teacher_disagreement_score":0.94579077,"about_ca_system_score_codex":0.0033730876,"about_ca_system_score_gemma":0.004911563,"threshold_uncertainty_score":0.99997896},"labels":[],"label_agreement":null},{"id":"W44932258","doi":"","title":"Online Queries for Collaborative Filtering","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Precomputation; Collaborative filtering; Computer science; Recommender system; Information retrieval; Computation; Theoretical computer science; Algorithm","score_opus":0.1817496231968929,"score_gpt":0.5025650383189986,"score_spread":0.32081541512210565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W44932258","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15345982,0.00003102016,0.8343419,0.0034167098,0.0011338046,0.0006824699,0.0003603505,0.000109704764,0.0064642425],"genre_scores_gemma":[0.3789194,0.0000085689235,0.5641948,0.00027466868,0.0006322996,0.000118368036,0.000022257631,0.000026741647,0.055802904],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99844223,0.000028760956,0.00027307085,0.00031574038,0.00069597096,0.0002442352],"domain_scores_gemma":[0.9966696,0.0018161568,0.00006349926,0.0003951252,0.0009585176,0.00009710897],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00088449696,0.00008267277,0.00015942863,0.00014361793,0.000163787,0.00019838673,0.0005025344,0.000050809238,0.0015978494],"category_scores_gemma":[0.006725111,0.00005353152,0.000045788354,0.0006226474,0.0001584863,0.0004041111,0.00013394636,0.0001572437,0.00013306765],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003627653,0.0004540625,0.0019125097,0.000013737886,0.000048103844,0.000021979653,0.002055926,0.0007138534,0.18162405,0.03541988,0.09271111,0.684662],"study_design_scores_gemma":[0.0006396159,0.0001884013,0.0028956193,0.000002927191,0.0000018239643,0.0000057539182,0.0036822848,0.011245149,0.06827096,0.07680345,0.8360464,0.00021762373],"about_ca_topic_score_codex":0.000007947594,"about_ca_topic_score_gemma":0.0008676035,"teacher_disagreement_score":0.7433353,"about_ca_system_score_codex":0.0000106963425,"about_ca_system_score_gemma":0.00010773562,"threshold_uncertainty_score":0.99931484},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.37014291537915395,"score_gpt":0.4472209630766811,"score_spread":0.07707804769752713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W53582479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005894133,0.0006153731,0.99378043,0.0001824531,0.00033983839,0.0009209413,0.00004497142,0.000019608486,0.0035069399],"genre_scores_gemma":[0.98345333,0.000010938836,0.006611512,0.00004592372,0.000113307244,0.00012286633,5.1161936e-7,0.000011153668,0.009630441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99753594,0.000172002,0.0005657709,0.000285234,0.0011676832,0.00027335956],"domain_scores_gemma":[0.99205345,0.0059381626,0.0002237875,0.00069377705,0.0010160145,0.000074838186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032982803,0.00010201052,0.0003103545,0.00012343662,0.00019077302,0.00006244148,0.00092813966,0.000056414403,0.00030911414],"category_scores_gemma":[0.0032919182,0.000046858077,0.00012375388,0.000422869,0.000301351,0.00022794894,0.00006569282,0.00010714415,0.00012564055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009356047,0.0014480387,0.007775884,0.00018319252,0.0017601501,0.000063477295,0.026148451,0.029959502,0.0020402086,0.5137246,0.097511575,0.31002885],"study_design_scores_gemma":[0.0014638441,0.0007969422,0.0009889356,0.000017393832,0.000024759856,0.0000054471266,0.008943573,0.9409765,0.0017051125,0.028842961,0.016077783,0.00015677226],"about_ca_topic_score_codex":0.00021427605,"about_ca_topic_score_gemma":0.000058579335,"teacher_disagreement_score":0.98716897,"about_ca_system_score_codex":0.000023796718,"about_ca_system_score_gemma":0.00010834506,"threshold_uncertainty_score":0.39409715},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07402534430139121,"score_gpt":0.39450746002030646,"score_spread":0.3204821157189153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W659523800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96650463,0.000058187634,0.032716222,0.00012154252,0.000042541607,0.00042991186,0.0000053782423,0.0000010248638,0.00012058441],"genre_scores_gemma":[0.99841833,0.000008307662,0.0007220399,0.000012943876,0.000004405953,0.000027699643,4.2726828e-7,0.0000025020001,0.000803338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644923,0.00027705915,0.00038991962,0.00020230048,0.0025553573,0.00012615732],"domain_scores_gemma":[0.9985639,0.0005111185,0.00018004721,0.0005512491,0.00016834264,0.00002533499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026472495,0.000060885803,0.00017967114,0.00024705892,0.000058674486,0.000020480895,0.00054070994,0.000029289165,0.0008780953],"category_scores_gemma":[0.0010327455,0.000026690122,0.00006599887,0.0017350456,0.00025678508,0.00024374132,0.0002738545,0.000086420056,0.000015094829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054883744,0.00008487834,0.09414473,0.0000017563881,0.000108086926,4.346863e-8,0.0007668289,0.22497381,0.0022949334,0.000011663114,0.0000564677,0.6775513],"study_design_scores_gemma":[0.000109070344,0.0000115038365,0.4605617,0.0000027561246,0.000027778644,1.2804468e-7,0.00019310243,0.53719455,0.00129535,0.00058067887,0.0000049493806,0.000018400155],"about_ca_topic_score_codex":0.000089757355,"about_ca_topic_score_gemma":0.00004746301,"teacher_disagreement_score":0.6775329,"about_ca_system_score_codex":0.000045662262,"about_ca_system_score_gemma":0.00003903714,"threshold_uncertainty_score":0.9614528},"labels":[],"label_agreement":null},{"id":"W6892570696","doi":"10.5281/zenodo.11867602","title":"Iso 3103 pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardization; Order (exchange); Brewing; International standardization; Sensory analysis","score_opus":0.09434761987973811,"score_gpt":0.3624524832899565,"score_spread":0.2681048634102184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892570696","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000034149452,0.0009921585,0.017400557,0.00081079284,0.0006057884,0.00063982076,0.00073131314,0.0016099947,0.9772062],"genre_scores_gemma":[0.00036559821,0.00024655505,0.0006175481,0.00010109241,0.00090602634,8.2276486e-8,0.0007762112,0.012556111,0.9844308],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937021,0.0007003692,0.00059812824,0.0014218251,0.002827416,0.0007501415],"domain_scores_gemma":[0.99668205,0.00012691961,0.00027029697,0.0016727676,0.0008538086,0.00039413694],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026370431,0.0003627454,0.0004546731,0.0018668763,0.0010449863,0.0035200417,0.0042514494,0.00029134715,0.5778213],"category_scores_gemma":[0.004907034,0.00031525988,0.00018473029,0.0023037537,0.00047355215,0.00024958022,0.003820283,0.0009560059,0.78035384],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015607095,0.000047901904,1.0774247e-7,0.000047578636,0.000051916046,0.000073031304,0.00016633465,0.000011949084,0.00005291353,0.000720371,0.87562895,0.123183355],"study_design_scores_gemma":[0.0002625501,0.00013527815,0.0000079903475,0.000106901985,0.0000148558565,0.00010521734,0.00024067069,0.00029140912,0.000035612036,0.0049300464,0.9935367,0.00033277192],"about_ca_topic_score_codex":0.000024592113,"about_ca_topic_score_gemma":0.000001852489,"teacher_disagreement_score":0.20253253,"about_ca_system_score_codex":0.0002355723,"about_ca_system_score_gemma":0.000012809816,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W6968595109","doi":"10.5281/zenodo.3554750","title":"Statistical