{"meta":{"query_hash":"9d470e2ffb3e","filters":{"topic":"Adaptive Dynamic Programming Control"},"cohort_total":117,"direct_labels_cover":0,"predictions_cover":117,"exported":117,"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/9d470e2ffb3e","api":"https://metacan.xera.ac/api/v1/cohort?topic=Adaptive+Dynamic+Programming+Control"},"results":[{"id":"W1526607063","doi":"10.1007/978-3-540-72432-2_81","title":"Generalized Reinforcement Learning Fuzzy Control with Vague States","year":2007,"lang":"en","type":"book-chapter","venue":"Advances in soft computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Toronto","funders":"","keywords":"Reinforcement learning; Robustness (evolution); Fuzzy logic; Control theory (sociology); Computer science; Vagueness; Controller (irrigation); Fuzzy control system; Binary number; Control engineering; Artificial intelligence; Control (management); Mathematics; Engineering","score_opus":0.010652102777369513,"score_gpt":0.2566872670682516,"score_spread":0.24603516429088212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1526607063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009991881,0.001155284,0.974305,0.00023016849,0.00016028908,0.000025323061,0.00001813351,0.00015572255,0.013958315],"genre_scores_gemma":[0.7886962,0.0017275529,0.18208686,0.00022183855,0.00017663099,0.00013464791,0.000056959812,0.00005174773,0.026847461],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981004,0.00004675671,0.000009228031,0.000031292126,0.00008838273,0.000014348376],"domain_scores_gemma":[0.9998442,0.000068641435,0.00001571496,0.000025717722,0.000037316397,0.000008395528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046102275,0.0005714957,0.0006523348,0.00022387439,0.000193529,0.0006056888,0.00084769254,0.00061630865,0.0019985333],"category_scores_gemma":[0.00082443457,0.00017805198,0.0004306353,0.00040239797,0.0009376598,0.00072247203,0.0007024515,0.0010082129,0.00025632442],"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":[0.000060961564,0.0000367575,0.0001112665,0.00027256395,0.000059911108,0.00018045744,0.00017913415,0.50098497,0.0071622166,0.30445752,0.0031003498,0.18339388],"study_design_scores_gemma":[0.000016508318,0.000050256505,0.00012419118,0.000032695047,0.000015109223,0.00006179923,0.000013719056,0.8249849,0.0013321629,0.16824016,0.0051116967,0.000016903832],"about_ca_topic_score_codex":0.00096910266,"about_ca_topic_score_gemma":0.0011789432,"teacher_disagreement_score":0.0019985333,"about_ca_system_score_codex":0.0004576225,"about_ca_system_score_gemma":0.00032055855,"threshold_uncertainty_score":0.0066857934},"labels":[],"label_agreement":null},{"id":"W1873139171","doi":"10.1109/ccece.2000.849537","title":"A modified actor-critic reinforcement learning algorithm","year":2002,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Université de Sherbrooke","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Computer science; Backpropagation; Inverted pendulum; Artificial neural network; Bellman equation; Function (biology); Function approximation; Artificial intelligence; Fuzzy logic; Algorithm; Mathematics; Mathematical optimization; Nonlinear system","score_opus":0.01959364087753272,"score_gpt":0.22708790000562337,"score_spread":0.20749425912809066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1873139171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041327747,0.00021461431,0.99077094,0.0001505814,0.00011352041,0.000082183695,0.000026352996,0.0005972258,0.003911848],"genre_scores_gemma":[0.5365903,0.00037535094,0.44286487,0.00031591413,0.00014661161,0.0005780216,0.00016230762,0.00016975612,0.018796865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994516,0.000160542,0.000025745749,0.00010486854,0.00019927768,0.000057941917],"domain_scores_gemma":[0.99947625,0.00019740315,0.000045274137,0.000042707106,0.00019268748,0.0000457748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010227404,0.0010869964,0.001337473,0.0004607877,0.00045900635,0.000789281,0.002040872,0.0014764428,0.0046565286],"category_scores_gemma":[0.0017113611,0.0004060448,0.00045713986,0.00034915973,0.00068768865,0.0006745546,0.00087252137,0.0011922606,0.0012047219],"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":[0.0001225703,0.000060459577,0.000328023,0.00007896553,0.00007155022,0.00014406754,0.000052141884,0.8693155,0.002771113,0.019897584,0.0030170677,0.10414084],"study_design_scores_gemma":[0.000025050542,0.000023825853,0.000030225656,0.0000037969446,0.000005329607,0.0000149323205,0.0000014623707,0.99664295,0.00028095586,0.0017052881,0.0012615601,0.000004663948],"about_ca_topic_score_codex":0.004361044,"about_ca_topic_score_gemma":0.0032209512,"teacher_disagreement_score":0.0046565286,"about_ca_system_score_codex":0.0007509685,"about_ca_system_score_gemma":0.0012865491,"threshold_uncertainty_score":0.015577614},"labels":[],"label_agreement":null},{"id":"W2003323955","doi":"10.1109/ijcnn.2007.4370928","title":"Pitch Control of an Aircraft with Aggregated Reinforcement Learning Algorithms","year":2007,"lang":"en","type":"article","venue":"IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Cerebellar model articulation controller; Controller (irrigation); Aerodynamics; Control theory (sociology); Control system; Pitch control; Control engineering; Control (management); Adaptive control; Artificial intelligence; Engineering","score_opus":0.037093143854737345,"score_gpt":0.29929420971262816,"score_spread":0.2622010658578908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003323955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05173929,0.00013881047,0.945328,0.000110122535,0.00004664745,0.000036070596,0.000010857276,0.00033570247,0.0022546093],"genre_scores_gemma":[0.9617229,0.00006331014,0.03688772,0.000042684573,0.00003195113,0.000072990544,0.000019167654,0.000012386453,0.0011467774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960464,0.000111749425,0.000024332026,0.0000726714,0.00013178129,0.000054880154],"domain_scores_gemma":[0.9993037,0.0002693209,0.00012975556,0.000055671513,0.00019182703,0.00004982867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090025325,0.00065656274,0.00071689475,0.00025372714,0.0003296913,0.00062282354,0.0006606517,0.0005327863,0.00088450906],"category_scores_gemma":[0.0014680478,0.00022379203,0.00033679607,0.00021569342,0.00062358857,0.00045355954,0.00092503615,0.000779583,0.00014352977],"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":[0.000052304455,0.000030944062,0.00033577628,0.000026834103,0.000026876924,0.000038468075,0.000043068358,0.9698602,0.0021607857,0.003130978,0.0002571463,0.02403659],"study_design_scores_gemma":[0.000007719084,0.000023543013,0.000036983154,0.0000011058853,0.000002583526,0.000003051707,0.0000014461674,0.9991503,0.00016439818,0.0005346553,0.000072908755,0.0000012294432],"about_ca_topic_score_codex":0.0039299587,"about_ca_topic_score_gemma":0.0022514798,"teacher_disagreement_score":0.0039299587,"about_ca_system_score_codex":0.00045947012,"about_ca_system_score_gemma":0.00059100636,"threshold_uncertainty_score":0.007814169},"labels":[],"label_agreement":null},{"id":"W2016840647","doi":"10.1162/neco_a_00277","title":"Adaptive Optimal Control Without Weight Transport","year":2012,"lang":"en","type":"article","venue":"Neural Computation","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"York University; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Optimal control; Adaptive control; Control (management); Mathematics; Control theory (sociology); Mathematical optimization; Artificial intelligence","score_opus":0.014906962990867497,"score_gpt":0.24952887589965603,"score_spread":0.23462191290878853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016840647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009005128,0.0003744967,0.97897387,0.00054663623,0.00009312861,0.000030416111,0.000028481745,0.00017639768,0.0107714385],"genre_scores_gemma":[0.8310802,0.0008767585,0.14302716,0.0004977038,0.00016031714,0.00027107247,0.00008728211,0.00015124695,0.023848215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99964106,0.00008984528,0.000020777901,0.0000963029,0.00010493134,0.00004711515],"domain_scores_gemma":[0.99964607,0.00016878816,0.000044759574,0.000052251347,0.00006330703,0.000024834742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072615914,0.00069004117,0.0007140192,0.00036767137,0.00040342516,0.0010541445,0.00077931554,0.001149662,0.0028421786],"category_scores_gemma":[0.0024691452,0.00036937054,0.00055659685,0.0003899182,0.001594905,0.0014617125,0.0016114004,0.0015346871,0.00043708706],"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":[0.000057547542,0.000024673374,0.00015086395,0.00008000497,0.000031693693,0.00005330837,0.000057621957,0.60499823,0.0036678899,0.35539714,0.0014990306,0.033981998],"study_design_scores_gemma":[0.0000132059895,0.000018189383,0.00004162277,0.000007705939,0.0000051775896,0.000010209937,0.0000044150233,0.9232418,0.00069208234,0.07453419,0.0014220806,0.000009374313],"about_ca_topic_score_codex":0.0038771434,"about_ca_topic_score_gemma":0.0021657434,"teacher_disagreement_score":0.0038771434,"about_ca_system_score_codex":0.0010518638,"about_ca_system_score_gemma":0.0009478673,"threshold_uncertainty_score":0.009508073},"labels":[],"label_agreement":null},{"id":"W2023678709","doi":"10.1002/oca.993","title":"2‐DOF nonlinear ℋ<sub>∞</sub> certainty‐equivalent filters (CEFs)","year":2011,"lang":"en","type":"article","venue":"Optimal Control Applications and Methods","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Control theory (sociology); Nonlinear system; Filter (signal processing); Mathematics; Impulse response; Linear filter; Impulse (physics); Class (philosophy); Degrees of freedom (physics and chemistry); Mathematical analysis; Applied mathematics; Computer science; Physics; Classical mechanics","score_opus":0.02331007977431794,"score_gpt":0.30127617060313466,"score_spread":0.27796609082881674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023678709","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069897687,0.00014140566,0.9832397,0.00010576866,0.00006253022,0.000015685315,0.000034473665,0.00015252359,0.009258146],"genre_scores_gemma":[0.8645099,0.0005991366,0.11309232,0.0002554425,0.0001088661,0.00013291974,0.00013466996,0.00004589091,0.021120897],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99969494,0.00004120722,0.000015990296,0.0000619504,0.00014489457,0.000041017374],"domain_scores_gemma":[0.99976975,0.00006473911,0.000050793962,0.00003503535,0.00006622432,0.000013504239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003970594,0.0004428441,0.00038702463,0.00025085936,0.00024899145,0.00091907714,0.0005223849,0.0005729552,0.004362832],"category_scores_gemma":[0.0008803517,0.00015780193,0.00042961616,0.00016783619,0.00060753664,0.0006853503,0.00051903666,0.00081509835,0.0005090146],"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":[0.00015996592,0.000043421354,0.000580459,0.00017664988,0.000039778963,0.00018245837,0.00013422994,0.39790115,0.026040034,0.43390855,0.0025783987,0.138255],"study_design_scores_gemma":[0.0000189992,0.00009628551,0.00040687952,0.00003497989,0.0000138322075,0.000111427384,0.00003393197,0.90807724,0.011553154,0.06590313,0.013716976,0.000033161272],"about_ca_topic_score_codex":0.0016815804,"about_ca_topic_score_gemma":0.00095316075,"teacher_disagreement_score":0.004362832,"about_ca_system_score_codex":0.00050858705,"about_ca_system_score_gemma":0.0005032646,"threshold_uncertainty_score":0.014595091},"labels":[],"label_agreement":null},{"id":"W2032378315","doi":"10.1109/tcyb.2014.2311578","title":"A Clustering-Based Graph Laplacian Framework for Value Function Approximation in Reinforcement Learning","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Cluster analysis; Graph; Laplace operator; Reinforcement; Laplacian matrix; Computer science; Mathematics; Theoretical computer science; Artificial intelligence; Psychology; Mathematical analysis; Social psychology","score_opus":0.012196086102425497,"score_gpt":0.23833626966938337,"score_spread":0.22614018356695786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032378315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013186005,0.00009306885,0.9977931,0.00007346578,0.000014792714,0.0000132269615,0.000017830132,0.00006115794,0.00061487453],"genre_scores_gemma":[0.4369905,0.0007948863,0.556937,0.00019507488,0.0001201822,0.00029376848,0.0002701611,0.00014517189,0.0042533064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999387,0.00025588254,0.000029117838,0.000120668454,0.00016743972,0.000039979455],"domain_scores_gemma":[0.9991609,0.00045737365,0.00007640605,0.0000781139,0.00018465745,0.000042720185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010809463,0.0008550411,0.0010075556,0.0009397635,0.00045011108,0.00091006164,0.0013764938,0.00093374384,0.002031742],"category_scores_gemma":[0.003315634,0.00034984073,0.0009115535,0.001225512,0.0010034924,0.0012921294,0.0010348842,0.0016574647,0.00044593628],"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":[0.000028418486,0.000043692915,0.00030294986,0.00008858188,0.000041436007,0.000065507134,0.00008135842,0.8134548,0.0025948272,0.12955004,0.0016996629,0.052048672],"study_design_scores_gemma":[0.0000018526057,0.000008764056,0.000025667892,0.0000024203907,0.0000024055437,0.000007894494,0.000003686476,0.9818486,0.00013437976,0.017602809,0.00035745723,0.000004123707],"about_ca_topic_score_codex":0.0047762827,"about_ca_topic_score_gemma":0.0034084225,"teacher_disagreement_score":0.0047762827,"about_ca_system_score_codex":0.0010237064,"about_ca_system_score_gemma":0.0010337816,"threshold_uncertainty_score":0.009496927},"labels":[],"label_agreement":null},{"id":"W2039416092","doi":"10.1002/cjce.5450790127","title":"Bang‐Bang solution of nonlinear time‐optimal control problems using a semi‐exhaustivesearch","year":2001,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bang–bang control; Convergence (economics); Optimal control; Nonlinear system; Mathematics; Control (management); Mathematical optimization; Control theory (sociology); Nonlinear programming; Applied mathematics; Computer science; Economics; Physics","score_opus":0.012513258134855447,"score_gpt":0.2155197025225859,"score_spread":0.20300644438773044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039416092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11596928,0.0005839127,0.8761771,0.00020545504,0.000019042456,0.00015794513,0.000052460407,0.00028340306,0.0065514096],"genre_scores_gemma":[0.62936956,0.00029277007,0.36637813,0.00009091833,0.000014398793,0.0005461839,0.00009515718,0.000049439644,0.003163448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963856,0.0001885984,0.000025903595,0.000030589355,0.00008636583,0.00002994354],"domain_scores_gemma":[0.9981482,0.0014298336,0.00012382246,0.00008398278,0.00017082562,0.0000433144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011881833,0.0004646281,0.0008654398,0.0007889712,0.00038844958,0.0005423354,0.0005321907,0.0008624841,0.0020128512],"category_scores_gemma":[0.0027864883,0.0004969742,0.00043634354,0.0006680656,0.00066623604,0.0005877208,0.00087329233,0.0004068218,0.00020759233],"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":[0.00013630127,0.00009199108,0.00059162546,0.0001780673,0.00007678391,0.00007304858,0.00010266438,0.933448,0.0029952128,0.012181326,0.000445226,0.049679745],"study_design_scores_gemma":[0.000025631945,0.00005277537,0.00009439619,0.000012737411,0.0000062955255,0.000017521876,0.000008858045,0.9965731,0.00072866655,0.0021928265,0.0002829374,0.000004290016],"about_ca_topic_score_codex":0.0026889225,"about_ca_topic_score_gemma":0.0028559582,"teacher_disagreement_score":0.0026889225,"about_ca_system_score_codex":0.0003479382,"about_ca_system_score_gemma":0.0011793993,"threshold_uncertainty_score":0.006733656},"labels":[],"label_agreement":null},{"id":"W2066268309","doi":"10.2316/journal.206.2011.1.206-3412","title":"DISCRETE-TIME OPTIMAL CONTROL OF NONHOLONOMIC MOBILE ROBOT FORMATIONS USING LINEARLY PARAMETERIZED NEURAL NETWORKS","year":2011,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":5,"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":"Control theory (sociology); Artificial neural network; Parameterized complexity; Controller (irrigation); Computer science; Optimal control; Discrete time and continuous time; Mobile robot; Lyapunov stability; Nonlinear system; Nonholonomic system; Kinematics; Lyapunov function; Dynamic programming; Stability (learning theory); Robot; Mathematics; Mathematical optimization; Control (management); Artificial intelligence; Algorithm","score_opus":0.015170453927309292,"score_gpt":0.25193749398421583,"score_spread":0.23676704005690655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066268309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049400963,0.0004688624,0.9469833,0.00017117812,0.000047057605,0.000028919525,0.00001754958,0.00019084831,0.0026914454],"genre_scores_gemma":[0.96902466,0.00023614478,0.028523685,0.000042075866,0.000018188097,0.00007941174,0.000026857255,0.00001439593,0.002034622],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984896,0.000042065887,0.000007783796,0.00004153332,0.00003874944,0.000020887792],"domain_scores_gemma":[0.9997054,0.00012689497,0.00008957052,0.000019318002,0.000044804678,0.000013956908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034343897,0.00052806723,0.00045215312,0.00014303111,0.00028784855,0.000620161,0.000522883,0.0005172335,0.00057329197],"category_scores_gemma":[0.0008173858,0.00030690775,0.00030546743,0.00021595189,0.0006775038,0.00056960055,0.0005944924,0.0006111929,0.00009273789],"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":[0.00003100908,0.0000149419075,0.00015359283,0.000039047074,0.000013073844,0.000048495236,0.00004954811,0.98297185,0.0023419652,0.0025153086,0.00010648139,0.011714653],"study_design_scores_gemma":[0.000005406227,0.000020991325,0.00004922945,0.000002033778,0.0000022908507,0.0000046231457,0.0000049142127,0.99868125,0.00032574523,0.00077852345,0.00012274887,0.00000208499],"about_ca_topic_score_codex":0.0039714603,"about_ca_topic_score_gemma":0.0035915254,"teacher_disagreement_score":0.0039714603,"about_ca_system_score_codex":0.00044213436,"about_ca_system_score_gemma":0.00054657826,"threshold_uncertainty_score":0.007896662},"labels":[],"label_agreement":null},{"id":"W2083748997","doi":"10.1007/s11768-011-0170-8","title":"Asymptotic