Consequences of using Multi-armed Bandits to Conduct Adaptive Educational Experiments","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Key (lock); Statistical power; Randomized experiment; Design of experiments; Statistical hypothesis testing; Statistical analysis","score_opus":0.31909689091757365,"score_gpt":0.45198857970293516,"score_spread":0.1328916887853615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968595109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49663436,0.000171169,0.47219983,0.0014705055,0.0007857726,0.0026479461,0.0017213116,0.0002782169,0.02409089],"genre_scores_gemma":[0.97949326,0.000005328907,0.018335233,0.00006559668,0.00006676427,1.0908644e-7,0.0001956338,0.00035370197,0.001484366],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99610645,0.0006663897,0.00052333256,0.0006464984,0.0016396284,0.00041768554],"domain_scores_gemma":[0.9965966,0.00046188576,0.0001926468,0.00054857077,0.0018921243,0.00030822534],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015993578,0.00014789616,0.0002725586,0.0005149897,0.00078162836,0.00046134565,0.0014670964,0.000054658136,0.04440981],"category_scores_gemma":[0.005763982,0.00013178663,0.000048244252,0.0010827826,0.0004803362,0.0004340929,0.0010643166,0.00021090503,0.012146288],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016317768,0.0020973058,0.0009669947,0.00012027177,0.00033528107,0.000062599036,0.0143350735,0.010813867,0.63338846,0.047532167,0.1354626,0.15325363],"study_design_scores_gemma":[0.0051151817,0.0023398006,0.020689078,0.00021419226,0.000034228873,0.00033672844,0.014066147,0.031144505,0.08258038,0.011719523,0.8304108,0.0013494446],"about_ca_topic_score_codex":0.00003173538,"about_ca_topic_score_gemma":3.1510316e-7,"teacher_disagreement_score":0.6949482,"about_ca_system_score_codex":0.00021755416,"about_ca_system_score_gemma":0.0000425738,"threshold_uncertainty_score":0.98862284},"labels":[],"label_agreement":null},{"id":"W6977790614","doi":"10.6084/m9.figshare.7145417.v1","title":"Additional file 2: of Global, regional, and national prevalence of hepatitis B infection in the general and key populations living with HIV: a systematic review and meta-analysis protocol","year":2018,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Protocol (science); Key (lock); Hepatitis B; Hepatitis B virus; Population; Quality (philosophy)","score_opus":0.23891528062892448,"score_gpt":0.45106282257667835,"score_spread":0.21214754194775387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977790614","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003637327,0.000573281,0.000053665583,0.00011978329,7.61407e-7,0.009900109,0.9892006,0.0000042917445,0.00011115674],"genre_scores_gemma":[0.026779495,0.00015611551,0.023286372,0.001263189,0.00016883621,0.7634905,0.18181199,0.000040118997,0.0030033856],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9977418,0.00033967648,0.0004588518,0.00026115097,0.0011102546,0.00008822231],"domain_scores_gemma":[0.9952812,0.0030279486,0.00043681002,0.00021233194,0.0010066254,0.00003506529],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047935246,0.00009257116,0.00047310552,0.00014563491,0.0000976568,0.00005899699,0.00016252008,0.000029896102,0.5971183],"category_scores_gemma":[0.015480986,0.000051160405,0.00008371394,0.0012404423,0.000082920196,0.00032441138,0.00009072863,0.00005775366,0.000019327608],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033786282,0.000038181097,0.001810763,0.014219291,0.0008318346,8.1984564e-7,0.00007185295,0.000049861566,8.803587e-8,0.000041048635,0.98291415,0.000018727806],"study_design_scores_gemma":[0.000249183,0.00031833065,0.94340485,0.02509532,0.008003539,0.00012619913,0.000049994986,0.011454422,0.0000014988428,0.0022716883,0.008721542,0.00030342097],"about_ca_topic_score_codex":0.000031148415,"about_ca_topic_score_gemma":0.00055531133,"teacher_disagreement_score":0.9741926,"about_ca_system_score_codex":0.00002312332,"about_ca_system_score_gemma":0.00008117893,"threshold_uncertainty_score":0.99281204},"labels":[],"label_agreement":null},{"id":"W6979268663","doi":"","title":"Minimax Rate-Optimal Algorithms for High-Dimensional Stochastic Linear Bandits","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Minimax; Regret; Estimator; Lasso (programming language); Logarithm; Upper and lower bounds; Thresholding; Dimension (graph theory); Least-squares function approximation","score_opus":0.1399943811085759,"score_gpt":0.4363972147109591,"score_spread":0.2964028336023832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979268663","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45000893,0.00023115263,0.54533285,0.0019165456,0.001469077,0.000705398,0.0001301227,0.00009606559,0.0001098629],"genre_scores_gemma":[0.94593126,0.000007450187,0.02144772,0.0006689452,0.0005949168,0.0002312628,0.00006576945,0.00004979561,0.03100289],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99553096,0.00019918545,0.0008885526,0.0011639855,0.00136939,0.0008479314],"domain_scores_gemma":[0.9925481,0.004953486,0.00020463028,0.0008956954,0.0011450655,0.00025301203],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00243533,0.00033475074,0.00057759037,0.0006194395,0.00053138676,0.0001421914,0.0011368053,0.00019450541,0.0013381455],"category_scores_gemma":[0.007291218,0.00026107824,0.00021975233,0.0014592703,0.00033572374,0.0004700301,0.0004614846,0.00039621844,0.0017106094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051648715,0.0023949847,0.04587228,0.00016898927,0.0010674065,0.00044673955,0.0010645231,0.39626646,0.02121512,0.005162393,0.26709646,0.25407976],"study_design_scores_gemma":[0.012721792,0.0017144337,0.24344558,0.00023508424,0.00017156363,0.000040328167,0.00088176434,0.5884984,0.04023966,0.051289625,0.058678057,0.002083699],"about_ca_topic_score_codex":0.000028133098,"about_ca_topic_score_gemma":0.000015422234,"teacher_disagreement_score":0.52388513,"about_ca_system_score_codex":0.00012661092,"about_ca_system_score_gemma":0.0004258702,"threshold_uncertainty_score":0.99998415},"labels":[],"label_agreement":null},{"id":"W7024151739","doi":"","title":"Putting Trials on Trial: Sexual Assault and the Failure of the Legal Profession","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Distrust; Sexual assault; Commit; Economic Justice; Criminal justice; Sexual violence; Criminal trial; Suicide prevention","score_opus":0.22828142911056837,"score_gpt":0.5148975797955458,"score_spread":0.2866161506849775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024151739","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8911893,0.000100257086,0.026876625,0.061204694,0.0028975203,0.0056907022,0.000027918608,0.00008086258,0.011932153],"genre_scores_gemma":[0.9777217,0.0000021137664,0.0017141185,0.000228955,0.0007169849,0.000031868294,3.338456e-7,0.000010032015,0.019573929],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99303466,0.0027808947,0.00089193764,0.0003896276,0.0026480157,0.00025488445],"domain_scores_gemma":[0.985649,0.012406058,0.0005017558,0.00079308334,0.0005920328,0.00005810558],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0284976,0.00012053701,0.00047374892,0.000108698805,0.00048046155,0.00021406064,0.0009499405,0.00010778526,0.00038220806],"category_scores_gemma":[0.050771177,0.000038182498,0.00011135445,0.0007017458,0.0009118626,0.00025802365,0.00045237472,0.0003444944,0.00006545593],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.042103842,0.00026309912,0.0006030599,0.000013233144,0.000099112774,0.000004040892,0.0034826177,0.000089165485,0.006297866,0.020976925,0.11806466,0.80800235],"study_design_scores_gemma":[0.24907254,0.00518241,0.0054347455,0.00023573883,0.00010396047,0.000037173286,0.03772396,0.0312034,0.16431925,0.260577,0.24531145,0.0007983881],"about_ca_topic_score_codex":0.000066523935,"about_ca_topic_score_gemma":0.00012515737,"teacher_disagreement_score":0.807204,"about_ca_system_score_codex":0.000017810753,"about_ca_system_score_gemma":0.00014231392,"threshold_uncertainty_score":0.98767567},"labels":[],"label_agreement":null},{"id":"W7024172320","doi":"","title":"Recherche-action-formation sur l'efficacité du changement assisté dans la réalite de la pratique","year":2007,"lang":"fr","type":"dissertation","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Fusible alloy; Hyporeflexia; Dysgeusia","score_opus":0.0843459556938104,"score_gpt":0.36524212314077903,"score_spread":0.28089616744696866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024172320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2115898,0.0028083632,0.7272264,0.00025478294,0.00095794606,0.0008273824,0.000070361886,0.000045205583,0.05621979],"genre_scores_gemma":[0.92339957,0.0057143252,0.036860645,0.000024465897,0.00027075878,0.000006992956,0.00018598912,0.000047155263,0.033490073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9938199,0.0024802026,0.00086327014,0.00060495315,0.001758117,0.00047358248],"domain_scores_gemma":[0.9942052,0.00283011,0.0006478322,0.00063101633,0.0014536179,0.00023226354],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005560775,0.00044015903,0.0006196999,0.0006597196,0.0011299984,0.00010660464,0.0018438045,0.0010553186,0.00019587146],"category_scores_gemma":[0.0024310106,0.0004102974,0.0005784986,0.0014906937,0.0018567516,0.0010142546,0.00039194018,0.0011784893,0.000115556766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030538545,0.004865479,0.012233466,0.0124423355,0.0012379576,0.00027978994,0.17511204,0.3025413,0.19055212,0.034658447,0.0064835027,0.25653973],"study_design_scores_gemma":[0.0029494406,0.00033118212,0.28199986,0.0095144035,0.0005377605,0.0002880442,0.016088486,0.19050772,0.2812369,0.0035110298,0.21196327,0.0010719043],"about_ca_topic_score_codex":0.0028990777,"about_ca_topic_score_gemma":0.045923356,"teacher_disagreement_score":0.7118098,"about_ca_system_score_codex":0.006799331,"about_ca_system_score_gemma":0.0018366869,"threshold_uncertainty_score":0.9998349},"labels":[],"label_agreement":null},{"id":"W7025114976","doi":"","title":"Transform Fresno: 2024 Progress Report on Implementation of the Transformative Climate Communities Program Grant","year":2024,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transformative learning; Legislature; Transformational leadership; Disadvantaged; State (computer science); Globe; Climate change; Conference of the parties; Program evaluation","score_opus":0.058399282912740214,"score_gpt":0.3845701843569714,"score_spread":0.32617090144423116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025114976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.885681,0.001684901,0.0029236414,0.0135196345,0.0019048925,0.007879689,0.0366755,0.0015194347,0.04821132],"genre_scores_gemma":[0.9975792,0.000056191315,0.000507546,0.00008675726,0.00007966853,0.00026758245,0.00043539106,0.00006856556,0.0009190907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99445975,0.00030186283,0.0014157571,0.0004906716,0.0026569278,0.0006750108],"domain_scores_gemma":[0.9975408,0.0009419603,0.00023314034,0.0009027809,0.00018114425,0.00020021178],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016117987,0.00034954076,0.0004107068,0.00048015223,0.00038341462,0.0033642848,0.0015460573,0.00012229878,0.0011361116],"category_scores_gemma":[0.00020290141,0.00020154637,0.00046188603,0.0021142047,0.0006432886,0.00629393,0.00028283065,0.00093128026,0.0005856377],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021648698,0.00033580972,0.027418515,0.00022075741,0.000112442816,0.00015355734,0.0013739178,0.000041663923,0.000012114949,0.0019650436,0.0031418158,0.9650079],"study_design_scores_gemma":[0.0014279878,0.001347308,0.022372738,0.0009795482,0.00006249058,0.00024174237,0.010941835,0.0025192664,0.034829453,0.12593304,0.79839486,0.00094976334],"about_ca_topic_score_codex":0.00000932091,"about_ca_topic_score_gemma":0.000030846157,"teacher_disagreement_score":0.9640581,"about_ca_system_score_codex":0.000063011474,"about_ca_system_score_gemma":0.00027867453,"threshold_uncertainty_score":0.99977696},"labels":[],"label_agreement":null},{"id":"W7043060603","doi":"","title":"Regret Analysis of Bilateral Trade with a Smoothed Adversary","year":2024,"lang":"en","type":"article","venue":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Regret; Order (exchange); Adversary; Bilateral trade; Minimax","score_opus":0.0785588179925852,"score_gpt":0.3637387840940678,"score_spread":0.2851799661014826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043060603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95235467,0.00018463314,0.045010608,0.00043270833,0.000033337954,0.0001458535,0.00028474917,0.000052900068,0.0015005392],"genre_scores_gemma":[0.99645245,0.00007367495,0.0030872421,0.000014726894,0.0000065397167,3.189322e-7,0.000020196425,0.0000092388655,0.00033560488],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9959016,0.0015546913,0.0004287707,0.00039237525,0.0014412324,0.00028133945],"domain_scores_gemma":[0.994875,0.003454704,0.0003053082,0.0009054097,0.0003095627,0.00014999525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026284482,0.00020836349,0.0009588991,0.0015662566,0.00022986539,0.00003190494,0.0015527345,0.00020069203,0.00059275486],"category_scores_gemma":[0.00046849338,0.00015824907,0.00045411926,0.0043221503,0.0021463183,0.0003978051,0.0006936753,0.0007780583,0.00000954034],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010003585,0.0057467856,0.07134531,0.0010432268,0.0095715765,0.013248991,0.1173245,0.073783934,0.020271406,0.047980182,0.003014812,0.6266657],"study_design_scores_gemma":[0.003580066,0.007708172,0.6721227,0.0005506194,0.0018230081,0.00023068672,0.09772899,0.18292406,0.0014853044,0.018785993,0.01181229,0.0012480948],"about_ca_topic_score_codex":0.00030078235,"about_ca_topic_score_gemma":0.00038155686,"teacher_disagreement_score":0.6254176,"about_ca_system_score_codex":0.00004735175,"about_ca_system_score_gemma":0.00009397484,"threshold_uncertainty_score":0.79081994},"labels":[],"label_agreement":null},{"id":"W7096516363","doi":"","title":"University of Alberta MULTI-ARMED BANDIT PROBLEMS UNDER DELAYED FEEDBACK","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Adversarial system; Upper and lower bounds; Term (time); Key (lock); Online learning; Style (visual