tracking by a reinforcement learning-based adaptive critic controller","year":2011,"lang":"en","type":"article","venue":"Journal of Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":47,"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":"Control theory (sociology); Controller (irrigation); Reinforcement learning; Artificial neural network; Tracking error; Computer science; Feed forward; Bounded function; Adaptive control; Nonlinear system; Lyapunov function; Lyapunov stability; Mathematics; Artificial intelligence; Control engineering; Engineering; Control (management)","score_opus":0.01146694965448446,"score_gpt":0.2295948023311984,"score_spread":0.21812785267671392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083748997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024479596,0.00025331884,0.96771425,0.00027083923,0.00017340886,0.000043121472,0.000011721211,0.00051702134,0.006536722],"genre_scores_gemma":[0.93992335,0.00014856568,0.054787982,0.00012170378,0.00007030233,0.00011579944,0.000024372765,0.000044478416,0.0047634738],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969447,0.000086940716,0.00001549192,0.000065775355,0.0001031244,0.000034281908],"domain_scores_gemma":[0.99923265,0.00032256232,0.00007719813,0.00006702799,0.00025655818,0.000043980926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009457591,0.0006158239,0.0008139966,0.00036899833,0.0004313576,0.0007652216,0.0010654432,0.0012482967,0.0019117703],"category_scores_gemma":[0.002619898,0.00036319045,0.0003897452,0.00026370632,0.0007593481,0.0005146516,0.00091788964,0.0012002233,0.000502574],"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":[0.00021457531,0.00011198292,0.00063219416,0.000104205006,0.00008313947,0.0001870533,0.00009785877,0.89491314,0.013342216,0.014433319,0.0017969236,0.07408335],"study_design_scores_gemma":[0.000018341656,0.00003330024,0.000063126856,0.0000035027106,0.0000061038504,0.00001779573,0.0000018327432,0.998566,0.00035165373,0.0007325963,0.00020100723,0.0000047399353],"about_ca_topic_score_codex":0.005257497,"about_ca_topic_score_gemma":0.0036934686,"teacher_disagreement_score":0.005257497,"about_ca_system_score_codex":0.0005234191,"about_ca_system_score_gemma":0.0007896974,"threshold_uncertainty_score":0.010453761},"labels":[],"label_agreement":null},{"id":"W2110469502","doi":"10.1016/j.automatica.2013.03.004","title":"Pareto optimality in infinite horizon linear quadratic differential games","year":2013,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Mathematics; Pareto principle; Mathematical optimization; Optimal control; Transversality; Quadratic equation; Scalar (mathematics); Minification; Pareto optimal; Applied mathematics; Multi-objective optimization","score_opus":0.009988373953563707,"score_gpt":0.2409104974390513,"score_spread":0.2309221234854876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110469502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1163646,0.0012300726,0.82212746,0.002201595,0.00015434525,0.00009205975,0.0002546952,0.00011683036,0.057458322],"genre_scores_gemma":[0.9589292,0.0010523859,0.019740632,0.00023399034,0.00007812769,0.00018183536,0.00015608597,0.00006443418,0.019563511],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99860257,0.00065250957,0.000050846993,0.00012406408,0.0003213065,0.00024879957],"domain_scores_gemma":[0.99578357,0.0032714796,0.0002947509,0.000080848135,0.00031653477,0.00025273536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028196364,0.0012415047,0.0017964476,0.000874002,0.0009909959,0.0028164443,0.0012826376,0.001526164,0.0039428966],"category_scores_gemma":[0.0077718757,0.0008644525,0.0007865851,0.00084923033,0.002519343,0.0022564179,0.0019707587,0.0022590258,0.00030032074],"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":[0.00010307322,0.00007177412,0.00044458147,0.00014322069,0.000058643494,0.00012999169,0.00015713432,0.42087278,0.00066436955,0.56749976,0.0015941154,0.008260569],"study_design_scores_gemma":[0.000034106506,0.00004492559,0.00020560826,0.000028725268,0.00001263475,0.000019190014,0.00006187375,0.56638265,0.00017815162,0.43231645,0.0007013033,0.000014331705],"about_ca_topic_score_codex":0.0071399724,"about_ca_topic_score_gemma":0.0057465946,"teacher_disagreement_score":0.0071399724,"about_ca_system_score_codex":0.0028825882,"about_ca_system_score_gemma":0.0031166775,"threshold_uncertainty_score":0.020914733},"labels":[],"label_agreement":null},{"id":"W2180467047","doi":"10.1007/s10462-015-9447-5","title":"Exponential moving average based multiagent reinforcement learning algorithms","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Carleton University","funders":"","keywords":"Nash equilibrium; Computer science; Reinforcement learning; Algorithm; Convergence (economics); Q-learning; Weighted Majority Algorithm; Mathematical optimization; Artificial intelligence; Mathematics; Wake-sleep algorithm; Unsupervised learning; Generalization error","score_opus":0.0888835926429212,"score_gpt":0.3256896554819136,"score_spread":0.2368060628389924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180467047","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008172801,0.005466222,0.97899204,0.0003517083,0.00021196518,0.000031622065,0.00001766059,0.00025104557,0.006504895],"genre_scores_gemma":[0.6313337,0.0095930025,0.34146082,0.00048527424,0.00041041148,0.0002697038,0.00013219287,0.00014421988,0.01617068],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99949265,0.00018223621,0.000032997315,0.00007486495,0.00018035667,0.00003683905],"domain_scores_gemma":[0.9984549,0.0010395637,0.00009548625,0.00006650971,0.00030574834,0.00003774615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014750529,0.0007967117,0.0011220874,0.00057546975,0.00027242771,0.00084763486,0.0019208458,0.0009036099,0.0020589915],"category_scores_gemma":[0.0035492193,0.00028405015,0.00039194236,0.00072059524,0.0005467906,0.0011538074,0.0008146957,0.0013766709,0.0003743491],"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":[0.000058780075,0.000104463325,0.00043620507,0.00015434013,0.00008809959,0.000031094434,0.000036357997,0.70852566,0.0004903006,0.032541674,0.0022161514,0.25531682],"study_design_scores_gemma":[0.000014113892,0.00003548747,0.000102065926,0.00001815832,0.000014658207,0.000022579696,0.000004998727,0.98869306,0.00028468666,0.009048709,0.0017549769,0.0000065161007],"about_ca_topic_score_codex":0.00214475,"about_ca_topic_score_gemma":0.0017337879,"teacher_disagreement_score":0.00214475,"about_ca_system_score_codex":0.0006077897,"about_ca_system_score_gemma":0.00054482673,"threshold_uncertainty_score":0.0078009367},"labels":[],"label_agreement":null},{"id":"W2199527024","doi":"10.1016/j.ifacol.2015.11.170","title":"On the Relation between the Hybrid Minimum Principle and Hybrid Dynamic Programming: a Linear Quadratic Example","year":2015,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"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":"Dynamic programming; Hybrid system; Bellman equation; Mathematical optimization; Optimal control; Mathematics; Hamiltonian (control theory); Maximum principle; Quadratic equation; Control theory (sociology); Key (lock); Function (biology); Process (computing); Quadratic programming; Computer science; Control (management)","score_opus":0.03561845750667487,"score_gpt":0.2763211445067575,"score_spread":0.24070268700008263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2199527024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04678418,0.00052399153,0.92108697,0.0012147081,0.00003695948,0.00003747565,0.000038540566,0.00006157932,0.030215632],"genre_scores_gemma":[0.8873876,0.00053350953,0.099839896,0.00022747685,0.000069912974,0.00012014826,0.000039476614,0.000052513125,0.011729449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996387,0.00018233673,0.000008142469,0.000043169064,0.00009213141,0.000035582685],"domain_scores_gemma":[0.9987459,0.0010238579,0.00006440766,0.000028408627,0.000102625476,0.00003474297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011922477,0.00050780113,0.0005409378,0.00037650522,0.00054126565,0.0007634265,0.00067685544,0.00094877585,0.004159636],"category_scores_gemma":[0.0025339301,0.00026988515,0.0004823651,0.0005341422,0.0013846206,0.001141726,0.0014165343,0.0015780793,0.00023248348],"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":[0.000058136087,0.00004794053,0.00024789464,0.000121272715,0.000017899723,0.00021643357,0.00020677065,0.29075617,0.00199937,0.6919877,0.0009945282,0.013345803],"study_design_scores_gemma":[0.000012556943,0.000043382784,0.00012874015,0.000010948392,0.000004464175,0.00003467579,0.00002822791,0.756631,0.00021742881,0.24200808,0.0008706327,0.000009795224],"about_ca_topic_score_codex":0.0021439388,"about_ca_topic_score_gemma":0.0014399319,"teacher_disagreement_score":0.004159636,"about_ca_system_score_codex":0.00058166514,"about_ca_system_score_gemma":0.0004490166,"threshold_uncertainty_score":0.01391536},"labels":[],"label_agreement":null},{"id":"W2463409156","doi":"10.1016/j.automatica.2018.05.005","title":"Inversion-based output tracking and unknown input reconstruction of square discrete-time linear systems","year":2018,"lang":"en","type":"preprint","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Concordia University","funders":"","keywords":"Minimum phase; Control theory (sociology); Inversion (geology); Unit circle; Tracking (education); Observer (physics); Computer science; Filter (signal processing); Mathematics; Phase (matter); Upper and lower bounds; Algorithm; Control (management); Artificial intelligence","score_opus":0.015063547042502439,"score_gpt":0.24443402173483275,"score_spread":0.22937047469233032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463409156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01874351,0.00012945267,0.9793881,0.000092239374,0.000029904815,0.000020182537,0.000020394597,0.0001722721,0.0014039181],"genre_scores_gemma":[0.829381,0.00023279956,0.16528535,0.00009326607,0.000040012827,0.00007438329,0.00014280593,0.000080731144,0.004669599],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997173,0.00006632937,0.000013681666,0.00006832345,0.00010156706,0.00003283119],"domain_scores_gemma":[0.99932766,0.00038859705,0.000059860777,0.00007096356,0.00013298703,0.000020084837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006508609,0.0005309208,0.0005495028,0.00024341614,0.00024692735,0.000694065,0.00050060253,0.0010125403,0.0015538578],"category_scores_gemma":[0.0031674844,0.00037539116,0.00037113114,0.00030923655,0.00063734583,0.0007254301,0.00081379147,0.0011860377,0.00035585635],"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":[0.00044667328,0.00010534179,0.0008529467,0.00032694277,0.00007522639,0.00014289081,0.00032252973,0.7199928,0.03431964,0.020358978,0.0012917871,0.22176427],"study_design_scores_gemma":[0.000007998005,0.00002684857,0.000113610455,0.0000047344693,0.0000051441602,0.0000199987,0.000006191257,0.99441963,0.003623788,0.0015291647,0.00023784349,0.000005028687],"about_ca_topic_score_codex":0.0029162436,"about_ca_topic_score_gemma":0.002206934,"teacher_disagreement_score":0.0029162436,"about_ca_system_score_codex":0.00028936027,"about_ca_system_score_gemma":0.0006994688,"threshold_uncertainty_score":0.005798459},"labels":[],"label_agreement":null},{"id":"W2529970964","doi":"10.1109/tac.2016.2616644","title":"Stability Analysis of Discrete-Time Infinite-Horizon Optimal Control With Discounted Cost","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":109,"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":"Australian Research Council; Agence Universitaire de la Francophonie; Agence Nationale de la Recherche","keywords":"Controllability; Robustness (evolution); Discounting; Control theory (sociology); Stability (learning theory); Mathematics; Lyapunov function; Mathematical optimization; Discrete time and continuous time; Optimal control; Sequence (biology); Bellman equation; Nonlinear system; Computer science; Applied mathematics; Control (management); Economics","score_opus":0.008061752130508127,"score_gpt":0.23248288229923736,"score_spread":0.22442113016872922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529970964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11660307,0.0006527432,0.8743084,0.0003984916,0.000045251014,0.0000415459,0.00007815245,0.00012505411,0.0077472166],"genre_scores_gemma":[0.98966134,0.00018551068,0.008181924,0.00002258457,0.0000094581355,0.0000366852,0.000034083932,0.000014092606,0.0018543198],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995875,0.00012318394,0.000020434047,0.00007625607,0.00013108236,0.000061588544],"domain_scores_gemma":[0.9987697,0.0007136669,0.00019667658,0.000045854955,0.00021738186,0.000056651017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013381597,0.00062627206,0.00062816974,0.00048394248,0.0003280972,0.0010866185,0.0007961539,0.0006257962,0.0011486423],"category_scores_gemma":[0.003203849,0.0003042998,0.00056249165,0.00028913908,0.0011645877,0.00064496504,0.0007222865,0.00068314123,0.0000916663],"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":[0.000068131136,0.000015795158,0.000390777,0.0000705354,0.000038718717,0.000079269616,0.000056482106,0.95894957,0.0030951842,0.03329246,0.00014203311,0.003801146],"study_design_scores_gemma":[0.0000038793023,0.000013627162,0.00007971788,0.0000040466825,0.0000046285836,0.000005158853,0.0000045282154,0.9945986,0.00035410645,0.004847674,0.00008051463,0.000003461796],"about_ca_topic_score_codex":0.00581756,"about_ca_topic_score_gemma":0.002188971,"teacher_disagreement_score":0.00581756,"about_ca_system_score_codex":0.0017612049,"about_ca_system_score_gemma":0.0011490646,"threshold_uncertainty_score":0.012778461},"labels":[],"label_agreement":null},{"id":"W2588293788","doi":"10.1007/s40815-016-0284-8","title":"A Residual Gradient Fuzzy Reinforcement Learning Algorithm for Differential Games","year":2017,"lang":"en","type":"article","venue":"International Journal of Fuzzy Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":19,"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":"Reinforcement learning; Algorithm; Residual; Computer science; Weighted Majority Algorithm; Convergence (economics); Fuzzy logic; Artificial intelligence; Mathematics; Mathematical optimization; Wake-sleep algorithm; Artificial neural network; Generalization error","score_opus":0.018618079922298057,"score_gpt":0.2851494187181415,"score_spread":0.2665313387958434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588293788","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009284125,0.00013527008,0.98802674,0.00009928626,0.000061438834,0.000059811046,0.000013298653,0.00021846053,0.0021015976],"genre_scores_gemma":[0.5036252,0.00021181046,0.48790315,0.00019800584,0.00007006413,0.00034111983,0.00008259053,0.00012354141,0.0074444884],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996834,0.000106796055,0.000015966201,0.00006115581,0.00008841739,0.000044275715],"domain_scores_gemma":[0.999438,0.00029835964,0.000031982847,0.00003276791,0.00015059947,0.000048325874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012791815,0.00064788957,0.0014982519,0.00051760045,0.0004144222,0.0006843343,0.0016564525,0.0013674079,0.003676849],"category_scores_gemma":[0.0020290734,0.00038751806,0.00050019304,0.0003439793,0.0007808998,0.00071445614,0.0012285882,0.0012118685,0.00061284803],"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":[0.00019997588,0.00014847488,0.0004265029,0.000113479444,0.00006174956,0.00008496899,0.00010185074,0.80918795,0.0030562056,0.034695752,0.0022809014,0.14964221],"study_design_scores_gemma":[0.00002207785,0.000037969297,0.00002545681,0.0000040638433,0.000004592145,0.000008846562,0.0000026220287,0.9975504,0.0001695064,0.0018595734,0.0003109914,0.000003957299],"about_ca_topic_score_codex":0.0053235153,"about_ca_topic_score_gemma":0.003395457,"teacher_disagreement_score":0.0053235153,"about_ca_system_score_codex":0.00075665204,"about_ca_system_score_gemma":0.00124799,"threshold_uncertainty_score":0.0123003125},"labels":[],"label_agreement":null},{"id":"W2604485348","doi":"10.1155/2017/4575926","title":"Online Adaptive Optimal Control of Vehicle Active Suspension Systems Using Single‐Network Approximate Dynamic Programming","year":2017,"lang":"en","type":"article","venue":"Mathematical Problems in Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Concordia University","funders":"Zhejiang University of Technology; Zhejiang University; National Natural Science Foundation of China","keywords":"Control theory (sociology); Sprung mass; Dynamic programming; Active suspension; Optimal control; Lyapunov function; Suspension (topology); Linear-quadratic regulator; Adaptive control; Controller (irrigation); Hamilton–Jacobi–Bellman equation; Parametric statistics; Computer science; Engineering; Mathematics; Mathematical optimization; Control engineering; Control (management); Nonlinear system; Actuator","score_opus":0.022306285279354316,"score_gpt":0.2466972457208165,"score_spread":0.22439096044146217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604485348","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04295298,0.00023106989,0.9523077,0.00015349535,0.000046739475,0.00003147687,0.000022362714,0.0001801604,0.004074012],"genre_scores_gemma":[0.97510433,0.00016667285,0.022468295,0.000034731824,0.000025167652,0.0000997717,0.00003083561,0.000013995075,0.0020562445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982774,0.00004231736,0.000008975787,0.000041967505,0.000050215353,0.000028857658],"domain_scores_gemma":[0.99966836,0.00018211777,0.00005548545,0.000014132249,0.000065888526,0.000013966417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041786354,0.0005814454,0.00067610055,0.00022729374,0.00035636895,0.0007816945,0.0005542778,0.0005241822,0.0007806724],"category_scores_gemma":[0.0007349647,0.00033565526,0.00036070799,0.0002954406,0.00058154325,0.00042280622,0.0005789701,0.00061859813,0.00009903876],"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":[0.000039522252,0.000022457058,0.0001545477,0.000042889915,0.000018309855,0.000036517373,0.000033256358,0.9790365,0.0021578427,0.0027292965,0.00019288126,0.015535898],"study_design_scores_gemma":[0.000003257374,0.000015659376,0.000032393862,8.8627525e-7,0.0000017614411,0.0000023755983,0.0000021797744,0.9994042,0.0001318285,0.0003137714,0.00009046359,0.0000012209806],"about_ca_topic_score_codex":0.007974653,"about_ca_topic_score_gemma":0.0047833305,"teacher_disagreement_score":0.007974653,"about_ca_system_score_codex":0.00043513687,"about_ca_system_score_gemma":0.00073218025,"threshold_uncertainty_score":0.015856445},"labels":[],"label_agreement":null},{"id":"W2708409974","doi":"10.1016/j.neunet.2017.05.013","title":"Adaptive near-optimal neuro controller for continuous-time nonaffine nonlinear systems with constrained input","year":2017,"lang":"en","type":"article","venue":"Neural Networks","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":27,"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; Concordia University","funders":"","keywords":"Control theory (sociology); Nonlinear system; Computer science; Controller (irrigation); Artificial intelligence; Control (management); Physics","score_opus":0.01076070531881443,"score_gpt":0.22836813267640643,"score_spread":0.217607427357592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2708409974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058437087,0.0006332735,0.931323,0.0003224446,0.00023223185,0.000058686277,0.000038410835,0.0003102675,0.00864452],"genre_scores_gemma":[0.97578806,0.00021584211,0.019447416,0.00010646684,0.000057526042,0.00008515471,0.00002929827,0.000022336251,0.00424786],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997855,0.00004197706,0.000011234216,0.00006214359,0.00006693735,0.000032246004],"domain_scores_gemma":[0.99956125,0.00018680742,0.00007547681,0.000023182614,0.00013007004,0.000023161356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005373381,0.00073660753,0.0006202245,0.0002992866,0.0004633527,0.00088731654,0.0007323142,0.0009410044,0.0017283437],"category_scores_gemma":[0.001502709,0.00034418955,0.00026730512,0.0002894055,0.00073736813,0.00058556226,0.00092138664,0.00082354504,0.00022688496],"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":[0.00020229431,0.000089771325,0.00036123235,0.00014855758,0.00004893702,0.00015852784,0.00012826118,0.92353916,0.009049409,0.013493081,0.0014345472,0.051346224],"study_design_scores_gemma":[0.0000098938435,0.000033292134,0.00010172549,0.0000040749064,0.0000042431075,0.000010539226,0.000005323765,0.9977851,0.00043578728,0.001389816,0.00021592167,0.0000042835095],"about_ca_topic_score_codex":0.0068893344,"about_ca_topic_score_gemma":0.0062837447,"teacher_disagreement_score":0.0068893344,"about_ca_system_score_codex":0.0005616329,"about_ca_system_score_gemma":0.0007642454,"threshold_uncertainty_score":0.013698459},"labels":[],"label_agreement":null},{"id":"W2737014169","doi":"10.1016/j.neucom.2017.07.027","title":"Adaptive critics based cooperative control scheme for islanded Microgrids","year":2017,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":14,"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 Ottawa","funders":"Deanship of Scientific Research, King Faisal University; King Fahd University of Petroleum and Minerals","keywords":"Computer science; Scheme (mathematics); Synchronization (alternating current); Graph; Adaptive control; Control (management); Function (biology); Distributed generation; Distributed computing; Mathematical optimization; Artificial intelligence; Theoretical computer science; Mathematics; Engineering; Telecommunications","score_opus":0.025456849660838873,"score_gpt":0.28568807393149687,"score_spread":0.260231224270658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737014169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05822059,0.00039740172,0.9285246,0.00027416222,0.00021698898,0.00007224731,0.00003967322,0.00054838223,0.0117059965],"genre_scores_gemma":[0.9819087,0.000098424665,0.013371433,0.000059859827,0.000031660755,0.00007037838,0.000025852516,0.000016035208,0.0044177924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998179,0.000040466308,0.000011973402,0.0000509678,0.000047612895,0.00003125205],"domain_scores_gemma":[0.99971586,0.00006151309,0.000040573465,0.000024991532,0.00013581669,0.000021268861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046916876,0.0007511034,0.00065105414,0.000246542,0.0005330568,0.00082745054,0.0011129619,0.0006826385,0.0020001412],"category_scores_gemma":[0.0005815554,0.00026294735,0.00031842277,0.00028251094,0.00043124205,0.0004634108,0.00081602356,0.000735698,0.00033141702],"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":[0.00019384123,0.00007469703,0.0004415975,0.00012268663,0.00007362443,0.00019650454,0.00017486663,0.9230261,0.011035054,0.0059086587,0.0020833309,0.05666896],"study_design_scores_gemma":[0.000016565165,0.00006854967,0.00010637258,0.0000047142285,0.0000126715895,0.00001700146,0.0000119015185,0.99801147,0.00062914763,0.00067186373,0.00044456378,0.000005204434],"about_ca_topic_score_codex":0.0049229497,"about_ca_topic_score_gemma":0.006248257,"teacher_disagreement_score":0.0049229497,"about_ca_system_score_codex":0.00038578548,"about_ca_system_score_gemma":0.00046617904,"threshold_uncertainty_score":0.009788632},"labels":[],"label_agreement":null},{"id":"W2770533010","doi":"10.1504/ijdsss.2017.10008987","title":"Policy iteration and coupled Riccati solutions for dynamic graphical games","year":2017,"lang":"en","type":"article","venue":"International Journal of Digital Signals and Smart Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"Computer science; Nash equilibrium; Graph; Convergence (economics); Reinforcement learning; Mathematical optimization; Mathematics; Theoretical computer science; Artificial intelligence","score_opus":0.01823689569409537,"score_gpt":0.29038850178871645,"score_spread":0.2721516060946211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770533010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005624935,0.00018892145,0.98736286,0.00024757185,0.000043292024,0.000033808494,0.000025155412,0.00008234145,0.0063911],"genre_scores_gemma":[0.8074038,0.00070622645,0.1750176,0.00024368461,0.00010433762,0.00042617702,0.00012802538,0.00012524934,0.015844995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992855,0.000297813,0.000027100397,0.0001269265,0.00018035214,0.00008241718],"domain_scores_gemma":[0.9990287,0.0006126422,0.00012568252,0.000043695884,0.00012900899,0.00006031003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095662335,0.00099661,0.0008790796,0.0005849372,0.00035353244,0.0009634478,0.0010297312,0.0011985719,0.0033626405],"category_scores_gemma":[0.0031021081,0.00043273624,0.00078981783,0.0006075256,0.0016491541,0.0009573359,0.0013856937,0.0015466838,0.0004917437],"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":[0.00003553157,0.000036517307,0.0002186924,0.00008130955,0.000037042882,0.000084536696,0.00009931111,0.6824676,0.0016665341,0.2996576,0.0012556275,0.014359716],"study_design_scores_gemma":[0.000008916719,0.000014624401,0.000032316384,0.000004479146,0.0000031523234,0.000013767996,0.000005159395,0.95651096,0.00018706883,0.042617742,0.0005956908,0.000006133522],"about_ca_topic_score_codex":0.003387812,"about_ca_topic_score_gemma":0.0022089467,"teacher_disagreement_score":0.003387812,"about_ca_system_score_codex":0.0010571434,"about_ca_system_score_gemma":0.0012094693,"threshold_uncertainty_score":0.011249125},"labels":[],"label_agreement":null},{"id":"W2783810978","doi":"10.1109/iris.2017.8250107","title":"Multi-agent reinforcement learning approach based on reduced value function approximations","year":2017,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":17,"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":"Reinforcement learning; Bellman equation; Convergence (economics); Computer science; Mathematical optimization; Graph; Function approximation; Artificial neural network; Function (biology); Markov decision process; Artificial intelligence; Mathematics; Theoretical computer science; Markov process","score_opus":0.033509293003429586,"score_gpt":0.2669293575365366,"score_spread":0.23342006453310704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783810978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068322895,0.00013910886,0.9903831,0.00012660005,0.000031448606,0.000023421311,0.000011928327,0.00016748109,0.0022845648],"genre_scores_gemma":[0.7905774,0.00026778216,0.20375262,0.00012900154,0.000056752255,0.00022354159,0.000070831884,0.00009150798,0.0048306193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954516,0.00018926722,0.000015203981,0.00006466621,0.00014098249,0.00004469636],"domain_scores_gemma":[0.99929094,0.00041834216,0.00006995454,0.000050692226,0.00013044597,0.000039630224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008235368,0.0006378317,0.001268667,0.00042851226,0.00031073877,0.00072129193,0.0014994565,0.0008315143,0.0021032149],"category_scores_gemma":[0.0019957286,0.00034920682,0.00053738314,0.00030775627,0.00072000764,0.00084789284,0.00077307585,0.0013128776,0.00038639075],"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":[0.00002732002,0.000026874746,0.0001521188,0.000038103575,0.000028960178,0.000050605275,0.00004003653,0.9582337,0.0007701286,0.024764046,0.00041948006,0.015448581],"study_design_scores_gemma":[0.0000030234305,0.0000060182883,0.00000906439,0.0000011685569,0.0000013927457,0.0000029157684,0.0000011438672,0.99729854,0.00007430888,0.0024585018,0.00014280927,0.0000012646384],"about_ca_topic_score_codex":0.0043184855,"about_ca_topic_score_gemma":0.0024993133,"teacher_disagreement_score":0.0043184855,"about_ca_system_score_codex":0.00082729285,"about_ca_system_score_gemma":0.00094235205,"threshold_uncertainty_score":0.008586705},"labels":[],"label_agreement":null},{"id":"W2792955766","doi":"10.1109/intellisys.2017.8324243","title":"A comparative study of the optimal control design using evolutionary algorithms: Application on a close-loop system","year":2017,"lang":"en","type":"article","venue":"2017 Intelligent Systems Conference (IntelliSys)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"École de Technologie Supérieure","funders":"","keywords":"Control theory (sociology); PID controller; Controller (irrigation); Linkage (software); Computer science; Evolutionary algorithm; Full state feedback; Stability (learning theory); Linear system; Optimal control; Control system; Open-loop controller; State (computer science); Control engineering; Algorithm; Control (management); Closed loop; Mathematics; Engineering; Mathematical optimization; Artificial intelligence; Temperature control","score_opus":0.10519427667976203,"score_gpt":0.32579997793991383,"score_spread":0.2206057012601518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792955766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33214998,0.0016031973,0.649632,0.00023333692,0.000063865205,0.00014968509,0.000016406822,0.0002469359,0.015904645],"genre_scores_gemma":[0.9527518,0.0002707139,0.045530267,0.000025804604,0.000008753674,0.00004938099,0.00001316896,0.00001477634,0.0013353049],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963176,0.00013964275,0.000018688466,0.000048820286,0.00012703806,0.000033975317],"domain_scores_gemma":[0.9992023,0.00052996946,0.00004581072,0.000046026435,0.00015801722,0.000017813509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094842433,0.00043808692,0.00066486694,0.00052587246,0.00035082633,0.00069531426,0.0003371276,0.0009902084,0.0012605205],"category_scores_gemma":[0.00291136,0.00018054973,0.0003648023,0.00025476073,0.00031777954,0.00042024662,0.00031988142,0.0003834707,0.000104777915],"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":[0.00016344077,0.00017516167,0.0008571487,0.000190951,0.000071920906,0.00012149153,0.000097440374,0.9103924,0.009924299,0.0045781457,0.00015689744,0.073270716],"study_design_scores_gemma":[0.000019522044,0.00027520058,0.0006200328,0.000010316455,0.000019482502,0.000039997805,0.000023633209,0.9944112,0.0032944283,0.0006737302,0.00060359767,0.000008915546],"about_ca_topic_score_codex":0.001499113,"about_ca_topic_score_gemma":0.0009207715,"teacher_disagreement_score":0.001499113,"about_ca_system_score_codex":0.00024258645,"about_ca_system_score_gemma":0.0003290363,"threshold_uncertainty_score":0.00501585},"labels":[],"label_agreement":null},{"id":"W2803623613","doi":"10.1109/tnnls.2018.2832025","title":"Optimal Synchronization Control of Multiagent Systems With Input Saturation via Off-Policy Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Victoria","funders":"Australian Research Council; Higher Education Discipline Innovation Project; Youth Innovation Promotion Association of the Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Hamilton–Jacobi–Bellman equation; Reinforcement learning; Optimal control; Computer science; Synchronization (alternating current); Controller (irrigation); Control theory (sociology); Mathematical optimization; Artificial neural network; Bellman equation; Control (management); Mathematics; Artificial intelligence","score_opus":0.0066463272838310685,"score_gpt":0.2161807311212928,"score_spread":0.20953440383746172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803623613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10685088,0.0002888416,0.8865497,0.0003478783,0.000054474425,0.000072126575,0.000022745166,0.00033706654,0.005476264],"genre_scores_gemma":[0.9884673,0.000051215604,0.010310988,0.00004172329,0.000009900402,0.00005205101,0.0000125646475,0.000011978436,0.001042263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966335,0.0001135174,0.000016237704,0.00006977523,0.00007642275,0.000060762122],"domain_scores_gemma":[0.9989974,0.0005572347,0.00019026862,0.000053386862,0.00014192643,0.00005978646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010452315,0.0007795766,0.00078092323,0.00031001942,0.00039587432,0.0006705157,0.00069733,0.00076519715,0.0010792526],"category_scores_gemma":[0.0025049758,0.00031801016,0.00032037127,0.00022738414,0.0010782825,0.00060570065,0.0011978288,0.0008087049,0.00013135443],"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":[0.00005746921,0.00002746155,0.0004048295,0.000035322555,0.000018537838,0.00007508255,0.000059468126,0.98293173,0.0013589335,0.0066697155,0.000165782,0.008195774],"study_design_scores_gemma":[0.000008151831,0.000019092886,0.000039337418,0.0000025049483,0.0000024159724,0.0000039780493,0.0000042536217,0.99824023,0.0001898769,0.0014141025,0.00007421057,0.0000019034245],"about_ca_topic_score_codex":0.005544028,"about_ca_topic_score_gemma":0.0027000294,"teacher_disagreement_score":0.005544028,"about_ca_system_score_codex":0.00074178365,"about_ca_system_score_gemma":0.00085487246,"threshold_uncertainty_score":0.011023521},"labels":[],"label_agreement":null},{"id":"W2805646502","doi":"10.1109/syscon.2018.8369536","title":"Applying expectation-maximization evaluation on approximate optimal control","year":2018,"lang":"en","type":"article","venue":"2018 Annual IEEE International Systems Conference (SysCon)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 New Brunswick","funders":"","keywords":"Maximization; Iterative learning control; Reinforcement learning; Computer science; Frame (networking); Optimal control; Trajectory; Convergence (economics); Tracking (education); Task (project management); Generator (circuit theory); Artificial intelligence; Mathematical optimization; Expectation–maximization algorithm; Control theory (sociology); Control (management); Mathematics; Power (physics); Engineering; Maximum likelihood","score_opus":0.035015107107010036,"score_gpt":0.3010516916635031,"score_spread":0.26603658455649304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805646502","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003003718,0.000117103744,0.99545646,0.000106902124,0.000014787474,0.00002203386,0.0000069170546,0.00010267068,0.0011694499],"genre_scores_gemma":[0.6522849,0.0003745944,0.34236157,0.00030932124,0.00010985279,0.00035696628,0.0001233919,0.0002594492,0.0038198899],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99737823,0.0015936574,0.00011177435,0.00024523906,0.00051352323,0.00015760276],"domain_scores_gemma":[0.99471927,0.003972937,0.00024122313,0.00027484907,0.000684206,0.00010748587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072863903,0.0014006364,0.0019431832,0.0008148231,0.00043765677,0.0015633203,0.0015960627,0.0016076326,0.002412819],"category_scores_gemma":[0.017570024,0.00068117597,0.0006232713,0.0007458812,0.00193935,0.0020499278,0.0019849874,0.0016028419,0.00041581076],"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":[0.000060860908,0.000027580349,0.0002266774,0.00007600855,0.000034428554,0.00003415281,0.000046719568,0.9354173,0.00049430685,0.042474907,0.00043257538,0.02067456],"study_design_scores_gemma":[0.0000036701206,0.00001696728,0.000019043468,0.000006829279,0.0000020818472,0.0000044293083,0.000002400693,0.9924825,0.00016607434,0.0071590953,0.00013407707,0.0000027663816],"about_ca_topic_score_codex":0.004090538,"about_ca_topic_score_gemma":0.0022068773,"teacher_disagreement_score":0.0072863903,"about_ca_system_score_codex":0.0019804442,"about_ca_system_score_gemma":0.0016267534,"threshold_uncertainty_score":0.038534522},"labels":[],"label_agreement":null},{"id":"W2885245712","doi":"10.1109/tcyb.2018.2859801","title":"Functional