arts)","score_opus":0.12231490048786577,"score_gpt":0.372325968829354,"score_spread":0.25001106834148823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096516363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04194264,0.000032228614,0.9495665,0.0022586596,0.00013826106,0.00032512666,0.00002327606,0.000036250305,0.005677082],"genre_scores_gemma":[0.80174077,0.00004061826,0.0075618783,0.00003543079,0.00002240683,8.957985e-7,0.000001503012,0.000011783039,0.19058469],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974598,0.00015227051,0.0003333271,0.0004931519,0.0011941259,0.00036732477],"domain_scores_gemma":[0.9961527,0.0023270037,0.00015439474,0.0006541943,0.00052265497,0.00018903699],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000874226,0.00012341155,0.0002587824,0.00022154169,0.00011679908,0.000031952233,0.000978202,0.00009089535,0.008329121],"category_scores_gemma":[0.0010439921,0.000069255286,0.000109369335,0.0006626238,0.0004014442,0.00049433106,0.00031278198,0.00008696493,0.0021436438],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024472012,0.0024637275,0.048805553,0.00005657331,0.0007682971,0.00013047057,0.006089033,0.012800823,0.08132219,0.009806163,0.16110468,0.6742053],"study_design_scores_gemma":[0.03705492,0.0017900476,0.2503255,0.00028269642,0.00009277027,0.00006753386,0.015053526,0.058192655,0.051079463,0.15285341,0.4303744,0.0028330318],"about_ca_topic_score_codex":0.00088124676,"about_ca_topic_score_gemma":0.00419462,"teacher_disagreement_score":0.9420046,"about_ca_system_score_codex":0.00008540616,"about_ca_system_score_gemma":0.000120989615,"threshold_uncertainty_score":0.9986333},"labels":[],"label_agreement":null},{"id":"W7097340650","doi":"","title":"Multi-armed bandits, Gittins index, and its calculation. http://www.ece.mcgill.ca/ amahaj1/projects/bandits/book/2013-bandit -computations.pdf [7","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Lemma (botany); Key (lock); Counterfactual thinking","score_opus":0.10099396275231036,"score_gpt":0.3823988705056625,"score_spread":0.28140490775335214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097340650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38629395,0.0046284855,0.5670801,0.0104345875,0.0033955586,0.010811547,0.00059976644,0.0013756717,0.01538037],"genre_scores_gemma":[0.89091104,0.0003477619,0.011635411,0.0010344284,0.00045489633,0.00041365702,0.00010696742,0.000104963474,0.09499087],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913893,0.0004613407,0.0016486077,0.0018320906,0.0033719526,0.0012967315],"domain_scores_gemma":[0.9925661,0.003079299,0.0005404811,0.0010746567,0.0018972562,0.00084219145],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018665612,0.0006746253,0.0008891619,0.0013233302,0.0012732922,0.0010240988,0.0012410297,0.00042063542,0.013604959],"category_scores_gemma":[0.0027965538,0.0005013813,0.000249967,0.0020758135,0.00044015842,0.0031329142,0.0006461632,0.00077941216,0.024308586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004903994,0.0025479381,0.0342086,0.00025940975,0.000879554,0.00033239252,0.004088338,0.0726159,0.007363786,0.0040134727,0.67162883,0.20157136],"study_design_scores_gemma":[0.004633369,0.00025619063,0.101960234,0.00005711318,0.000034671135,0.00007885597,0.0010490649,0.7590389,0.001991084,0.0033205366,0.12645175,0.001128193],"about_ca_topic_score_codex":0.0007300287,"about_ca_topic_score_gemma":0.00038357452,"teacher_disagreement_score":0.68642306,"about_ca_system_score_codex":0.00024289895,"about_ca_system_score_gemma":0.00025364337,"threshold_uncertainty_score":0.99974376},"labels":[],"label_agreement":null},{"id":"W7100077618","doi":"","title":"Author manuscript, published in &amp;quot;Advances in Neural Information Processing Systems, Canada (2008)&amp;quot; Algorithms for Infinitely Many-Armed Bandits","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Logarithm; Artificial neural network; Information processing; Imprecise probability; Probability distribution","score_opus":0.12492032992043503,"score_gpt":0.3955459154269162,"score_spread":0.2706255855064812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100077618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1684637,0.0063221892,0.779386,0.013670921,0.008465724,0.0143606765,0.000594827,0.00055459136,0.008181364],"genre_scores_gemma":[0.90942293,0.00011567227,0.04157827,0.0013386664,0.00067762414,0.003560434,0.0006561886,0.00013105378,0.04251917],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906966,0.00035176976,0.002759356,0.00097464846,0.0035886278,0.0016290069],"domain_scores_gemma":[0.99382854,0.0019347806,0.0007777594,0.0009162932,0.0020490498,0.0004935554],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.003884655,0.00053273916,0.00093606376,0.0020812296,0.00035823265,0.002740361,0.001705726,0.00026913531,0.0007721355],"category_scores_gemma":[0.009329351,0.0004057868,0.00010361885,0.003629592,0.0001793678,0.016408676,0.00031572528,0.00071313186,0.00027102014],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000275759,0.00021467092,0.015610023,0.00047447468,0.0000237595,0.000028797267,0.0024991326,0.04637075,0.00007050528,0.0003166881,0.20156659,0.73254883],"study_design_scores_gemma":[0.0026530582,0.000097123964,0.021549927,0.00013638061,0.0000059114677,0.00004117804,0.005152431,0.38644466,0.00007592313,0.0042453175,0.57873344,0.00086466596],"about_ca_topic_score_codex":0.13587226,"about_ca_topic_score_gemma":0.49064976,"teacher_disagreement_score":0.7409592,"about_ca_system_score_codex":0.00085938716,"about_ca_system_score_gemma":0.0013559626,"threshold_uncertainty_score":0.9998394},"labels":[],"label_agreement":null},{"id":"W7105903772","doi":"10.23952/jano.7.2025.3.04","title":"Robust contextual bandit method for optimal loan offering","year":2025,"lang":"","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Loan; Context (archaeology); Term (time); Production (economics); Robustness (evolution)","score_opus":0.058461756882175794,"score_gpt":0.38796934007498757,"score_spread":0.32950758319281176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7105903772","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028217552,0.00094538386,0.9949779,0.0012978889,0.0007729868,0.00066766544,0.000024472107,0.00001222024,0.0010192952],"genre_scores_gemma":[0.085228585,0.0006716848,0.9124167,0.00032445035,0.0004969006,0.000022729406,0.0000064302267,0.00003652851,0.0007959955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952929,0.00018671386,0.0020108363,0.0006278744,0.001299546,0.0005821463],"domain_scores_gemma":[0.99315995,0.0036128636,0.0011685073,0.00029351772,0.0013828116,0.00038232128],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036583075,0.00036745178,0.0011633228,0.00085376523,0.00051140133,0.00061995967,0.000687566,0.00028833532,0.0003170772],"category_scores_gemma":[0.0018588088,0.0002908152,0.00030692568,0.0013357109,0.00025058718,0.0006638826,0.00026890475,0.00065948494,0.000005074697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022673125,0.00014926666,0.000010943165,0.00003755712,0.00012977388,0.0000068996433,0.00024693852,0.8031765,0.00029115292,0.0010774753,0.0010925229,0.19151363],"study_design_scores_gemma":[0.003661741,0.00071930845,0.000088922614,0.000109617205,0.00014586208,0.000034907436,0.0012889095,0.9795957,0.0012933732,0.003525037,0.009258858,0.0002777631],"about_ca_topic_score_codex":0.0000030356623,"about_ca_topic_score_gemma":2.1624106e-7,"teacher_disagreement_score":0.19123586,"about_ca_system_score_codex":0.00018439238,"about_ca_system_score_gemma":0.0004563031,"threshold_uncertainty_score":0.9999544},"labels":[],"label_agreement":null},{"id":"W7108210594","doi":"10.1109/tac.2025.3639124","title":"Online Best-Response Algorithm in Open Noncooperative Games","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Regret; Interval (graph theory); Stability (learning theory); Upper and lower bounds; Trajectory; Nash equilibrium; Online algorithm; Online learning; Cournot competition","score_opus":0.04965455923632081,"score_gpt":0.42018282951190844,"score_spread":0.37052827027558766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108210594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076121213,0.000487941,0.97161686,0.008605896,0.002127377,0.007468047,0.0015502782,0.00012932057,0.00040216692],"genre_scores_gemma":[0.9120518,0.00026927236,0.030349983,0.0018931441,0.00009653919,0.0023455003,0.000005904021,0.000098257675,0.05288962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9866995,0.004094969,0.0031304697,0.0020424835,0.0025617734,0.0014708057],"domain_scores_gemma":[0.9791118,0.016597277,0.0004606914,0.0022496914,0.0011088842,0.00047166698],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0066625355,0.0009376328,0.0021808061,0.0033168555,0.00094548106,0.0018605413,0.0042153476,0.00051146286,0.005608582],"category_scores_gemma":[0.0018309122,0.0008231525,0.00051265885,0.0063338843,0.0008265257,0.0017481637,0.000044584755,0.0015476521,0.0015945933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022015532,0.0050366316,0.000007967905,0.000029979494,0.00030927538,0.00018770188,0.0011364926,0.06671459,0.0003766662,0.00001024434,0.000414786,0.9235741],"study_design_scores_gemma":[0.016216913,0.0013990776,0.0010146005,0.0011685931,0.00015175028,0.000021843265,0.0040712887,0.96730506,0.0024616483,0.00127539,0.0042007747,0.00071304414],"about_ca_topic_score_codex":0.0004211241,"about_ca_topic_score_gemma":0.0013749994,"teacher_disagreement_score":0.9412669,"about_ca_system_score_codex":0.0012466926,"about_ca_system_score_gemma":0.003747737,"threshold_uncertainty_score":0.99942195},"labels":[],"label_agreement":null},{"id":"W7112773223","doi":"","title":"A Parametric Contextual Online Learning Theory of Brokerage","year":2024,"lang":"en","type":"article","venue":"Bristol Research (University of Bristol)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche; University of Ottawa","keywords":"Regret; Asset (computer security); Parametric statistics; Context (archaeology); Online learning","score_opus":0.25388020423483015,"score_gpt":0.4610343178363569,"score_spread":0.20715411360152675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7112773223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8072955,0.007891445,0.17092809,0.0011179149,0.00031131975,0.00079483166,0.000368333,0.00016439523,0.01112818],"genre_scores_gemma":[0.9519945,0.00045098248,0.0016775785,0.0000055061555,0.000077102406,6.6492146e-7,0.000023703757,0.000027117787,0.04574285],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99068815,0.0021443465,0.00054994255,0.00093498,0.004941467,0.0007411322],"domain_scores_gemma":[0.9868652,0.009458188,0.00022264256,0.0008680662,0.002239372,0.00034648934],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011857551,0.00018843947,0.0006546262,0.0035101147,0.00048985024,0.00014412036,0.002281757,0.00018354904,0.0015057072],"category_scores_gemma":[0.014747038,0.00019232123,0.0003519402,0.0072427588,0.0022616214,0.0007499952,0.0010992427,0.0015382024,0.0005966264],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007345578,0.0005713305,0.0015035287,0.00019433684,0.00020077964,0.0013948681,0.003956992,0.0011456436,0.002363975,0.0064795576,0.04649139,0.93496305],"study_design_scores_gemma":[0.002659504,0.0024090253,0.019908901,0.0005142489,0.00006846379,0.00013916785,0.1252916,0.15370817,0.00090063154,0.046761774,0.6467624,0.000876159],"about_ca_topic_score_codex":0.0008203327,"about_ca_topic_score_gemma":0.00027545265,"teacher_disagreement_score":0.93408686,"about_ca_system_score_codex":0.00033446957,"about_ca_system_score_gemma":0.0006764002,"threshold_uncertainty_score":0.99940705},"labels":[],"label_agreement":null},{"id":"W7117323897","doi":"10.1007/s10994-025-06943-6","title":"Extended UCB Policies for Multi-armed Bandit Problems","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Novelis (Canada)","funders":"","keywords":"Regret; Process (computing); Markov decision process; Simplicity; Order (exchange); Reinforcement learning; Extension (predicate logic)","score_opus":0.15270853510586288,"score_gpt":0.48696366916655853,"score_spread":0.3342551340606956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117323897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00972465,0.000982565,0.9819115,0.0029642277,0.0004466046,0.0009338223,0.000029900211,0.00023368638,0.002773053],"genre_scores_gemma":[0.79479253,0.000053373853,0.03199154,0.00044374398,0.00022375573,0.00029944215,0.000042040694,0.000053706437,0.17209986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969368,0.00028029212,0.0005786738,0.00063935656,0.00093982805,0.0006250275],"domain_scores_gemma":[0.99679434,0.0020398027,0.00017917145,0.000470259,0.00040061952,0.00011579905],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025741989,0.00020845344,0.0003847441,0.0006982075,0.0006478426,0.00035252256,0.0008694151,0.00009539142,0.00035375817],"category_scores_gemma":[0.01145622,0.00015516493,0.00017047267,0.001243871,0.00017418108,0.00026264976,0.0003560881,0.00047483874,0.00013966214],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003365572,0.0004255272,0.0610071,0.00013722005,0.00017193968,0.000022958318,0.003197398,0.12581636,0.00570742,0.0038569276,0.012290519,0.7870301],"study_design_scores_gemma":[0.002055271,0.00016150002,0.01831249,0.000042445936,0.00001160622,0.000004483434,0.0005348827,0.5994303,0.0012688861,0.017223885,0.36069855,0.00025563748],"about_ca_topic_score_codex":0.0001419023,"about_ca_topic_score_gemma":0.00016043104,"teacher_disagreement_score":0.94991994,"about_ca_system_score_codex":0.00008663331,"about_ca_system_score_gemma":0.000105695544,"threshold_uncertainty_score":0.9968707},"labels":[],"label_agreement":null},{"id":"W7117744886","doi":"10.3390/s26010226","title":"Comparative Evaluation of Bandit-Style Heuristic Policies for Moving Target Detection in a Linear Grid Environment","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Defense Acquisition Program Administration","keywords":"Heuristics; Grid; Heuristic; Greedy algorithm; Monte Carlo method; Posterior probability; Probability distribution; Sampling (signal processing); Bayesian probability","score_opus":0.139089121442262,"score_gpt":0.4653359788925978,"score_spread":0.3262468574503358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117744886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8923557,0.00019534012,0.10559136,0.0001840721,0.00034054354,0.0009397065,0.000061037885,0.0000126358345,0.00031963995],"genre_scores_gemma":[0.99599856,0.000011852848,0.0030703,0.00001268761,0.000063418534,0.00007181633,0.0000068574695,0.0000056648787,0.0007588163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732006,0.00037617897,0.0005028152,0.0003333285,0.0012397326,0.00022786082],"domain_scores_gemma":[0.99757487,0.0016168469,0.0001598711,0.00028469064,0.00032691326,0.00003680973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030332848,0.00010339027,0.00029186343,0.0005635825,0.00010462656,0.000027889144,0.0002042776,0.000055115706,0.000092146496],"category_scores_gemma":[0.0033481591,0.000086345324,0.00006972039,0.00062302756,0.00012897862,0.00011142564,0.00007095264,0.00011830199,0.000033754986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017893821,0.000120867786,0.0015513642,0.0000178998,0.000027665303,0.0000010639828,0.0023753755,0.9698674,0.00514508,0.00004968603,0.00036609205,0.020298589],"study_design_scores_gemma":[0.00091840635,0.00010461364,0.020268468,0.000025304886,0.000013740233,6.4670996e-7,0.0024183928,0.9058102,0.056976594,0.010625762,0.0027435636,0.00009432568],"about_ca_topic_score_codex":0.000074560696,"about_ca_topic_score_gemma":0.00011653045,"teacher_disagreement_score":0.10364292,"about_ca_system_score_codex":0.0002307188,"about_ca_system_score_gemma":0.00008498347,"threshold_uncertainty_score":0.40083012},"labels":[],"label_agreement":null},{"id":"W7123346749","doi":"10.1109/cdc57313.2025.11312073","title":"Online