Nonlinear Model Predictive Control Based on Adaptive Dynamic Programming","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":88,"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":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Model predictive control; Control theory (sociology); Optimal control; Robustness (evolution); Nonlinear system; Dynamic programming; Computer science; Mathematical optimization; Artificial neural network; Lyapunov function; Mathematics; Control (management); Artificial intelligence","score_opus":0.014439540201730003,"score_gpt":0.23581651935001469,"score_spread":0.2213769791482847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885245712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004716059,0.0003599611,0.9891873,0.0001121807,0.00006319239,0.000019106004,0.00001737254,0.00019498405,0.0053299707],"genre_scores_gemma":[0.8939598,0.0007622859,0.09897691,0.00013651368,0.00012003528,0.00016156488,0.000100752426,0.00005768987,0.005724477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997907,0.000055561188,0.000009868519,0.000047580008,0.00007500264,0.000021345417],"domain_scores_gemma":[0.9997795,0.00011314451,0.000025573087,0.000018020042,0.000054492266,0.000009218443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004345015,0.0007043727,0.000639896,0.00031272642,0.00031879242,0.0007473671,0.0008491004,0.0005682598,0.0012351983],"category_scores_gemma":[0.0007679573,0.00023903689,0.0003913497,0.00045857596,0.000602811,0.0005552772,0.00059149944,0.00090911705,0.00024398121],"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":[0.000030330015,0.000025806596,0.00016335504,0.000098107615,0.0000237025,0.0000748566,0.000039491264,0.92413205,0.0017984478,0.025937542,0.00078142795,0.04689497],"study_design_scores_gemma":[0.0000020332527,0.000011869878,0.000023272498,0.0000021051283,0.0000018015115,0.000006795385,0.0000011132543,0.99777323,0.00014011402,0.0016236955,0.0004120242,0.0000019372515],"about_ca_topic_score_codex":0.0042486237,"about_ca_topic_score_gemma":0.002832989,"teacher_disagreement_score":0.0042486237,"about_ca_system_score_codex":0.00039996675,"about_ca_system_score_gemma":0.0005168232,"threshold_uncertainty_score":0.008447766},"labels":[],"label_agreement":null},{"id":"W2887000122","doi":"10.1109/civemsa.2018.8439974","title":"Model-Free Value Iteration Solution for Dynamic Graphical Games","year":2018,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Computer science; Perceptron; Reinforcement learning; A priori and a posteriori; Graph; Graphical model; Set (abstract data type); Artificial neural network; Artificial intelligence; Theoretical computer science; Mathematical optimization; Mathematics","score_opus":0.014368884697763856,"score_gpt":0.26553231667832555,"score_spread":0.2511634319805617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887000122","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006527718,0.00015305323,0.9872348,0.00025896583,0.00003383175,0.000035414345,0.000023837547,0.000074352414,0.0056579392],"genre_scores_gemma":[0.831893,0.00037100294,0.15293472,0.00022047645,0.000059285958,0.0004902896,0.00012003089,0.00010713852,0.013803948],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958247,0.00017378031,0.000014383081,0.00007585639,0.00009958809,0.000053829903],"domain_scores_gemma":[0.9991665,0.0005596342,0.00008722067,0.000030739982,0.000103000966,0.000052949454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078636326,0.00093020924,0.00085785653,0.00035685376,0.00031527126,0.00087273924,0.0009033801,0.0013012748,0.0030270203],"category_scores_gemma":[0.0030307279,0.0003636112,0.00058860064,0.00030369466,0.0010882149,0.0007106003,0.0014443403,0.0014471296,0.0003379187],"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":[0.000025942305,0.000025936419,0.0001772299,0.000059854206,0.000017780982,0.000060876613,0.000062298095,0.89176494,0.00085411867,0.097004525,0.00080380583,0.009142689],"study_design_scores_gemma":[0.000007138848,0.000009673583,0.000018981673,0.0000033762785,0.0000016667138,0.000006188808,0.0000045152724,0.9802332,0.000087157285,0.019252544,0.00037286186,0.0000027060426],"about_ca_topic_score_codex":0.003797723,"about_ca_topic_score_gemma":0.002657162,"teacher_disagreement_score":0.003797723,"about_ca_system_score_codex":0.0008745493,"about_ca_system_score_gemma":0.0012398307,"threshold_uncertainty_score":0.010126412},"labels":[],"label_agreement":null},{"id":"W2887066212","doi":"10.1109/civemsa.2018.8439951","title":"Reinforcement Learning Solution with Costate Approximation for a Flexible Wing Aircraft","year":2018,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Heuristic; Dynamic programming; Optimal control; Adaptive control; System dynamics; Function (biology); Dynamical systems theory; Dual (grammatical number); Control theory (sociology); Mathematical optimization; Control (management); Artificial intelligence; Mathematics; Algorithm","score_opus":0.015981380659571984,"score_gpt":0.2507460581578228,"score_spread":0.2347646774982508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887066212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011443791,0.00016408371,0.9856566,0.00012234597,0.000024609564,0.000020945427,0.000007002357,0.00012350234,0.0024370686],"genre_scores_gemma":[0.91715735,0.00019398097,0.07827778,0.00006558178,0.000034780864,0.00015726536,0.000026859478,0.000025208188,0.0040612225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983776,0.00005807718,0.000005898611,0.000027819986,0.000047020185,0.00002352744],"domain_scores_gemma":[0.99963474,0.00020095849,0.000046209123,0.000020141368,0.000077338205,0.0000206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056027406,0.00047179798,0.0005393812,0.00024219243,0.0002689599,0.0004835782,0.00052971346,0.0008631253,0.0015538394],"category_scores_gemma":[0.0010930108,0.00026606838,0.0003527425,0.00023161573,0.0006798973,0.00033614633,0.0007357316,0.00090123806,0.000207984],"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":[0.000020575879,0.000012066292,0.0001392063,0.00002856253,0.000010921995,0.00003725235,0.000029243944,0.9815382,0.0010888934,0.005785902,0.00020940295,0.011099734],"study_design_scores_gemma":[0.0000029346295,0.00001310902,0.00001994298,0.0000014468927,0.0000011082947,0.0000034457114,0.0000017142897,0.9990301,0.00009530374,0.0006824012,0.00014717216,0.0000012682522],"about_ca_topic_score_codex":0.005493876,"about_ca_topic_score_gemma":0.0029915797,"teacher_disagreement_score":0.005493876,"about_ca_system_score_codex":0.00047601355,"about_ca_system_score_gemma":0.0008154254,"threshold_uncertainty_score":0.010923803},"labels":[],"label_agreement":null},{"id":"W2897010625","doi":"10.3390/robotics7040066","title":"Model-Free Gradient-Based Adaptive Learning Controller for an Unmanned Flexible Wing Aircraft","year":2018,"lang":"en","type":"article","venue":"Robotics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"Ontario Centres of Excellence","keywords":"Optimal control; Control theory (sociology); Controller (irrigation); Reinforcement learning; Computer science; Adaptive control; Mathematical optimization; Heuristic; Dynamic programming; Dynamical systems theory; Aerodynamics; Gradient descent; Artificial neural network; Control engineering; Mathematics; Artificial intelligence; Control (management); Engineering","score_opus":0.042728730709356906,"score_gpt":0.27880226149812287,"score_spread":0.23607353078876597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897010625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035311773,0.0005453738,0.9535463,0.0002749925,0.000112708476,0.00006809885,0.00003449358,0.00062031834,0.009486075],"genre_scores_gemma":[0.96273065,0.00018360274,0.032806225,0.00006637828,0.000030589832,0.00011340644,0.000035188074,0.000021468475,0.0040124445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987197,0.000020506988,0.0000063237667,0.00003431485,0.000048070546,0.000018862649],"domain_scores_gemma":[0.99983954,0.00004948818,0.000036141362,0.000011559486,0.000054649485,0.000008568222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035540762,0.0005930476,0.00041274325,0.00021563996,0.00034653398,0.00054217875,0.0007448455,0.00059887336,0.001406726],"category_scores_gemma":[0.00058693293,0.00022334162,0.00030998807,0.00022073367,0.0004670882,0.00031690398,0.0005186069,0.00080371357,0.00024666003],"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":[0.000047614445,0.000029542723,0.00019794052,0.000052762018,0.000022826647,0.000072803734,0.000052617,0.9606687,0.0046602525,0.005069447,0.0007165701,0.028408978],"study_design_scores_gemma":[0.000004701706,0.000021066619,0.000044760975,0.0000020154323,0.0000025352047,0.0000050493245,0.0000017170961,0.999097,0.00027532488,0.00032497526,0.000218895,0.0000019245665],"about_ca_topic_score_codex":0.008801944,"about_ca_topic_score_gemma":0.006293954,"teacher_disagreement_score":0.008801944,"about_ca_system_score_codex":0.0004706523,"about_ca_system_score_gemma":0.0008000534,"threshold_uncertainty_score":0.017501414},"labels":[],"label_agreement":null},{"id":"W2904050798","doi":"10.1109/iccss.2018.8572428","title":"Adaptive Critic Optimal Fuzzy Control for Quarter-Car Suspension Systems","year":2018,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":4,"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":"Fuzzy control system; Control theory (sociology); Computer science; Suspension (topology); Fuzzy logic; Adaptive control; Active suspension; Quarter (Canadian coin); Control engineering; Control (management); Engineering; Artificial intelligence; Mathematics; Actuator","score_opus":0.01547698783135517,"score_gpt":0.25287297785473495,"score_spread":0.23739599002337977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904050798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07543231,0.00079874106,0.90821767,0.0006245574,0.00019028061,0.00005363611,0.000078507306,0.00042255234,0.014181836],"genre_scores_gemma":[0.9853808,0.00023884574,0.009105958,0.00005040902,0.000025126208,0.000057737754,0.000036152767,0.00001414853,0.005090849],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997805,0.000054949516,0.000010428137,0.000051557516,0.00006437054,0.000038273938],"domain_scores_gemma":[0.99962604,0.00016633703,0.00006565428,0.000015623438,0.00010407368,0.000022324586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057197333,0.00080619386,0.00078364334,0.0003236916,0.0005415745,0.0010536129,0.0006623874,0.0010115317,0.0018256059],"category_scores_gemma":[0.0007970139,0.00037693838,0.00045218307,0.0003176602,0.0007396826,0.0004758915,0.0006912661,0.0009929521,0.00021005486],"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":[0.00008176487,0.000020178193,0.00021160132,0.00007275328,0.00002369168,0.00009963228,0.00007025533,0.97947615,0.0029337602,0.0067675947,0.0005063763,0.009736297],"study_design_scores_gemma":[0.000005511521,0.000019330228,0.000047033034,0.000001912255,0.0000030357414,0.0000044730773,0.00000471715,0.99886143,0.00015754988,0.0007118019,0.000180157,0.0000029634311],"about_ca_topic_score_codex":0.017945115,"about_ca_topic_score_gemma":0.009930589,"teacher_disagreement_score":0.017945115,"about_ca_system_score_codex":0.0010674807,"about_ca_system_score_gemma":0.0010976059,"threshold_uncertainty_score":0.035681307},"labels":[],"label_agreement":null},{"id":"W2912067707","doi":"10.1002/acs.2964","title":"Editorial for the Special Issue on Learning‐based Adaptive Control: Theory and Applications","year":2019,"lang":"en","type":"article","venue":"International Journal of Adaptive Control and Signal Processing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Computer science; Adaptive learning; Adaptive control; Artificial intelligence; Control (management); Machine learning; Data science","score_opus":0.006952249410241171,"score_gpt":0.2509708647991017,"score_spread":0.24401861538886052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912067707","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000074214666,0.0023870477,0.00057638175,0.011882043,0.9832054,0.000018655419,0.000057494257,0.000079179095,0.0017196933],"genre_scores_gemma":[0.0006104725,0.0021927229,0.00015489887,0.003777034,0.98395145,0.000016857006,0.000041806124,0.00006373536,0.009191034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973635,0.00023019729,0.00032935143,0.00058099756,0.0012740897,0.0002219216],"domain_scores_gemma":[0.98886114,0.0028273338,0.00069322024,0.00037192646,0.0053255893,0.0019206918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002889625,0.002856071,0.0027426537,0.002424732,0.0016166369,0.0055663683,0.0022732131,0.005980007,0.03353471],"category_scores_gemma":[0.011150789,0.000851962,0.0021589706,0.0008326652,0.0011599737,0.0028851742,0.001072055,0.009002675,0.018553302],"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":[0.000056944602,0.000023500674,0.00004327203,0.00023352985,0.000022496577,0.000075280375,0.000008215,0.0000962018,0.0002414197,0.00050122483,0.9853439,0.013354057],"study_design_scores_gemma":[0.000056667253,0.000084782936,0.0004577899,0.00023982907,0.000055519293,0.0002542066,0.000021616628,0.0006525465,0.0004358967,0.0022381023,0.995479,0.000023952447],"about_ca_topic_score_codex":0.0003506558,"about_ca_topic_score_gemma":0.00073061406,"teacher_disagreement_score":0.03353471,"about_ca_system_score_codex":0.0012243267,"about_ca_system_score_gemma":0.0014784625,"threshold_uncertainty_score":0.11218476},"labels":[],"label_agreement":null},{"id":"W2912832158","doi":"10.1109/tcyb.2018.2890046","title":"Optimal Output Regulation of Linear Discrete-Time Systems With Unknown Dynamics Using Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Alberta","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project; Northeastern University; National Natural Science Foundation of China","keywords":"Reinforcement learning; Optimization problem; Optimal control; Mathematical optimization; Control theory (sociology); Computer science; Discrete time and continuous time; Discrete optimization; Noise (video); System dynamics; Control (management); Mathematics; Artificial intelligence","score_opus":0.009236036983152505,"score_gpt":0.22108144031156662,"score_spread":0.21184540332841412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912832158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02270144,0.0002964036,0.97398245,0.00019555411,0.000043113167,0.000029225877,0.000013966315,0.00029142312,0.0024464345],"genre_scores_gemma":[0.96974504,0.00015116556,0.028378246,0.000080986894,0.000033403652,0.00008026934,0.000030093135,0.000030028948,0.0014707579],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944276,0.00018757141,0.000025708427,0.000115521936,0.00013953369,0.00008883641],"domain_scores_gemma":[0.9987803,0.0007924307,0.00017742463,0.000056393954,0.00015144097,0.000042000414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012481356,0.0010048179,0.001138707,0.0003463698,0.0003685315,0.00094658986,0.0008513303,0.00091208087,0.00092801655],"category_scores_gemma":[0.0027810957,0.00042102407,0.0004764307,0.00028518957,0.0012893958,0.00069355755,0.00086734403,0.0011894725,0.0001387926],"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":[0.00003732865,0.00003341221,0.00022116821,0.000040035997,0.000020076071,0.00003956485,0.00003936256,0.98264575,0.000896015,0.0045000874,0.00021741727,0.011309863],"study_design_scores_gemma":[0.000006569626,0.000014047637,0.000025352489,0.000002318456,0.0000022820896,0.0000028829938,0.0000018956516,0.9987404,0.00014216108,0.0009932074,0.00006698896,0.0000019366512],"about_ca_topic_score_codex":0.0072272946,"about_ca_topic_score_gemma":0.0036514197,"teacher_disagreement_score":0.0072272946,"about_ca_system_score_codex":0.0008810821,"about_ca_system_score_gemma":0.0010160804,"threshold_uncertainty_score":0.014370441},"labels":[],"label_agreement":null},{"id":"W2928373814","doi":"10.1109/tcyb.2019.2901268","title":"Granular Prediction and Dynamic Scheduling Based on Adaptive Dynamic Programming for the Blast Furnace Gas System","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Scheduling (production processes); Dynamic priority scheduling; Computer science; Mathematical optimization; Schedule; Mathematics","score_opus":0.007921224045344375,"score_gpt":0.2191847700500824,"score_spread":0.21126354600473804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2928373814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04015985,0.0002345864,0.956714,0.00017094234,0.00003609159,0.000043849024,0.000025827712,0.0002362566,0.002378647],"genre_scores_gemma":[0.95441127,0.00014227926,0.044043556,0.00004234826,0.000021510928,0.00009830418,0.000040233645,0.000023929893,0.0011764955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970335,0.00006788292,0.000016460554,0.00007458012,0.000086956665,0.000050718903],"domain_scores_gemma":[0.99951684,0.00028151137,0.00006910758,0.00002254314,0.00008307474,0.000026931144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000620171,0.0007130057,0.00083838194,0.00036704136,0.0004382137,0.0008186357,0.0006343597,0.0006260065,0.0009000393],"category_scores_gemma":[0.0014650214,0.00033239348,0.00048334335,0.0004205618,0.00059195684,0.0005880013,0.0007074596,0.0009948025,0.000080310856],"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":[0.000030410254,0.000015144324,0.00025778433,0.00001981649,0.0000099012495,0.00003228932,0.000025052874,0.9849722,0.00068099995,0.0020606725,0.00013176372,0.011763959],"study_design_scores_gemma":[0.0000016264815,0.0000050123863,0.000029579216,6.481708e-7,0.0000012385377,0.000001710312,0.0000012883164,0.9995277,0.00007149155,0.0003295581,0.00002895862,0.0000012371094],"about_ca_topic_score_codex":0.014536044,"about_ca_topic_score_gemma":0.0068142344,"teacher_disagreement_score":0.014536044,"about_ca_system_score_codex":0.0007883512,"about_ca_system_score_gemma":0.0009527135,"threshold_uncertainty_score":0.028902888},"labels":[],"label_agreement":null},{"id":"W2951873227","doi":"10.1109/tac.2019.2922953","title":"Distributed