bandit non-cooperative games with arbitrary delays","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Regret; Online learning; Order (exchange); Upper and lower bounds; Multi-armed bandit; Online algorithm","score_opus":0.043627701022410335,"score_gpt":0.4100376357551577,"score_spread":0.3664099347327474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123346749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038633026,0.0026043206,0.8644701,0.007439375,0.0010759145,0.0018102011,0.0003219412,0.0001225851,0.0835225],"genre_scores_gemma":[0.57427895,0.0012603907,0.053134646,0.0032607338,0.0005071089,0.00011930713,0.000062504696,0.00008196422,0.3672944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99130553,0.0004208555,0.0015005649,0.0021351378,0.0032226339,0.0014152488],"domain_scores_gemma":[0.99175525,0.0035395226,0.00026663265,0.001821073,0.0020927787,0.0005247672],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016963992,0.00076105644,0.0011816062,0.0013591235,0.0008684388,0.0010673515,0.002365306,0.000338716,0.010966708],"category_scores_gemma":[0.0017128421,0.0004805943,0.0002504102,0.0061977007,0.0015155156,0.0017201976,0.00096529257,0.001416733,0.0010692681],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004687914,0.007200415,0.009312949,0.00021065582,0.001967812,0.0020854236,0.004346575,0.036779985,0.0007086182,0.0076415027,0.15581565,0.7692425],"study_design_scores_gemma":[0.013831623,0.0055888807,0.026306832,0.0015475986,0.00028662066,0.00015499849,0.032206178,0.5903814,0.039792407,0.034204554,0.2523257,0.0033732331],"about_ca_topic_score_codex":0.00014813575,"about_ca_topic_score_gemma":0.00076824665,"teacher_disagreement_score":0.8113355,"about_ca_system_score_codex":0.0002731977,"about_ca_system_score_gemma":0.0029381944,"threshold_uncertainty_score":0.99996966},"labels":[],"label_agreement":null},{"id":"W7124160515","doi":"10.65109/bvlt2388","title":"Using adaptive consultation of experts to improve convergence rates in multiagent learning","year":2008,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convergence (economics); Set (abstract data type); Multi-agent system; Advice (programming); Process (computing); Class (philosophy); Order (exchange)","score_opus":0.28631231996863216,"score_gpt":0.4785216023773186,"score_spread":0.19220928240868645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124160515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5657413,0.00041044565,0.4321712,0.00006699195,0.00043412272,0.00091663626,0.000011297083,0.0000140590855,0.0002339183],"genre_scores_gemma":[0.95027345,0.00030953134,0.04597995,0.000046641067,0.000049522387,0.000033359258,0.0000013483028,0.000024322087,0.003281874],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934124,0.000684093,0.0016527117,0.0011503322,0.0022952247,0.0008052335],"domain_scores_gemma":[0.9930338,0.00364113,0.00049671036,0.0004714585,0.0019899975,0.00036686985],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018813948,0.0003397183,0.00070396194,0.0010087133,0.00037723235,0.00006779803,0.0006820825,0.00016860376,0.0019186768],"category_scores_gemma":[0.012212072,0.00029611727,0.0001254579,0.0030727296,0.00068612804,0.0009893571,0.0004794281,0.0004018659,0.00023509099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013354789,0.00053251925,0.022361131,0.000026849006,0.000054943903,0.00027879825,0.05083559,0.59927505,0.2372488,0.00010537425,0.00018237127,0.087763116],"study_design_scores_gemma":[0.0014570262,0.0005630433,0.00456694,0.0000888697,0.000004203709,0.00001277809,0.032258984,0.75458914,0.20567057,0.00019686161,0.00024685907,0.00034476194],"about_ca_topic_score_codex":0.0012878446,"about_ca_topic_score_gemma":0.00013531928,"teacher_disagreement_score":0.38619125,"about_ca_system_score_codex":0.0003299807,"about_ca_system_score_gemma":0.00070949947,"threshold_uncertainty_score":0.9999491},"labels":[],"label_agreement":null},{"id":"W7124305818","doi":"10.65109/hhyv8660","title":"An Online Learning Theory of Brokerage","year":2024,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Regret; Bounded function; Constant (computer programming); Focus (optics); Online learning; Online algorithm","score_opus":0.1508691918332686,"score_gpt":0.47760096021013443,"score_spread":0.3267317683768658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124305818","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07920172,0.009092769,0.89655954,0.00045787255,0.001378617,0.00035654343,0.000108654676,0.00021221917,0.012632087],"genre_scores_gemma":[0.8590187,0.0009298374,0.0068223365,0.00004314577,0.00039116014,0.000003873872,0.000013523003,0.00004860476,0.13272882],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924883,0.0013753728,0.0012331026,0.0012072528,0.0029853324,0.0007106003],"domain_scores_gemma":[0.99142677,0.0063978657,0.0001399978,0.0010341039,0.00062572805,0.00037556436],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0075637787,0.0003056815,0.00055096974,0.001018532,0.00024598866,0.0007229749,0.0015951702,0.0002008567,0.03028618],"category_scores_gemma":[0.0039338386,0.00021706529,0.00027810028,0.0028563244,0.0007287732,0.0015892424,0.00045546584,0.0012363405,0.0014643087],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010213153,0.00027939782,0.00018048615,0.000057859932,0.00005715898,0.00014874985,0.0018028922,0.01190045,0.002213592,0.007708336,0.00043562736,0.97511333],"study_design_scores_gemma":[0.0003797576,0.0013817376,0.0019495811,0.0002327047,0.000029930516,0.000036145713,0.014324292,0.77860624,0.005276172,0.103379704,0.093962036,0.00044173183],"about_ca_topic_score_codex":0.000027418697,"about_ca_topic_score_gemma":0.000022101915,"teacher_disagreement_score":0.9746716,"about_ca_system_score_codex":0.00008031446,"about_ca_system_score_gemma":0.00046325868,"threshold_uncertainty_score":0.9993132},"labels":[],"label_agreement":null},{"id":"W7124307892","doi":"10.65109/apzr4957","title":"Learning in Games with Progressive Hiding","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Counterfactual thinking; Imperfect; Regret; Perfect information; Information hiding; Recall; Complete information","score_opus":0.045895036896597706,"score_gpt":0.44139978224570314,"score_spread":0.39550474534910546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124307892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27402893,0.01310963,0.53826696,0.012533401,0.0012901913,0.0038608059,0.0000071325408,0.00036642808,0.15653652],"genre_scores_gemma":[0.8782854,0.0001679674,0.00782634,0.00010814843,0.000054327786,0.0000794608,0.0000010441552,0.000020163236,0.11345713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99381524,0.00058624917,0.0009413947,0.0013160295,0.0022391665,0.0011018929],"domain_scores_gemma":[0.99490213,0.0032927697,0.00025066055,0.00065043464,0.00072379276,0.00018021913],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028395976,0.00034603692,0.00062848907,0.0017930374,0.00044279883,0.00090481335,0.0012025716,0.0001761945,0.0025480925],"category_scores_gemma":[0.005382416,0.00023247422,0.00009258167,0.00678057,0.0006601318,0.0010345976,0.00074641616,0.0012853547,0.00035404463],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040842238,0.0001969861,0.08125786,0.000040456598,0.000053594707,0.00051949086,0.00140931,0.020335687,0.000079717065,0.0012591257,0.00072410953,0.89371526],"study_design_scores_gemma":[0.01052869,0.0033661001,0.07787236,0.0046240455,0.00006174811,0.000091189715,0.118163414,0.6158255,0.020723403,0.042841017,0.10368517,0.0022174004],"about_ca_topic_score_codex":0.00005335319,"about_ca_topic_score_gemma":0.00011176451,"teacher_disagreement_score":0.89149785,"about_ca_system_score_codex":0.00029227044,"about_ca_system_score_gemma":0.00114818,"threshold_uncertainty_score":0.99836373},"labels":[],"label_agreement":null},{"id":"W7125929930","doi":"10.1145/3768292.3793394","title":"10.1145/3768292.3793394","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Portfolio; Process (computing); Component (thermodynamics)","score_opus":0.05551599963377606,"score_gpt":0.3566894785234227,"score_spread":0.30117347888964663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125929930","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007413418,0.0000661022,0.00017508827,0.0008221022,0.000006877016,0.0002628445,0.00002909656,0.000117244315,0.9977793],"genre_scores_gemma":[0.00032367167,5.1894244e-7,0.0010069269,0.00007701427,0.00018990424,0.000023169958,0.000004582401,0.000023489438,0.99835074],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99635804,0.00014833383,0.00042927536,0.00059516926,0.0019254386,0.0005437642],"domain_scores_gemma":[0.9976282,0.0007709792,0.00004861904,0.0009230086,0.00026936684,0.00035984413],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013625543,0.000163771,0.00027531636,0.00030596837,0.00018067796,0.0002467902,0.0012219803,0.00007426256,0.9983703],"category_scores_gemma":[0.0014194577,0.0001271486,0.00010088041,0.0013441476,0.00010539099,0.0003658331,0.00017678969,0.00018809173,0.9980617],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005775216,0.000028089955,3.1603452e-7,4.1677686e-7,0.0000041038825,0.000014253393,0.000015733509,0.0008041752,0.000025361947,6.863624e-7,0.23706304,0.7619861],"study_design_scores_gemma":[0.00023020644,0.00014759446,0.00011240557,0.0000048586307,0.0000023389389,0.000011861904,0.0000039546676,0.0023989435,0.00016163205,0.00055836426,0.99619657,0.00017125321],"about_ca_topic_score_codex":0.000012429347,"about_ca_topic_score_gemma":3.6488348e-7,"teacher_disagreement_score":0.76181483,"about_ca_system_score_codex":0.000061241844,"about_ca_system_score_gemma":0.00007045136,"threshold_uncertainty_score":0.51849693},"labels":[],"label_agreement":null},{"id":"W7132960036","doi":"","title":"Online Learning and Optimization in Communication Networks","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Exploit; Online algorithm; Wireless network; Resource allocation; Optimization problem; Convex optimization; Stochastic gradient descent; Asynchrony (computer programming); Key (lock); Gradient descent","score_opus":0.0873601606606339,"score_gpt":0.4951564731886173,"score_spread":0.4077963125279834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132960036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22523552,0.02147747,0.7424656,0.0028679385,0.0020409846,0.0033500413,0.000024059165,0.00045809904,0.0020802438],"genre_scores_gemma":[0.47031617,0.13666235,0.060204525,0.0000728272,0.0005172194,0.00025001014,0.0073623857,0.00046188475,0.32415262],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942843,0.0011954209,0.0011282719,0.0010756202,0.0016225466,0.00069387676],"domain_scores_gemma":[0.99344546,0.0040303925,0.00076702284,0.00077255856,0.0007761163,0.00020843948],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003376861,0.0004376553,0.00071611244,0.0013244892,0.000628254,0.00054618804,0.0009419944,0.00063993526,0.0005767521],"category_scores_gemma":[0.00650207,0.00044683376,0.000091480346,0.003908862,0.0002407301,0.000505916,0.0004676988,0.0022650585,0.0001306639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001149599,0.000085155465,0.000977446,0.00002674213,0.000013857437,0.000012792528,0.0084414,0.90322,0.000008616711,0.000012287938,0.00010933876,0.086977385],"study_design_scores_gemma":[0.00065803906,0.00010448351,0.008395734,0.00042405105,0.000014953695,0.0000030680048,0.083282195,0.9054266,0.000011620239,0.00034173616,0.0009684964,0.0003690323],"about_ca_topic_score_codex":0.00059230195,"about_ca_topic_score_gemma":0.0024286928,"teacher_disagreement_score":0.6822611,"about_ca_system_score_codex":0.00021132061,"about_ca_system_score_gemma":0.00018923044,"threshold_uncertainty_score":0.99979836},"labels":[],"label_agreement":null},{"id":"W7133405170","doi":"","title":"Lexicographic Lipschitz Bandits:New Algorithms and a Lower Bound","year":2025,"lang":"en","type":"article","venue":"CityU Scholars","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; City University of Hong Kong","keywords":"Lexicographical order; Regret; Upper and lower bounds; Lipschitz continuity; Dimension (graph theory); Matching (statistics)","score_opus":0.07882936778791948,"score_gpt":0.4231396116865803,"score_spread":0.34431024389866083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133405170","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6659198,0.00957529,0.2563366,0.0131329615,0.008444889,0.001626962,0.00011091327,0.0005218145,0.044330794],"genre_scores_gemma":[0.89193344,0.0008965395,0.020251684,0.0021624959,0.0007955397,0.00006269003,0.000014265138,0.000071419214,0.08381194],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954969,0.00024530452,0.00063692493,0.0010989483,0.0018610616,0.0006608059],"domain_scores_gemma":[0.9968605,0.0009640648,0.00013399831,0.0011321212,0.00045395162,0.00045535312],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030591905,0.00027656442,0.00043785956,0.0012682285,0.0005820416,0.0023142213,0.0014796213,0.00022771744,0.00066529476],"category_scores_gemma":[0.00611011,0.00022678543,0.00017373936,0.003198293,0.00044155426,0.0015081153,0.00068932434,0.0009090925,0.00037499517],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002001232,0.00021474082,0.04059453,0.000013783545,0.00016339718,0.00020177227,0.0002514772,0.00012419683,0.0012273446,0.001728469,0.050298296,0.90498185],"study_design_scores_gemma":[0.0022632303,0.00015438715,0.077614546,0.00008080443,0.000029464025,0.000046856643,0.000360465,0.0020174677,0.0011233233,0.18268014,0.73310405,0.0005252858],"about_ca_topic_score_codex":0.000045108845,"about_ca_topic_score_gemma":0.00004322022,"teacher_disagreement_score":0.90445656,"about_ca_system_score_codex":0.00007229195,"about_ca_system_score_gemma":0.000340445,"threshold_uncertainty_score":0.9987215},"labels":[],"label_agreement":null},{"id":"W7135006558","doi":"","title":"An Online Learning Theory of Trading-Volume Maximization","year":2025,"lang":"en","type":"article","venue":"Bristol Research (University of Bristol)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Regret; Earnings; Complement (music); Asset (computer security); Profit (economics); Private information retrieval; Maximization; Logarithm; Function (biology)","score_opus":0.1984716496858113,"score_gpt":0.43981916459205045,"score_spread":0.24134751490623915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135006558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41016623,0.0005203605,0.57939476,0.0010204868,0.00011095709,0.00048863015,0.000099032695,0.00006940321,0.008130124],"genre_scores_gemma":[0.9511991,0.00013631948,0.0056583774,0.000009150349,0.000026755346,5.196771e-7,0.00003918493,0.000015326412,0.04291528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99282265,0.002215527,0.00046927857,0.00072949927,0.0032179642,0.00054511137],"domain_scores_gemma":[0.99371266,0.002029389,0.0003086524,0.0009710574,0.0027422803,0.00023595883],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009193018,0.00014575518,0.0005214645,0.0022490635,0.00071192486,0.00008335121,0.0026962399,0.00016725989,0.0009817514],"category_scores_gemma":[0.0064452314,0.000165442,0.00017756986,0.0041807652,0.0016289835,0.00085571496,0.00060554344,0.0008295573,0.000072547286],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018764427,0.0014605958,0.027245127,0.00015946124,0.00014124486,0.000179592,0.0040500807,0.0102527635,0.00479104,0.006754703,0.031151302,0.91193765],"study_design_scores_gemma":[0.0034440772,0.0017309502,0.17193548,0.00028398377,0.000056021276,0.000017466931,0.10151171,0.43079728,0.001234941,0.1229529,0.16540472,0.00063047523],"about_ca_topic_score_codex":0.0005986412,"about_ca_topic_score_gemma":0.00031898782,"teacher_disagreement_score":0.91130716,"about_ca_system_score_codex":0.00030010653,"about_ca_system_score_gemma":0.00057238666,"threshold_uncertainty_score":0.9999315},"labels":[],"label_agreement":null},{"id":"W7139010223","doi":"10.1109/globecom59602.2025.11432650","title":"Kelly Bets and Single-Letter Codes: Optimal Information Processing in Natural Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Upper and lower bounds; Information processing; Population; Simple (philosophy); Point (geometry); Code (set theory); Investment (military); Complete information","score_opus":0.039392630988728174,"score_gpt":0.3778315229514149,"score_spread":0.3384388919626867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7139010223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15760477,0.013548025,0.8007802,0.00608019,0.0033539291,0.0027761275,0.000042458196,0.00014077358,0.015673567],"genre_scores_gemma":[0.9868913,0.0000766333,0.005763919,0.0008012211,0.00010751982,0.000036972426,0.0000093941,0.000010740287,0.0063022966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99453074,0.00028370883,0.0017025997,0.00067373575,0.0019653526,0.00084386807],"domain_scores_gemma":[0.9971906,0.00093332585,0.0003301096,0.00045520574,0.0009351216,0.00015567154],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002627332,0.00035544147,0.00059780857,0.0017569038,0.0004050542,0.0034691135,0.00079053396,0.00026200738,0.00010317244],"category_scores_gemma":[0.0019827064,0.00027691023,0.0000665203,0.0028453388,0.0004847769,0.0063942205,0.00061456906,0.000773522,0.00014637227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000357706,0.00017027765,0.003060614,0.0007831681,0.000025884776,0.000042620803,0.0036760499,0.018316826,0.0005460251,0.00039721155,0.006091584,0.96653205],"study_design_scores_gemma":[0.0015743679,0.00013027419,0.003619389,0.0008338746,0.000011097924,0.000024491814,0.006946726,0.9541617,0.0007318214,0.0005071516,0.031050147,0.00040893894],"about_ca_topic_score_codex":0.00009667932,"about_ca_topic_score_gemma":0.00005420858,"teacher_disagreement_score":0.9661231,"about_ca_system_score_codex":0.00034554483,"about_ca_system_score_gemma":0.00046675975,"threshold_uncertainty_score":0.9999683},"labels":[],"label_agreement":null},{"id":"W852997015","doi":"10.1007/978-3-319-18356-5_7","title":"Budget-Driven Big Data Classification","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Class (philosophy); Big data; Process (computing); Machine learning; Artificial intelligence; Set (abstract data type); Data set; Training set; Support vector machine; Data mining; Scale (ratio); Programming language","score_opus":0.37212191456823307,"score_gpt":0.4431382603684922,"score_spread":0.07101634580025912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W852997015","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012380146,0.0005729977,0.9891167,0.0012550917,0.0029712773,0.00043774518,0.00010267556,0.000071221955,0.005459854],"genre_scores_gemma":[0.21004733,0.0002950142,0.7491332,0.0019404149,0.011820267,0.00004068568,0.0005444791,0.00028636618,0.025892194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98892576,0.00010791866,0.0009556155,0.0029795987,0.0062793233,0.00075179717],"domain_scores_gemma":[0.9897659,0.00232896,0.00051253923,0.005509341,0.001518026,0.00036524405],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006387269,0.0004636925,0.0006620023,0.0017490064,0.00028646906,0.00096518337,0.011581258,0.0003901592,0.00014684016],"category_scores_gemma":[0.0047312807,0.00035207582,0.0000842487,0.0015422872,0.0018861231,0.0010076308,0.00490827,0.0011898609,0.0009167627],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009842054,0.000016334767,0.00005218604,0.0000039928577,0.000004589896,0.0000416115,0.0001343851,0.019493397,0.000044171822,0.00048791972,0.0012603599,0.9784512],"study_design_scores_gemma":[0.00022437995,0.0000908125,0.00022101091,0.000076547854,0.0000047256403,0.00003164239,9.0587434e-7,0.5864283,0.00007255978,0.32376805,0.08864967,0.0004313945],"about_ca_topic_score_codex":0.000018175644,"about_ca_topic_score_gemma":0.00022666802,"teacher_disagreement_score":0.97801983,"about_ca_system_score_codex":0.0005139626,"about_ca_system_score_gemma":0.0017086958,"threshold_uncertainty_score":0.9998931},"labels":[],"label_agreement":null},{"id":"W9422450","doi":"","title":"Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments","year":2011,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Minimax; Outcome (game theory); Action (physics); Logarithm; Computer science; Mathematical optimization; Mathematics; Mathematical economics; Statistics; Psychology","score_opus":0.24345939677892353,"score_gpt":0.40468048743075924,"score_spread":0.1612210906518357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W9422450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56400114,0.0002407765,0.41863665,0.00008062513,0.0005831943,0.00044511884,0.000009461096,0.00006780644,0.015935235],"genre_scores_gemma":[0.9931802,0.000036536974,0.0007948738,0.0000072851353,0.00004361662,0.000024787143,0.0000011772319,0.000018737072,0.0058927704],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966552,0.0007230219,0.0005647541,0.0005432352,0.0010938084,0.0004199814],"domain_scores_gemma":[0.9958445,0.0030545879,0.00030609462,0.00058497005,0.000089238194,0.00012064248],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035437194,0.00018048492,0.00035779818,0.000448207,0.00008975132,0.00004456486,0.0008228477,0.0000986713,0.0016376945],"category_scores_gemma":[0.009388884,0.00014627312,0.000071759256,0.00040815133,0.00042233022,0.0002394648,0.0002185866,0.00057678006,0.00060295104],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025282146,0.00072641496,0.06787108,0.000022029444,0.00007177454,0.00016582171,0.028487857,0.06851728,0.00688444,0.035576753,0.000051400508,0.78909695],"study_design_scores_gemma":[0.0034158016,0.0027275772,0.23075037,0.0010755978,0.000032790656,0.000010808361,0.026712727,0.06783741,0.051309265,0.61161965,0.0031130163,0.001394961],"about_ca_topic_score_codex":0.000010528344,"about_ca_topic_score_gemma":0.0000014552456,"teacher_disagreement_score":0.78770196,"about_ca_system_score_codex":0.00005067309,"about_ca_system_score_gemma":0.00007919039,"threshold_uncertainty_score":0.99927497},"labels":[],"label_agreement":null}]}