GNE Seeking Under Partial-Decision Information Over Networks via a Doubly-Augmented Operator Splitting Approach","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":148,"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":"Monotone polygon; Convergence (economics); Nash equilibrium; Operator (biology); Computation; Strongly monotone; Distributed algorithm","score_opus":0.006590390268237936,"score_gpt":0.22146990101472894,"score_spread":0.214879510746491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951873227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033610817,0.00007436909,0.9638287,0.0002194874,0.00001989168,0.0000326638,0.00001794113,0.00007089936,0.0021252662],"genre_scores_gemma":[0.8432589,0.000082190105,0.1532046,0.00010474776,0.000027387778,0.00015540876,0.000038677437,0.000037282596,0.003090929],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995189,0.00021073878,0.000015984262,0.00008472343,0.00010413182,0.00006561094],"domain_scores_gemma":[0.9988269,0.00078036945,0.0000988854,0.000080436825,0.00013159616,0.000081875354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015667776,0.00075504504,0.0010699568,0.0002871096,0.00039344843,0.0007880586,0.0011829485,0.0010900322,0.0015034655],"category_scores_gemma":[0.002922984,0.00045968147,0.0004960745,0.00028210937,0.0015225672,0.0012495749,0.0020914038,0.0010478542,0.00014552764],"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":[0.000068362235,0.000025579497,0.00020421186,0.00002761839,0.00002142925,0.00007424062,0.000059464473,0.95942307,0.0016848644,0.030066581,0.00023846707,0.008106116],"study_design_scores_gemma":[0.0000065107,0.000007660199,0.000007612934,0.0000010584486,0.0000010124947,0.0000029107769,0.0000026745888,0.99518114,0.00007863263,0.004669086,0.00004036913,0.0000012915865],"about_ca_topic_score_codex":0.0033954326,"about_ca_topic_score_gemma":0.0027414763,"teacher_disagreement_score":0.0033954326,"about_ca_system_score_codex":0.0007944109,"about_ca_system_score_gemma":0.0010600353,"threshold_uncertainty_score":0.008286059},"labels":[],"label_agreement":null},{"id":"W2963138810","doi":"10.1016/j.asoc.2019.105629","title":"Neurodynamic programming and tracking control scheme of constrained-input systems via a novel event-triggered PI algorithm","year":2019,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Dynamic programming; Control theory (sociology); Trajectory; Tracking (education); Bounded function; Artificial neural network; Tracking error; Computation; Algorithm; Mathematics; Control (management); Artificial intelligence","score_opus":0.0064897288057627935,"score_gpt":0.21646625536204842,"score_spread":0.20997652655628563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963138810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006068744,0.000065300366,0.9907673,0.00007355485,0.00003778855,0.00003136757,0.000008136652,0.00009085419,0.0028569284],"genre_scores_gemma":[0.80328494,0.00018473214,0.19032174,0.000108801614,0.00005405547,0.00026359953,0.00003675535,0.00003997937,0.0057054036],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998147,0.00003587307,0.000011012731,0.000050523086,0.00006492126,0.000023029726],"domain_scores_gemma":[0.99983203,0.00006876929,0.000024499128,0.000014376441,0.000046149446,0.000014115448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004181112,0.0005229668,0.00057945045,0.00023382127,0.00041773787,0.0008407523,0.0008917871,0.00074623025,0.0022186898],"category_scores_gemma":[0.0006804703,0.00025590492,0.00033829905,0.00033655472,0.0004774721,0.00054104126,0.00097295997,0.0008901385,0.00023347753],"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":[0.00015167418,0.000106043495,0.00029345282,0.0001308067,0.000046714635,0.00015267351,0.000122131,0.81346714,0.0099928845,0.05292369,0.0014083748,0.12120443],"study_design_scores_gemma":[0.0000067555457,0.000018916227,0.000025675503,0.0000021944827,0.0000024480664,0.000010309026,0.0000020568873,0.9974663,0.00044400012,0.0017672274,0.00025137782,0.000002651286],"about_ca_topic_score_codex":0.0017407824,"about_ca_topic_score_gemma":0.0017536142,"teacher_disagreement_score":0.0022186898,"about_ca_system_score_codex":0.00035660228,"about_ca_system_score_gemma":0.00076742726,"threshold_uncertainty_score":0.0074222684},"labels":[],"label_agreement":null},{"id":"W2967441303","doi":"10.1109/rose.2019.8790425","title":"An Online Reinforcement Learning Wing-Tracking Mechanism for Flexible Wing Aircraft","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Wing; Reinforcement learning; Mechanism (biology); Computer science; Aeronautics; Aerospace engineering; Simulation; Artificial intelligence; Engineering; Physics","score_opus":0.025428907904497814,"score_gpt":0.277794600672952,"score_spread":0.25236569276845416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967441303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046600454,0.00024724647,0.9479975,0.00017575207,0.00012263434,0.00007170806,0.000015999622,0.0008758863,0.0038927335],"genre_scores_gemma":[0.9651059,0.00008165578,0.031945363,0.000056817014,0.000026691689,0.00006591034,0.0000131225015,0.000015861564,0.0026886712],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998342,0.000034049055,0.00000960286,0.000046489502,0.00004992392,0.000025647072],"domain_scores_gemma":[0.9996779,0.0001044421,0.00007173779,0.000040221614,0.000070527676,0.00003522355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051105476,0.00041872545,0.00039408036,0.00018400831,0.00027561683,0.00035925664,0.001131952,0.00062557915,0.0016434251],"category_scores_gemma":[0.00094497873,0.00014845577,0.00025392507,0.00011572694,0.00051900576,0.0004108321,0.00063372095,0.000610407,0.0002767351],"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":[0.00027626476,0.00025023994,0.00089555717,0.00016932712,0.000077311786,0.00036969312,0.00015344785,0.7783773,0.050364867,0.026178332,0.0017740026,0.14111361],"study_design_scores_gemma":[0.00002127353,0.00009583818,0.000104006656,0.000003841571,0.0000050972985,0.00002961443,0.0000022179304,0.9962327,0.0017624439,0.0012836024,0.00045228613,0.0000070839747],"about_ca_topic_score_codex":0.0015602146,"about_ca_topic_score_gemma":0.00097076414,"teacher_disagreement_score":0.0016434251,"about_ca_system_score_codex":0.0003018645,"about_ca_system_score_gemma":0.00038041294,"threshold_uncertainty_score":0.005497813},"labels":[],"label_agreement":null},{"id":"W2967515641","doi":"10.1109/rose.2019.8790424","title":"Neurofuzzy Reinforcement Learning Control Schemes for Optimized Dynamical Performance","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Control (management); Artificial intelligence","score_opus":0.006745649804198587,"score_gpt":0.2209946881010428,"score_spread":0.21424903829684422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967515641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018578334,0.00028486885,0.97707933,0.00009454925,0.000049816066,0.000057014153,0.000010924608,0.00026584955,0.0035793574],"genre_scores_gemma":[0.89137393,0.00016870709,0.10474003,0.000054059496,0.000027433747,0.00012242406,0.00001744279,0.00002800646,0.0034680334],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980086,0.000047677742,0.0000129951595,0.000036302907,0.00008158447,0.000020498293],"domain_scores_gemma":[0.99955195,0.00018792065,0.00008799906,0.000046047415,0.00011134122,0.00001474575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081100344,0.00057664193,0.0004118856,0.0002248353,0.00022259924,0.0004776198,0.0007579207,0.00049519003,0.0016080606],"category_scores_gemma":[0.0012345633,0.00014948135,0.00022855155,0.00028147854,0.00047843225,0.0004590142,0.00045854296,0.00071469176,0.0002914373],"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":[0.00008738597,0.00011876491,0.00028714718,0.0001390107,0.000032454187,0.00007431587,0.00010835606,0.83161294,0.021191495,0.023040896,0.0011389826,0.122168176],"study_design_scores_gemma":[0.000011937382,0.00004203141,0.00007448601,0.0000057230873,0.000003863618,0.000012552839,0.000002791264,0.995333,0.0021456003,0.0015639665,0.0007985899,0.000005421472],"about_ca_topic_score_codex":0.0016921125,"about_ca_topic_score_gemma":0.0019253807,"teacher_disagreement_score":0.0016921125,"about_ca_system_score_codex":0.00057644356,"about_ca_system_score_gemma":0.00049335876,"threshold_uncertainty_score":0.0053795576},"labels":[],"label_agreement":null},{"id":"W2967692091","doi":"10.1109/rose.2019.8790432","title":"Model-Free Adaptive Control Approach Using Integral Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Adaptive control; Control (management); Reinforcement; Artificial intelligence; Engineering","score_opus":0.023251655482380784,"score_gpt":0.2321184257896034,"score_spread":0.20886677030722262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967692091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059616305,0.00011712548,0.99058753,0.000068616966,0.000026930486,0.000023282977,0.000006538207,0.00017136997,0.0030370594],"genre_scores_gemma":[0.9168585,0.00018562212,0.07899725,0.000098832155,0.000045562552,0.0001202828,0.00002834574,0.00003263776,0.003633007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996449,0.000073636744,0.000014750553,0.0000765652,0.00015092429,0.000039279705],"domain_scores_gemma":[0.999653,0.00013686248,0.000053106858,0.000040506813,0.000098024946,0.00001839603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007166868,0.00059271755,0.0006670687,0.00029205618,0.00031110246,0.00084507064,0.0010174206,0.00064415723,0.0016996413],"category_scores_gemma":[0.0009992946,0.00021904842,0.00044527295,0.0002599427,0.00073813304,0.0006358905,0.00097237434,0.0012000358,0.00025889944],"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":[0.000047403824,0.00006701287,0.00028181338,0.00007498933,0.000048247082,0.00007555874,0.000084906154,0.9024934,0.0052826637,0.02717608,0.00067291333,0.06369495],"study_design_scores_gemma":[0.0000043934783,0.00002476521,0.000029891753,0.0000024380925,0.000003962649,0.0000095677915,0.0000018564133,0.9972409,0.00043354015,0.0019155679,0.00033003345,0.0000031409077],"about_ca_topic_score_codex":0.0035132393,"about_ca_topic_score_gemma":0.0019449643,"teacher_disagreement_score":0.0035132393,"about_ca_system_score_codex":0.00056625006,"about_ca_system_score_gemma":0.0008498127,"threshold_uncertainty_score":0.0069856048},"labels":[],"label_agreement":null},{"id":"W2972407345","doi":"10.23919/acc.2019.8814309","title":"Constrained control Lyapunov function construction via approximation of static Hamilton-Jacobi-Bellman equations","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"McMaster University","funders":"","keywords":"Hamilton–Jacobi–Bellman equation; Nonlinear system; Mathematics; Lyapunov function; Classification of discontinuities; Optimal control; Bellman equation; Applied mathematics; Viscosity solution; Mathematical optimization; Mathematical analysis","score_opus":0.005842289523805856,"score_gpt":0.20276530716816488,"score_spread":0.19692301764435902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972407345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013158703,0.000061881925,0.98459923,0.00004847755,0.000012542149,0.000021678537,0.000009849761,0.00006647431,0.0020211719],"genre_scores_gemma":[0.7070676,0.00020976125,0.28905326,0.00006166393,0.000022952514,0.00029704333,0.00009722578,0.000077995355,0.0031124237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999835,0.000053119973,0.000006973528,0.000026476617,0.000060982202,0.000017349836],"domain_scores_gemma":[0.9997385,0.00013250823,0.00003299964,0.000021687354,0.000059480983,0.000014802527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065615145,0.00059769413,0.0005827417,0.00045458667,0.000409742,0.00065125426,0.0007447323,0.000625055,0.0013807946],"category_scores_gemma":[0.0016032143,0.00031697407,0.00042422028,0.00022577576,0.0005935919,0.0006784768,0.0008971765,0.00065563887,0.00021139541],"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":[0.000020632257,0.000016524498,0.00014703594,0.000048102727,0.000007977697,0.00005347075,0.000060852795,0.91060024,0.0041371984,0.0713035,0.0002810828,0.013323283],"study_design_scores_gemma":[0.0000026329917,0.000008293769,0.000015479218,0.000002980951,9.771277e-7,0.0000036532572,0.0000033639178,0.9943791,0.00042900056,0.0049510826,0.0002015547,0.0000019150764],"about_ca_topic_score_codex":0.0020918953,"about_ca_topic_score_gemma":0.001159047,"teacher_disagreement_score":0.0020918953,"about_ca_system_score_codex":0.0005727532,"about_ca_system_score_gemma":0.00079818553,"threshold_uncertainty_score":0.0046192408},"labels":[],"label_agreement":null},{"id":"W2974373467","doi":"10.3390/robotics8040082","title":"Online Multi-Objective Model-Independent Adaptive Tracking Mechanism for Dynamical Systems","year":2019,"lang":"en","type":"article","venue":"Robotics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Computer science; Reinforcement learning; Dynamical systems theory; Adaptive control; Scalability; Optimal control; Robotics; Iterative learning control; Aerodynamics; Adaptive learning; Tracking error; Control engineering; Artificial intelligence; Control theory (sociology); Control (management); Mathematical optimization; Robot; Mathematics; Engineering","score_opus":0.03195951659220993,"score_gpt":0.2699029278227233,"score_spread":0.23794341123051338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974373467","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012355202,0.00021685874,0.9841263,0.000113347436,0.00003586274,0.00004182771,0.000014694422,0.00032825329,0.0027677033],"genre_scores_gemma":[0.926957,0.00020466531,0.06816989,0.00008911703,0.00003919196,0.00024856525,0.00004375929,0.000031175325,0.00421657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999734,0.000061723586,0.0000148028275,0.00006896811,0.00008847458,0.000032139746],"domain_scores_gemma":[0.99960667,0.00015255617,0.00010355013,0.000038280825,0.00007665652,0.000022380025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091034966,0.00078454375,0.00062210835,0.00040607556,0.00038249584,0.0006921689,0.0012380689,0.00087422726,0.0021466375],"category_scores_gemma":[0.0011963772,0.00028226298,0.00044960657,0.00034581768,0.0006622652,0.0006535237,0.0011065886,0.0009529804,0.00027446775],"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":[0.00004269214,0.00005690171,0.00026375774,0.00009503332,0.000052979278,0.00008707061,0.000058926158,0.921542,0.005392509,0.026761621,0.0007692772,0.044877246],"study_design_scores_gemma":[0.000007729839,0.0000341519,0.00004294423,0.000003350762,0.0000038886906,0.0000099124645,0.0000016397743,0.997291,0.00036796115,0.0019570817,0.0002770799,0.000003315912],"about_ca_topic_score_codex":0.0020062488,"about_ca_topic_score_gemma":0.0017396781,"teacher_disagreement_score":0.0021466375,"about_ca_system_score_codex":0.00054100435,"about_ca_system_score_gemma":0.00067025534,"threshold_uncertainty_score":0.007181227},"labels":[],"label_agreement":null},{"id":"W2979612126","doi":"10.1049/iet-cta.2018.6163","title":"Online model‐free reinforcement learning for the automatic control of a flexible wing aircraft","year":2019,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Reinforcement learning; Wing; Computer science; Control (management); Control theory (sociology); Control engineering; Fixed wing; Aeronautics; Artificial intelligence; Engineering; Aerospace engineering","score_opus":0.00934140909909165,"score_gpt":0.25029503380541007,"score_spread":0.24095362470631843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979612126","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059179578,0.0003918792,0.9358497,0.00025981767,0.00006117804,0.00003764163,0.000013007967,0.00040593263,0.0038011337],"genre_scores_gemma":[0.9865173,0.000072972376,0.012256802,0.000026791531,0.000012616584,0.000035625508,0.000009855649,0.000008906096,0.0010590755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997974,0.00006574857,0.000007851521,0.000032365064,0.00006288095,0.00003371316],"domain_scores_gemma":[0.999522,0.00027075305,0.00008045703,0.000027374597,0.00007746692,0.000021989834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005992508,0.00040946752,0.00045712417,0.00016741903,0.00026865568,0.000426355,0.0005395421,0.00056703214,0.001023158],"category_scores_gemma":[0.0011917765,0.00018551845,0.00028909222,0.00013653576,0.0006605041,0.00030141676,0.00046673484,0.00084312505,0.00013871731],"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":[0.00004793291,0.000038076374,0.00022445178,0.00003636736,0.000017047136,0.00005297064,0.000033985536,0.9700342,0.002961028,0.005620758,0.00028967598,0.020643594],"study_design_scores_gemma":[0.0000046924297,0.000021305785,0.000033752967,0.0000011116284,0.0000014502433,0.0000037379891,9.724001e-7,0.9991591,0.0002109949,0.00048012755,0.00008135858,0.0000014273334],"about_ca_topic_score_codex":0.0067025363,"about_ca_topic_score_gemma":0.0039357212,"teacher_disagreement_score":0.0067025363,"about_ca_system_score_codex":0.00050248444,"about_ca_system_score_gemma":0.0009405275,"threshold_uncertainty_score":0.013327062},"labels":[],"label_agreement":null},{"id":"W2980804356","doi":"10.1007/s41315-019-00105-3","title":"Online model-free controller for flexible wing aircraft: a policy iteration-based reinforcement learning approach","year":2019,"lang":"en","type":"article","venue":"International Journal of Intelligent Robotics and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":10,"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 Ottawa","funders":"Ontario Centres of Excellence","keywords":"Aerodynamics; Reinforcement learning; Control theory (sociology); Wing; Kinematics; Controller (irrigation); Stability (learning theory); Computer science; Optimal control; Control engineering; Flight dynamics; Nonlinear system; Engineering; Control (management); Artificial intelligence; Mathematical optimization; Aerospace engineering; Mathematics","score_opus":0.019198946474780678,"score_gpt":0.2903157640076766,"score_spread":0.27111681753289596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980804356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029119054,0.00017748607,0.9660433,0.00022705013,0.000055382734,0.00005886332,0.000018378725,0.00032570795,0.0039748037],"genre_scores_gemma":[0.9606822,0.000071031274,0.037190676,0.00009217684,0.000029422881,0.00009962094,0.00002608307,0.000039148606,0.0017695887],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995938,0.00013756202,0.000018458768,0.000068100606,0.00011512319,0.00006696531],"domain_scores_gemma":[0.998645,0.0008602336,0.00013851249,0.00007125296,0.00021597673,0.000068977664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010776761,0.0007964787,0.0012607632,0.00041041986,0.00050875894,0.00079784374,0.001084466,0.0012177612,0.0024098034],"category_scores_gemma":[0.0025245827,0.00046663475,0.0005518466,0.0002233099,0.0010408513,0.0007496118,0.0012207435,0.0014722478,0.00031002884],"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":[0.000111162284,0.000091692054,0.00023240173,0.000046966477,0.000028581035,0.00006379715,0.000053602216,0.96751505,0.0012925074,0.0044975155,0.00044359872,0.025623133],"study_design_scores_gemma":[0.0000097883,0.000025858457,0.000029085119,0.0000020055875,0.0000028073598,0.0000053162316,0.0000017594685,0.99904877,0.00013159728,0.0006834101,0.000057456113,0.0000021628607],"about_ca_topic_score_codex":0.006415303,"about_ca_topic_score_gemma":0.004888696,"teacher_disagreement_score":0.006415303,"about_ca_system_score_codex":0.00065677706,"about_ca_system_score_gemma":0.0011749163,"threshold_uncertainty_score":0.01275593},"labels":[],"label_agreement":null},{"id":"W2998797223","doi":"10.1016/j.neucom.2020.01.026","title":"Near-optimal neural-network robot control with adaptive gravity compensation","year":2020,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cerebellar model articulation controller; Control theory (sociology); Computer science; Artificial neural network; Feed forward; Controller (irrigation); Inverted pendulum; Adaptive control; Lyapunov function; Bounded function; Feedforward neural network; Nonlinear system; Artificial intelligence; Control (management); Mathematics; Control engineering; Engineering","score_opus":0.01630035951098792,"score_gpt":0.21536037733356267,"score_spread":0.19906001782257476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998797223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05337621,0.00036299796,0.937647,0.00033750568,0.00017215004,0.00004273767,0.000028964896,0.00026387014,0.0077685774],"genre_scores_gemma":[0.95747006,0.00008761302,0.038745623,0.00007558292,0.000049319333,0.000053872423,0.000019841818,0.00002008739,0.0034779154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982184,0.000041276915,0.0000079599195,0.000045143952,0.000052391628,0.000031376196],"domain_scores_gemma":[0.99980205,0.00007022479,0.000038724753,0.000015443637,0.000057174246,0.00001632795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043875352,0.0005755814,0.0006217734,0.00027539697,0.00048852793,0.00054646475,0.00061239296,0.0010018895,0.0014051173],"category_scores_gemma":[0.0010964308,0.00028831355,0.00024021558,0.0003065191,0.00078050804,0.0007067103,0.0010070407,0.0005581378,0.00023215785],"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":[0.00016493755,0.000041264007,0.00025470153,0.00006143654,0.000026477506,0.00006813654,0.000052152496,0.9481383,0.0063602375,0.010825744,0.0009407224,0.03306593],"study_design_scores_gemma":[0.000007808295,0.000030602594,0.00008284549,0.0000026722607,0.0000026828016,0.000010048591,0.0000037217824,0.99736816,0.00046631,0.0018506213,0.00017066103,0.000003817738],"about_ca_topic_score_codex":0.0048122616,"about_ca_topic_score_gemma":0.0051982845,"teacher_disagreement_score":0.0048122616,"about_ca_system_score_codex":0.00049745076,"about_ca_system_score_gemma":0.00072210864,"threshold_uncertainty_score":0.009568512},"labels":[],"label_agreement":null},{"id":"W3017059342","doi":"10.1049/iet-cta.2019.0397","title":"Integral reinforcement learning solutions for a synchronisation system with constrained policies","year":2020,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Control theory (sociology); Control engineering; Mathematical optimization; Artificial intelligence; Mathematics; Control (management); Engineering","score_opus":0.01138973012840052,"score_gpt":0.22718047211648623,"score_spread":0.2157907419880857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017059342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059483282,0.00029932059,0.9293725,0.0003797363,0.000050781116,0.00005727286,0.000055698583,0.00016190512,0.010139458],"genre_scores_gemma":[0.97276443,0.00013272725,0.022382695,0.00004403029,0.00001271777,0.00009878842,0.000034556473,0.00001701394,0.0045129135],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997346,0.000075417,0.000012997,0.00006234272,0.00006327274,0.000051328596],"domain_scores_gemma":[0.9992742,0.00038144994,0.00016209611,0.000027178254,0.000111521935,0.00004358566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000701164,0.00066653045,0.000696756,0.0003529418,0.00032495218,0.00082974613,0.00061324215,0.0009320732,0.0018333191],"category_scores_gemma":[0.0017580154,0.000264194,0.00035787324,0.00030307798,0.0010858342,0.00050956116,0.0011328198,0.00085526926,0.00016232618],"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":[0.000031897776,0.000015386087,0.00019257821,0.000034161385,0.000011359324,0.000059902522,0.000056242952,0.9701245,0.0010278324,0.022942716,0.00024286473,0.0052606417],"study_design_scores_gemma":[0.000007614204,0.000012891886,0.000041059007,0.0000022498468,0.0000019866497,0.000004992146,0.0000053249123,0.9965383,0.00010748338,0.0031240871,0.0001517587,0.0000024125825],"about_ca_topic_score_codex":0.006656437,"about_ca_topic_score_gemma":0.0038790428,"teacher_disagreement_score":0.006656437,"about_ca_system_score_codex":0.0008871969,"about_ca_system_score_gemma":0.0009951954,"threshold_uncertainty_score":0.01323539},"labels":[],"label_agreement":null},{"id":"W3037738032","doi":"10.3390/robotics9030049","title":"Model-Free Optimized Tracking Control Heuristic","year":2020,"lang":"en","type":"article","venue":"Robotics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 de Moncton; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Overshoot (microwave communication); Computer science; Reinforcement learning; Heuristic; Tracking error; Controller (irrigation); Control theory (sociology); Control engineering; Artificial neural network; Iterative learning control; Tracking (education); Control (management); Engineering; Artificial intelligence","score_opus":0.03380149084032583,"score_gpt":0.23948310234438983,"score_spread":0.205681611504064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037738032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010986038,0.00019346262,0.9805931,0.00009875187,0.000029210323,0.000056764053,0.000025531064,0.0006700932,0.007347136],"genre_scores_gemma":[0.87052906,0.00015779816,0.12328536,0.00016979492,0.000028915954,0.00017838906,0.000091060014,0.00013002697,0.005429467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994999,0.00010342055,0.000029161036,0.00010873716,0.00015301951,0.000105712985],"domain_scores_gemma":[0.9994783,0.00022719688,0.00007469898,0.00008733855,0.00011000405,0.000022504037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007228774,0.0008617538,0.00094610977,0.0005742534,0.00042101022,0.0011144186,0.0012931968,0.0011082332,0.0030003353],"category_scores_gemma":[0.001605998,0.0003904356,0.0005161055,0.00044457888,0.0007708839,0.0009820154,0.0008074351,0.000861457,0.0005266779],"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":[0.000070724505,0.00004203725,0.00019441424,0.00006518716,0.000023320265,0.000048824462,0.000044933673,0.94131565,0.0020112284,0.014629479,0.0011764844,0.04037775],"study_design_scores_gemma":[0.00000974089,0.000032689426,0.00004670707,0.000007214852,0.000006090086,0.000015523026,0.0000045988013,0.9968882,0.0006539535,0.0018630245,0.00046783104,0.000004333048],"about_ca_topic_score_codex":0.0038935167,"about_ca_topic_score_gemma":0.0030104278,"teacher_disagreement_score":0.0038935167,"about_ca_system_score_codex":0.00096095196,"about_ca_system_score_gemma":0.0014270677,"threshold_uncertainty_score":0.010037184},"labels":[],"label_agreement":null},{"id":"W3083274012","doi":"","title":"Centralized & Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Reinforcement learning; Computer science; Telecommunications link; Mathematical optimization; Maximization; Convergence (economics); Optimization problem; Rate of convergence; State (computer science); Artificial intelligence; Algorithm; Mathematics","score_opus":0.06386126489103415,"score_gpt":0.24174866563835565,"score_spread":0.1778874007473215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083274012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01712161,0.00020113692,0.9800838,0.00018316957,0.000027628292,0.000021241749,0.000016159978,0.00025077915,0.0020944932],"genre_scores_gemma":[0.929237,0.00013406196,0.067827486,0.00008841103,0.000030503606,0.00007349326,0.000035297307,0.000050471743,0.0025234176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965036,0.00013097766,0.00001059017,0.00007769284,0.00008148269,0.000048877846],"domain_scores_gemma":[0.99917656,0.0004965894,0.00009925245,0.000065584725,0.000118613716,0.000043421598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010495681,0.0006968394,0.0008077406,0.00018589277,0.00024704906,0.0006175352,0.0007908575,0.000724928,0.0012657485],"category_scores_gemma":[0.0023541085,0.00030209712,0.00031631053,0.00024489642,0.0007937847,0.0006308702,0.00075815874,0.0012251764,0.0002032238],"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":[0.000029039238,0.000024313249,0.00014232025,0.000018638822,0.000011973433,0.000017250624,0.000013419613,0.98368627,0.00062152144,0.0033644582,0.00033113777,0.011739558],"study_design_scores_gemma":[0.000002742925,0.000006750108,0.000012063289,8.3010525e-7,8.888403e-7,0.0000016291142,0.0000010239069,0.9991178,0.00009521171,0.00070918864,0.00005107906,6.6985973e-7],"about_ca_topic_score_codex":0.004074241,"about_ca_topic_score_gemma":0.0037950054,"teacher_disagreement_score":0.004074241,"about_ca_system_score_codex":0.0007886747,"about_ca_system_score_gemma":0.0011005879,"threshold_uncertainty_score":0.008101046},"labels":[],"label_agreement":null},{"id":"W3093727384","doi":"10.48550/arxiv.2010.10577","title":"Structured Online Learning-based Control of Continuous-time Nonlinear Systems","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Reinforcement learning; Computer science; Bellman equation; Parameterized complexity; Benchmark (surveying); Optimal control; Bounded function; Nonlinear system; Mathematical optimization; Function (biology); Mathematics; Algorithm; Artificial intelligence","score_opus":0.027668265216133397,"score_gpt":0.17730922188356374,"score_spread":0.14964095666743035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093727384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0208643,0.000292413,0.97521555,0.0001756312,0.00005462116,0.00003558598,0.000023509952,0.0003157243,0.0030227134],"genre_scores_gemma":[0.9674394,0.00017101261,0.030608393,0.000054543412,0.00003393745,0.00010644795,0.00005335517,0.000027298338,0.0015057083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995838,0.0001419611,0.000018904282,0.000084987245,0.00012196685,0.00004825785],"domain_scores_gemma":[0.9991097,0.0005512957,0.00010923132,0.000053603166,0.00014688395,0.000029268484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085997826,0.0007727864,0.0008696102,0.00029502323,0.0003194444,0.00085330463,0.0007983997,0.0007652708,0.0013062516],"category_scores_gemma":[0.001971567,0.00033506638,0.0004110748,0.00031506902,0.0009729304,0.00053818617,0.0008506342,0.0011472742,0.00019404248],"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":[0.000029116787,0.000023939238,0.0001120091,0.000038193186,0.00001395498,0.000023818724,0.000023167857,0.98254746,0.0008475856,0.0039112545,0.0002041035,0.0122253625],"study_design_scores_gemma":[0.000003765345,0.000012353865,0.000020187113,0.000001817185,0.0000012001127,0.0000018866799,9.894225e-7,0.9989618,0.00013840443,0.00079409964,0.00006244001,0.0000010173333],"about_ca_topic_score_codex":0.0073476727,"about_ca_topic_score_gemma":0.0045079673,"teacher_disagreement_score":0.0073476727,"about_ca_system_score_codex":0.0006856237,"about_ca_system_score_gemma":0.0010060152,"threshold_uncertainty_score":0.014609814},"labels":[],"label_agreement":null},{"id":"W3111828395","doi":"10.1109/twc.2020.3022705","title":"Centralized and Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":59,"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":"Reinforcement learning; Computer science; Telecommunications link; Mathematical optimization; Maximization; Convergence (economics); Optimization problem; Transmitter power output; Artificial intelligence; Algorithm; Mathematics","score_opus":0.03467231661912773,"score_gpt":0.3130906819506749,"score_spread":0.2784183653315472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111828395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013917825,0.00020675077,0.9836584,0.00014814755,0.00002630728,0.000021071852,0.00001357854,0.00023790787,0.0017700301],"genre_scores_gemma":[0.9185174,0.00015423869,0.07870009,0.000092918664,0.000033744633,0.00008610258,0.000038442362,0.000055353565,0.0023217376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959534,0.00015336316,0.00001314653,0.00008420984,0.000097580836,0.00005637085],"domain_scores_gemma":[0.99896824,0.00063601095,0.00011939492,0.000073161376,0.00014866663,0.000054529788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011485027,0.0007898961,0.00094856886,0.00021533488,0.00026812908,0.00064570527,0.0009364367,0.0007814621,0.0013419184],"category_scores_gemma":[0.0026935453,0.000344737,0.0003627334,0.00027577535,0.00081550266,0.00070991763,0.00083082926,0.0014436885,0.00022258736],"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":[0.000030920084,0.000030436184,0.00015419991,0.000021405178,0.000013544994,0.000019269026,0.000016480742,0.9827612,0.0006066414,0.0033424534,0.00034095056,0.012662433],"study_design_scores_gemma":[0.0000028427626,0.000007476886,0.000011265143,8.766055e-7,9.799594e-7,0.0000019154859,0.0000011739601,0.9992466,0.0000914663,0.0005890808,0.00004561952,7.5877557e-7],"about_ca_topic_score_codex":0.0038860932,"about_ca_topic_score_gemma":0.003915517,"teacher_disagreement_score":0.0038860932,"about_ca_system_score_codex":0.00082192296,"about_ca_system_score_gemma":0.0012193373,"threshold_uncertainty_score":0.0077269673},"labels":[],"label_agreement":null},{"id":"W3112168663","doi":"10.1109/smc42975.2020.9283399","title":"Trajectory Tracking of Underactuated Sea Vessels With Uncertain Dynamics: An Integral Reinforcement Learning Approach","year":2020,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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","funders":"","keywords":"Rudder; Trajectory; Underactuation; Reinforcement learning; Control theory (sociology); Computer science; Tracking error; Tracking (education); Gradient descent; Process (computing); Thrust; Artificial intelligence; Robot; Control (management); Engineering; Artificial neural network; Physics","score_opus":0.028883624396327835,"score_gpt":0.24761960009628142,"score_spread":0.2187359756999536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112168663","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08472581,0.00016758584,0.91208756,0.00016535626,0.00002700752,0.000024092888,0.000011469891,0.00016303347,0.002628116],"genre_scores_gemma":[0.97631776,0.000070884074,0.022418872,0.000022016548,0.000014256602,0.000033143107,0.000010222361,0.000010801333,0.0011020097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998338,0.00005381803,0.000007299952,0.000032454704,0.00004296107,0.000029639874],"domain_scores_gemma":[0.9993895,0.00032912972,0.00009840378,0.000035586607,0.000109192224,0.00003813719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007659241,0.00044151125,0.0005597168,0.0002125754,0.00024609506,0.0004761742,0.0006848348,0.00054744486,0.0007521226],"category_scores_gemma":[0.0015825664,0.00023838687,0.00024180688,0.0001604788,0.0008203459,0.0004304502,0.0006240877,0.0007768243,0.00008833281],"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":[0.000029667599,0.000018739924,0.00027686032,0.000019567577,0.000013451792,0.000040025352,0.000040741044,0.98266554,0.0014484897,0.004962632,0.00010628105,0.010377906],"study_design_scores_gemma":[0.0000019516967,0.000009335226,0.000022333325,7.584684e-7,0.0000012235988,0.0000018838289,0.0000011501874,0.9993051,0.00010191505,0.00051428477,0.000039191793,9.494518e-7],"about_ca_topic_score_codex":0.005391871,"about_ca_topic_score_gemma":0.0024967978,"teacher_disagreement_score":0.005391871,"about_ca_system_score_codex":0.0004996896,"about_ca_system_score_gemma":0.0006653779,"threshold_uncertainty_score":0.010720968},"labels":[],"label_agreement":null},{"id":"W3183314948","doi":"10.23919/acc50511.2021.9482670","title":"A Structured Online Learning Approach to Nonlinear Tracking with Unknown Dynamics","year":2021,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science","keywords":"Computer science; Nonlinear system; Benchmark (surveying); Controller (irrigation); Iterative learning control; Control theory (sociology); Reinforcement learning; Optimal control; Online model; System dynamics; Parameterized complexity; Tracking (education); Function (biology); Mathematical optimization; Artificial intelligence; Mathematics; Algorithm; Control (management)","score_opus":0.011084799240474508,"score_gpt":0.23377520321328252,"score_spread":0.222690403972808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183314948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013916199,0.00007606237,0.9972434,0.000038696442,0.000012690403,0.000012933371,0.00000619006,0.000081903956,0.0011365683],"genre_scores_gemma":[0.6637583,0.00053093006,0.3279327,0.00017522303,0.00014169427,0.00033775013,0.00012122133,0.000101153906,0.0069011706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996258,0.000100395155,0.000017446078,0.000083737425,0.00014191848,0.00003066879],"domain_scores_gemma":[0.99948174,0.00026279694,0.00006577478,0.000060510658,0.00010994684,0.000019266108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006808164,0.0006367162,0.00070552895,0.0003518268,0.00030228353,0.0006229134,0.0010514461,0.00088980736,0.0023634015],"category_scores_gemma":[0.001591335,0.0003370887,0.00048130343,0.00033778566,0.00081052905,0.00080800004,0.0009076625,0.0011246374,0.00036729634],"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":[0.00002496025,0.00005687939,0.00017198398,0.00011273821,0.000025588135,0.00005675753,0.00006743466,0.90503705,0.0026646787,0.04036572,0.0005823699,0.05083392],"study_design_scores_gemma":[0.000003158583,0.000024400735,0.000021548714,0.0000039922293,0.0000022505728,0.000007427758,0.0000024657081,0.9944623,0.00033831625,0.0047149435,0.00041653018,0.0000025743584],"about_ca_topic_score_codex":0.002996019,"about_ca_topic_score_gemma":0.0023836768,"teacher_disagreement_score":0.002996019,"about_ca_system_score_codex":0.0005531684,"about_ca_system_score_gemma":0.0008787384,"threshold_uncertainty_score":0.007906377},"labels":[],"label_agreement":null},{"id":"W3203907149","doi":"10.1139/juvs-2021-0010","title":"Quadrotor motion control using deep reinforcement learning","year":2021,"lang":"en","type":"article","venue":"Journal of Unmanned Vehicle Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Controller (irrigation); Computer science; Control theory (sociology); Artificial neural network; Artificial intelligence; Control (management); Control engineering; Engineering","score_opus":0.01483512746151684,"score_gpt":0.24576967930088872,"score_spread":0.2309345518393719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203907149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054056026,0.0003345551,0.93913853,0.00020368065,0.00010413015,0.000046391157,0.000034987774,0.00083984906,0.0052417535],"genre_scores_gemma":[0.9631864,0.00006882951,0.034184698,0.00007604171,0.000015297319,0.000040206447,0.0000298806,0.000024680914,0.0023739852],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999027,0.000016994441,0.0000041161984,0.000028401364,0.000027253298,0.000020355053],"domain_scores_gemma":[0.9998097,0.00007115355,0.000035953515,0.000017288763,0.000047085003,0.000018813582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028950957,0.0005569033,0.00040217128,0.00014769826,0.00020217686,0.00031570045,0.00053977896,0.00045581098,0.0012405809],"category_scores_gemma":[0.0005387435,0.00019483933,0.00021261958,0.000112828464,0.0003962976,0.00029057113,0.0004883217,0.00055583403,0.000174847],"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":[0.000041120515,0.00003227811,0.00028543457,0.000023780036,0.000018051984,0.00005254286,0.000017050686,0.9702279,0.004079079,0.0015783346,0.00042958974,0.023214834],"study_design_scores_gemma":[0.0000032701398,0.000023179358,0.00003374925,0.0000010983524,0.0000013402222,0.0000037015557,7.8327156e-7,0.99927026,0.00035519962,0.00019572316,0.000110610694,0.0000010729962],"about_ca_topic_score_codex":0.006092533,"about_ca_topic_score_gemma":0.0056315917,"teacher_disagreement_score":0.006092533,"about_ca_system_score_codex":0.00049832586,"about_ca_system_score_gemma":0.00046003022,"threshold_uncertainty_score":0.012114108},"labels":[],"label_agreement":null},{"id":"W3215476862","doi":"10.1109/rose52750.2021.9611772","title":"A Data-Driven Model-Reference Adaptive Control Approach Based on Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"Universiti Kebangsaan Malaysia","keywords":"Reference model; Reinforcement learning; Computer science; Process (computing); Adaptive control; Control theory (sociology); Backstepping; Lyapunov function; Trajectory; System dynamics; Control (management); Control engineering; Artificial intelligence; Nonlinear system; Engineering","score_opus":0.06948349707183171,"score_gpt":0.2767778434236618,"score_spread":0.20729434635183008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215476862","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028466806,0.00015552933,0.99399346,0.00010945037,0.000034240937,0.000032060787,0.0000094911875,0.0001593709,0.002659753],"genre_scores_gemma":[0.7880207,0.00052706,0.20385242,0.00018190905,0.00010834972,0.00031466817,0.000071800256,0.00006382619,0.006859264],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997336,0.00006482265,0.000012787023,0.00006112309,0.0001052348,0.000022433598],"domain_scores_gemma":[0.9996741,0.00012672834,0.00004583436,0.000037695558,0.00009641296,0.000019165733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005585662,0.0006063386,0.00076371466,0.00026217132,0.00031288626,0.0007651658,0.0011250575,0.00082188816,0.002035516],"category_scores_gemma":[0.0010338894,0.00023507146,0.0004803689,0.0003403781,0.0006795932,0.0005528769,0.0008623029,0.0013268839,0.00041681583],"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":[0.00004069481,0.00006702336,0.00032332563,0.000120919285,0.000056615114,0.00010479552,0.0000918565,0.8843786,0.005739253,0.04042739,0.0010655551,0.06758397],"study_design_scores_gemma":[0.00000798203,0.000043545446,0.000042357107,0.000006391333,0.0000053017907,0.000018155544,0.0000031185189,0.99494296,0.0005786279,0.0034032136,0.0009432343,0.0000050003555],"about_ca_topic_score_codex":0.003573603,"about_ca_topic_score_gemma":0.0025747141,"teacher_disagreement_score":0.003573603,"about_ca_system_score_codex":0.0005016305,"about_ca_system_score_gemma":0.00085418817,"threshold_uncertainty_score":0.007105589},"labels":[],"label_agreement":null},{"id":"W4210630976","doi":"10.3390/math10030499","title":"Optimal Reinforcement Learning-Based Control Algorithm for a Class of Nonlinear Macroeconomic Systems","year":2022,"lang":"en","type":"article","venue":"Mathematics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Manitoba","funders":"National Natural Science Foundation of China; Education Department of Hunan Province","keywords":"Reinforcement learning; Nonlinear system; Control theory (sociology); Controller (irrigation); Optimal control; Computer science; Control (management); Class (philosophy); Mathematical optimization; Control engineering; Artificial intelligence; Mathematics; Engineering","score_opus":0.010665227900336085,"score_gpt":0.2329612270568643,"score_spread":0.22229599915652823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210630976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030541126,0.00047533127,0.9616432,0.00049398124,0.0000629069,0.00007454289,0.000031873646,0.00022721889,0.006449784],"genre_scores_gemma":[0.9375016,0.00026495353,0.05810195,0.00015246653,0.000039511426,0.00024272404,0.000059506827,0.000024075787,0.0036131907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997284,0.00008614777,0.000012976719,0.00006814921,0.00005758239,0.00004673858],"domain_scores_gemma":[0.99943036,0.00032669448,0.000078170146,0.000018621868,0.00011358731,0.000032604385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009873393,0.0006379554,0.0007970116,0.00032746687,0.00038041564,0.0007530862,0.0006781533,0.0009854265,0.0018491371],"category_scores_gemma":[0.0019232697,0.00023082363,0.00030709594,0.00024994166,0.0009349247,0.00042115714,0.00081784825,0.0010440458,0.00019230266],"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":[0.000049282207,0.000031530264,0.00033604933,0.000051303334,0.000018332008,0.000060563663,0.00004935563,0.9702269,0.0009752873,0.01061494,0.00058919046,0.016997304],"study_design_scores_gemma":[0.000011175824,0.000015293102,0.00004019406,0.000002974548,0.000002143457,0.0000048033903,0.0000024193444,0.9985482,0.00007839906,0.0011377162,0.00015463498,0.0000018909358],"about_ca_topic_score_codex":0.008250568,"about_ca_topic_score_gemma":0.003932522,"teacher_disagreement_score":0.008250568,"about_ca_system_score_codex":0.00086671073,"about_ca_system_score_gemma":0.001252694,"threshold_uncertainty_score":0.016405106},"labels":[],"label_agreement":null},{"id":"W4220820327","doi":"10.1177/09596518221080323","title":"Reinforcement learning-based optimal fault-tolerant control for offshore platforms","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Windsor","funders":"","keywords":"Actuator; Control theory (sociology); Fault tolerance; Reinforcement learning; Submarine pipeline; Observer (physics); Controller (irrigation); Engineering; Fault (geology); Control engineering; Computer science; Control (management); Reliability engineering; Artificial intelligence","score_opus":0.0074439450085303106,"score_gpt":0.19331800724330708,"score_spread":0.18587406223477676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220820327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06501647,0.00035079292,0.9311733,0.00024412017,0.00006671404,0.000041863008,0.000014935202,0.00026960197,0.0028221568],"genre_scores_gemma":[0.988526,0.0000673922,0.010224249,0.000042076215,0.000015815793,0.000041350788,0.000012692226,0.0000095971,0.0010609846],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996612,0.00007504872,0.000016930428,0.000076589604,0.00009885028,0.00007148071],"domain_scores_gemma":[0.9994863,0.0002047996,0.00013024561,0.000022284457,0.0001226569,0.000033777807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063457584,0.00073599146,0.000691364,0.00022142146,0.00031757023,0.00041858535,0.00071837165,0.0006019848,0.0007361745],"category_scores_gemma":[0.0012236178,0.0002430789,0.00030812618,0.00016169251,0.0007022099,0.00036323586,0.0006056654,0.00066293933,0.000105320054],"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":[0.00005797017,0.00003375181,0.0002458342,0.000034940906,0.00001738843,0.00006403557,0.000039580395,0.9793815,0.0025834015,0.0025230637,0.00024006919,0.014778446],"study_design_scores_gemma":[0.000007791353,0.000037204405,0.000047802434,0.0000016747323,0.0000022236866,0.000005041397,0.0000024653739,0.9990344,0.00024887087,0.00052543107,0.00008487568,0.0000021265237],"about_ca_topic_score_codex":0.007959043,"about_ca_topic_score_gemma":0.0031023102,"teacher_disagreement_score":0.007959043,"about_ca_system_score_codex":0.0007159308,"about_ca_system_score_gemma":0.00082065864,"threshold_uncertainty_score":0.01582545},"labels":[],"label_agreement":null},{"id":"W4244440630","doi":"10.1109/cac53003.2021.9727718","title":"Value Iteration-based Zero-sum Neuro-optimal Control of Modular and Reconfigurable Robots via Adaptive Dynamic Programming","year":2021,"lang":"en","type":"article","venue":"2021 China Automation Congress (CAC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Dynamic programming; Control theory (sociology); Optimal control; Bellman equation; Convergence (economics); Modular design; Artificial neural network; Mathematics; Iterated function; Lyapunov function; Dimension (graph theory); Adaptive control; Mathematical optimization; Computer science; Control (management); Nonlinear system; Artificial intelligence; Mathematical analysis","score_opus":0.005959237061519206,"score_gpt":0.22257855529873455,"score_spread":0.21661931823721534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244440630","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02576452,0.00022219894,0.97004086,0.000090792906,0.000033011114,0.000025837708,0.000011112639,0.00012477349,0.0036869084],"genre_scores_gemma":[0.929603,0.00016449773,0.06706146,0.00004643298,0.000021534132,0.0001482693,0.000024730645,0.000020346619,0.0029097323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982846,0.000044555967,0.000007952263,0.000043347944,0.00004654771,0.000029058227],"domain_scores_gemma":[0.9998171,0.00007596318,0.000043075634,0.000009515109,0.000042089985,0.000012406846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040945155,0.00066450273,0.0006152059,0.00024082558,0.0003211045,0.0006521331,0.0007043516,0.00051955786,0.00074998155],"category_scores_gemma":[0.0005887676,0.0003147295,0.00039656914,0.00032574625,0.0006408023,0.00038292163,0.0007346446,0.0006055624,0.00010842588],"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":[0.000031599953,0.000018651013,0.00017787005,0.00004219787,0.000023547405,0.000054989807,0.0000504895,0.958991,0.00302006,0.0065027857,0.0003369477,0.030749857],"study_design_scores_gemma":[0.0000035180979,0.000024518684,0.000034121782,0.0000018189461,0.0000021416076,0.0000057023767,0.0000028485345,0.9988005,0.00024118573,0.00074592646,0.00013524637,0.0000023980774],"about_ca_topic_score_codex":0.0036638442,"about_ca_topic_score_gemma":0.0026106392,"teacher_disagreement_score":0.0036638442,"about_ca_system_score_codex":0.00042162434,"about_ca_system_score_gemma":0.00065661967,"threshold_uncertainty_score":0.007284999},"labels":[],"label_agreement":null},{"id":"W4293057750","doi":"10.1109/vtc2022-spring54318.2022.9861023","title":"Energy- and Cost-Efficient Transmission Strategy in Networked UAV Control System with ADP Trajectory Tracking Control","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Windsor","funders":"Research and Development; National Natural Science Foundation of China","keywords":"Computer science; Energy consumption; Benchmark (surveying); Trajectory; Transmission (telecommunications); Real-time computing; Model predictive control; Control (management); Control theory (sociology); Engineering; Artificial intelligence; Telecommunications","score_opus":0.009365597415460381,"score_gpt":0.20902034867646765,"score_spread":0.19965475126100726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293057750","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045312323,0.00039589396,0.94651496,0.00028182892,0.000082683975,0.000047895446,0.00003789272,0.00014582936,0.007180681],"genre_scores_gemma":[0.9864113,0.00012204841,0.011611484,0.000038154754,0.0000148060535,0.000052081832,0.000020361917,0.000008565655,0.0017212562],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995203,0.00011600907,0.00003443198,0.00012608229,0.00013744476,0.000065661625],"domain_scores_gemma":[0.99956435,0.00016251829,0.00008325095,0.000031802076,0.00013250046,0.000025472908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006270589,0.00075497024,0.00057848525,0.0002727669,0.000562341,0.0009277575,0.00086844095,0.00071596995,0.0012401332],"category_scores_gemma":[0.0010239771,0.0002595096,0.00031950502,0.00042864177,0.0005943301,0.0008308099,0.00077611726,0.0007098097,0.00013844682],"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":[0.00010760046,0.00003400454,0.0004062023,0.00010441514,0.000027887607,0.00017662477,0.00007720338,0.9617176,0.003485898,0.012329792,0.00049055606,0.021042196],"study_design_scores_gemma":[0.000009543705,0.000054969754,0.000075969605,0.0000039263928,0.0000077347295,0.00001895254,0.000008581282,0.9975224,0.00047286513,0.0016044567,0.00021630997,0.000004285601],"about_ca_topic_score_codex":0.0049967673,"about_ca_topic_score_gemma":0.002577169,"teacher_disagreement_score":0.0049967673,"about_ca_system_score_codex":0.0005938499,"about_ca_system_score_gemma":0.0006352923,"threshold_uncertainty_score":0.009935379},"labels":[],"label_agreement":null},{"id":"W4294690836","doi":"10.23919/acc53348.2022.9867729","title":"Structured Online Learning for Low-Level Control of Quadrotors","year":2022,"lang":"en","type":"article","venue":"2022 American Control Conference (ACC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"","keywords":"Computer science; Controller (irrigation); Reinforcement learning; Artificial neural network; Identifier; Set (abstract data type); Control engineering; Parameterized complexity; Control theory (sociology); Artificial intelligence; Control (management); Engineering; Algorithm","score_opus":0.01740815177442727,"score_gpt":0.2586946933443374,"score_spread":0.24128654156991014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294690836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018156733,0.00012904129,0.97907764,0.00006381924,0.000026851858,0.000027327409,0.00002179739,0.0003749309,0.0021218336],"genre_scores_gemma":[0.95113766,0.00008382735,0.04664036,0.000054708635,0.000018116183,0.000093237526,0.000053150325,0.000038818176,0.0018800948],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997993,0.000044951288,0.000009064718,0.000055107994,0.000058910176,0.000032686294],"domain_scores_gemma":[0.99956113,0.00021944639,0.00007135206,0.000042669366,0.00008362715,0.00002168549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004995698,0.00058337965,0.0005701323,0.00018542544,0.0002137911,0.00048553562,0.0005318135,0.000502439,0.0019175485],"category_scores_gemma":[0.0010643287,0.00022812963,0.0003361108,0.00014489678,0.00060323346,0.0004054698,0.0006925704,0.00086212956,0.0002721157],"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":[0.000041176154,0.000027162776,0.00019244447,0.00005296146,0.0000105890895,0.000031627656,0.000033089505,0.971966,0.0036875694,0.0038467138,0.00024196209,0.01986873],"study_design_scores_gemma":[0.0000027012486,0.000020140562,0.000026742617,0.0000016406744,9.413643e-7,0.0000027435176,0.0000014935974,0.9990325,0.00030015231,0.00050977455,0.00009999388,0.0000010919537],"about_ca_topic_score_codex":0.0034010478,"about_ca_topic_score_gemma":0.003208044,"teacher_disagreement_score":0.0034010478,"about_ca_system_score_codex":0.000424359,"about_ca_system_score_gemma":0.00050844747,"threshold_uncertainty_score":0.0067625046},"labels":[],"label_agreement":null},{"id":"W4296473542","doi":"10.1109/access.2022.3208058","title":"Regulation With Guaranteed Convergence Rate for Continuous-Time Systems With Completely Unknown Dynamics in the Presence of Disturbance","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Engineering and Physical Sciences Research Council; National Centre for Nuclear Robotics","keywords":"Convergence (economics); Computer science; Rate of convergence; Function (biology); Mathematical optimization; Algorithm; Mathematics","score_opus":0.015457998732045876,"score_gpt":0.2453259712901463,"score_spread":0.22986797255810043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296473542","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008532655,0.00048177538,0.9876199,0.00014626925,0.00006251179,0.000037776073,0.000012035159,0.0001735437,0.002933652],"genre_scores_gemma":[0.942613,0.000927327,0.052141037,0.00016806503,0.00014622661,0.00019540632,0.00006539908,0.000062687795,0.0036810124],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99833566,0.0004603123,0.00009280358,0.00044286952,0.0005323951,0.00013600338],"domain_scores_gemma":[0.99832577,0.00083458103,0.00027786146,0.00013939821,0.00037231858,0.000050076218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00203879,0.001011115,0.0012116925,0.00039060402,0.00036298748,0.0016918185,0.0015779156,0.0015039737,0.0009958512],"category_scores_gemma":[0.0037373495,0.0003547974,0.0009303981,0.00038226222,0.0012054414,0.0009916835,0.001186558,0.0014123901,0.00031651385],"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":[0.00021145308,0.000102188875,0.0005266444,0.0007359788,0.000108078915,0.00029823164,0.00035026786,0.8368332,0.020443799,0.057655364,0.001346416,0.08138838],"study_design_scores_gemma":[0.000016294522,0.000106104875,0.00012182096,0.000021113683,0.000013715541,0.0000351711,0.000011505252,0.9945082,0.0020503397,0.002223304,0.00087989034,0.00001257451],"about_ca_topic_score_codex":0.0022344114,"about_ca_topic_score_gemma":0.0010024447,"teacher_disagreement_score":0.0022344114,"about_ca_system_score_codex":0.00074423314,"about_ca_system_score_gemma":0.0010610158,"threshold_uncertainty_score":0.010782301},"labels":[],"label_agreement":null},{"id":"W4308902993","doi":"10.1016/j.automatica.2022.110685","title":"Model-free optimal control of discrete-time systems with additive and multiplicative noises","year":2022,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":45,"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":"National Natural Science Foundation of China","keywords":"Algebraic Riccati equation; Multiplicative function; Reinforcement learning; Optimal control; Discrete time and continuous time; Mathematics; Stochastic control; Mathematical optimization; Convergence (economics); Iterative learning control; Markov decision process; Controller (irrigation); Control theory (sociology); Riccati equation; Computer science; Control (management); Markov process; Artificial intelligence","score_opus":0.005472723485347404,"score_gpt":0.20316843514690344,"score_spread":0.19769571166155603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308902993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03863682,0.0005982552,0.952022,0.0004742424,0.0001921443,0.000031601463,0.000063429216,0.00017629059,0.0078051533],"genre_scores_gemma":[0.9814462,0.00033810016,0.012291175,0.000083214836,0.000055107976,0.0000751233,0.000061474275,0.00003653314,0.005613243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99920577,0.0002596502,0.000030445028,0.00016833228,0.00020421072,0.00013162561],"domain_scores_gemma":[0.99909806,0.00054523797,0.00012332812,0.00004580542,0.0001444723,0.000043195203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009935404,0.0013905487,0.0012872822,0.0005590799,0.0004948308,0.0016566552,0.0010326334,0.0013158526,0.0012255161],"category_scores_gemma":[0.0033624761,0.0006727929,0.00078625686,0.00047916707,0.0013847629,0.0010130946,0.0014911729,0.00118406,0.00019485975],"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":[0.00010772996,0.000046255667,0.00013865477,0.00010137827,0.000048249894,0.000047318736,0.00005549103,0.9625023,0.001847138,0.025915204,0.00041660407,0.008773654],"study_design_scores_gemma":[0.000009707629,0.000026540485,0.00008845133,0.0000048021475,0.000008387379,0.000005681618,0.0000052702458,0.9937742,0.0003227067,0.0055673844,0.00018117458,0.0000057405164],"about_ca_topic_score_codex":0.0071589,"about_ca_topic_score_gemma":0.004760858,"teacher_disagreement_score":0.0071589,"about_ca_system_score_codex":0.00091083895,"about_ca_system_score_gemma":0.0015190026,"threshold_uncertainty_score":0.014234483},"labels":[],"label_agreement":null},{"id":"W4310607898","doi":"10.1002/9781119808602.ch9","title":"An Application to Low‐level Control of Quadrotors","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Computer science; Position (finance); Control (management); Stability (learning theory); Sequence (biology); Control engineering; Control theory (sociology); Artificial intelligence; Engineering; Machine learning","score_opus":0.007858356877669302,"score_gpt":0.2499228687523096,"score_spread":0.2420645118746403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310607898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059504326,0.0003753164,0.9108756,0.00021403012,0.0001125895,0.00010268396,0.00008923856,0.0017455249,0.026980732],"genre_scores_gemma":[0.89829993,0.00023644305,0.092039704,0.00006914565,0.000026054004,0.00006964877,0.000075708944,0.00009572899,0.009087561],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999095,0.000017726232,0.0000042421134,0.000022816526,0.000032131567,0.000013504634],"domain_scores_gemma":[0.9999049,0.000042837415,0.000008548532,0.000014165984,0.000021478549,0.0000080616255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001381173,0.00034625476,0.00028685134,0.00010671708,0.00022764486,0.00049175724,0.00029451793,0.00035467668,0.0054485975],"category_scores_gemma":[0.00031289432,0.00010231683,0.00024417505,0.00011711908,0.00031070175,0.00018802784,0.00036089387,0.000441538,0.0006149228],"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":[0.00013502753,0.0001141642,0.0007661622,0.0003151279,0.000027571803,0.0002916375,0.00017045882,0.78558487,0.07392491,0.01721693,0.001766862,0.11968622],"study_design_scores_gemma":[0.000019268993,0.00020695149,0.00035957719,0.00001757399,0.000006109344,0.0000656958,0.000023665805,0.9742528,0.01235804,0.003722767,0.008959513,0.000007987046],"about_ca_topic_score_codex":0.0023754588,"about_ca_topic_score_gemma":0.0019927563,"teacher_disagreement_score":0.0054485975,"about_ca_system_score_codex":0.00024940012,"about_ca_system_score_gemma":0.00023279554,"threshold_uncertainty_score":0.018227398},"labels":[],"label_agreement":null},{"id":"W4310607962","doi":"10.1002/9781119808602.ch6","title":"A Structured Online Learning Approach to Nonlinear Tracking with Unknown Dynamics","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Reinforcement learning; Computer science; Trajectory; Tracking (education); Identification (biology); Nonlinear system; Variety (cybernetics); Process (computing); Online model; Quadratic equation; Control (management); Artificial intelligence; Control theory (sociology); Mathematical optimization; Mathematics","score_opus":0.009120678008927265,"score_gpt":0.2278479429374062,"score_spread":0.21872726492847894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310607962","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013504296,0.00079599547,0.9864783,0.00021603452,0.0000693767,0.000028471026,0.000026574233,0.0001673217,0.010867416],"genre_scores_gemma":[0.4437372,0.0075137406,0.48643515,0.0005173898,0.0005608821,0.0004866288,0.00030199363,0.0001660022,0.060281064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997843,0.000054580683,0.000009808313,0.000047798734,0.000088432134,0.000015190138],"domain_scores_gemma":[0.99983716,0.000079318415,0.00001732932,0.000022154221,0.000034048186,0.000009936236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031800984,0.0005847338,0.00050161156,0.00029229015,0.00026536334,0.0008019548,0.0007156647,0.00071358617,0.0058227023],"category_scores_gemma":[0.00079029356,0.00023668828,0.00051823555,0.00045490247,0.0006943174,0.0007010183,0.000844438,0.0014054204,0.0010847611],"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":[0.00003856055,0.00009843973,0.00018950667,0.00026735888,0.000041823958,0.00011403189,0.00013283541,0.54391026,0.0053216955,0.28849494,0.004928861,0.15646166],"study_design_scores_gemma":[0.00000809461,0.00006306419,0.000064542284,0.000024378118,0.000007162541,0.000044384487,0.000010362271,0.92098117,0.00093168,0.06967754,0.008179774,0.000007855282],"about_ca_topic_score_codex":0.0017349033,"about_ca_topic_score_gemma":0.0017065298,"teacher_disagreement_score":0.0058227023,"about_ca_system_score_codex":0.0005272919,"about_ca_system_score_gemma":0.00074305746,"threshold_uncertainty_score":0.019478858},"labels":[],"label_agreement":null},{"id":"W4310613884","doi":"10.1002/9781119808602.ch5","title":"Structured Online Learning‐Based Control of Continuous‐Time Nonlinear Systems","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Benchmark (surveying); Reinforcement learning; Computer science; Nonlinear system; Stability (learning theory); Riccati equation; Optimal control; Identification (biology); Algebraic Riccati equation; Control theory (sociology); Control (management); Algorithm; Differential equation; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning","score_opus":0.004773300130568655,"score_gpt":0.21334127737555086,"score_spread":0.20856797724498222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310613884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009622211,0.00042426426,0.98297274,0.000114626804,0.00006240627,0.00002582358,0.000016376267,0.0002606448,0.006500774],"genre_scores_gemma":[0.9183772,0.00082159607,0.07474249,0.00008747651,0.00008093171,0.000121325465,0.00007313928,0.000041581563,0.005654235],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998129,0.00005370892,0.000007381988,0.000035387515,0.00007264801,0.000017930884],"domain_scores_gemma":[0.9997002,0.00016781627,0.00003685211,0.000029492234,0.00005369841,0.000011955711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033748907,0.00055498804,0.0005242617,0.0001942352,0.0002360093,0.00060839765,0.0005099557,0.00048638313,0.002237439],"category_scores_gemma":[0.0009823836,0.00018500723,0.0002906947,0.00024065802,0.00059629953,0.0004761068,0.0005877617,0.0007996548,0.00030627783],"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":[0.000040341394,0.00003946296,0.00010014964,0.00009051789,0.000018502446,0.000035399004,0.00004253495,0.9144055,0.0036537533,0.022666056,0.0008052329,0.058102626],"study_design_scores_gemma":[0.0000033234212,0.000016962797,0.000022897015,0.0000030707852,0.000001205881,0.0000049357304,0.0000018648037,0.99661785,0.0003507363,0.0026368357,0.0003390761,0.0000012276739],"about_ca_topic_score_codex":0.0020952607,"about_ca_topic_score_gemma":0.0017589177,"teacher_disagreement_score":0.002237439,"about_ca_system_score_codex":0.00036710818,"about_ca_system_score_gemma":0.00052260776,"threshold_uncertainty_score":0.0074849725},"labels":[],"label_agreement":null},{"id":"W4310613925","doi":"10.1002/9781119808602.ch3","title":"Reinforcement Learning","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Waterloo","funders":"","keywords":"Reinforcement learning; Markov decision process; Dynamic programming; Optimal control; Mathematical proof; Computer science; Bellman equation; Mathematical optimization; Class (philosophy); Stochastic control; Control (management); Field (mathematics); Markov process; Mathematics; Artificial intelligence","score_opus":0.00743149318627673,"score_gpt":0.22072598638547652,"score_spread":0.2132944931991998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310613925","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038796812,0.0033471622,0.8664241,0.0028644186,0.0005069555,0.000124107,0.00029745698,0.0007455495,0.12181055],"genre_scores_gemma":[0.45046088,0.011063342,0.38308132,0.0018527628,0.0009113627,0.00084606314,0.0009195576,0.0003420966,0.15052263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995546,0.00014148987,0.000019321866,0.000099613135,0.00015112438,0.000033914912],"domain_scores_gemma":[0.999433,0.00032709504,0.00004024099,0.000075709264,0.00007943453,0.00004442872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006155191,0.0006921303,0.00048392726,0.00032041004,0.0003672433,0.0011949269,0.0010592529,0.0008672663,0.023712367],"category_scores_gemma":[0.0027141413,0.00017564005,0.0003769046,0.00030420552,0.0007661267,0.0012122599,0.00093728467,0.001385369,0.0034277663],"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":[0.00004205948,0.00009135099,0.00038225847,0.00017492357,0.0000349688,0.00006914961,0.000086365246,0.08177592,0.00085527945,0.70491964,0.022718586,0.18884954],"study_design_scores_gemma":[0.000043450345,0.00008390607,0.00025219866,0.00012709264,0.000017466784,0.0001351852,0.000053371085,0.27192944,0.0010031004,0.5785427,0.1477881,0.000024027662],"about_ca_topic_score_codex":0.0010449607,"about_ca_topic_score_gemma":0.0014116808,"teacher_disagreement_score":0.023712367,"about_ca_system_score_codex":0.0007456292,"about_ca_system_score_gemma":0.0007524313,"threshold_uncertainty_score":0.079325795},"labels":[],"label_agreement":null},{"id":"W4314946886","doi":"10.1109/cdc51059.2022.9992796","title":"Inverse Optimal Control with Discount Factor for Continuous and Discrete-Time Control-Affine Systems and Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Optimal control; Bellman equation; Control theory (sociology); Mathematics; Weighting; Mathematical optimization; Linear-quadratic-Gaussian control; Quadratic equation; Linear-quadratic regulator; Computer science; Control (management)","score_opus":0.011549548085453835,"score_gpt":0.232297176825317,"score_spread":0.22074762873986317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4314946886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068638204,0.0010530733,0.9870903,0.00035327688,0.000080956896,0.000024658879,0.00001720771,0.000083279214,0.0044335094],"genre_scores_gemma":[0.8856953,0.0015436083,0.101767,0.00015654223,0.00017712137,0.00015586561,0.000073726034,0.00006799297,0.010362772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991273,0.00032406376,0.00003850979,0.0001971546,0.00023355288,0.00007941827],"domain_scores_gemma":[0.99829525,0.0011307521,0.00021181747,0.00009809357,0.00017816163,0.00008589081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019397894,0.0010930508,0.0011674083,0.00040019368,0.00031256842,0.001401314,0.00094653934,0.0012553971,0.002404956],"category_scores_gemma":[0.005534254,0.00047087105,0.00070181215,0.000521519,0.002002709,0.0014901614,0.0011283788,0.0026565099,0.00023440745],"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":[0.000072581926,0.00005665141,0.00037141622,0.00015734388,0.000044463446,0.0001255818,0.00012117336,0.7634312,0.0010642607,0.20980218,0.000735997,0.02401718],"study_design_scores_gemma":[0.000011810658,0.000033130982,0.000059515267,0.0000103469565,0.0000066575503,0.000013666506,0.000007044931,0.96502465,0.00016442411,0.03396201,0.0006991898,0.0000075859675],"about_ca_topic_score_codex":0.0059253364,"about_ca_topic_score_gemma":0.0035885095,"teacher_disagreement_score":0.0059253364,"about_ca_system_score_codex":0.0017825366,"about_ca_system_score_gemma":0.001189353,"threshold_uncertainty_score":0.012933254},"labels":[],"label_agreement":null},{"id":"W4315489024","doi":"10.1109/cdc51059.2022.9992565","title":"Thompson-Sampling Based Reinforcement Learning for Networked Control of Unknown Linear Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Linear-quadratic-Gaussian control; Reinforcement learning; Logarithm; Regret; Network packet; Bounded function; Control theory (sociology); Generalization; Controller (irrigation); Sampling (signal processing); Gaussian; Discrete mathematics; Mathematics; Computer science; Optimal control; Control (management); Mathematical optimization; Artificial intelligence; Mathematical analysis; Statistics; Telecommunications","score_opus":0.03500695118355131,"score_gpt":0.2775513208392075,"score_spread":0.24254436965565623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315489024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038314052,0.0007781439,0.95664567,0.0006250141,0.00007470426,0.000057649242,0.00004640245,0.00031201672,0.0031463534],"genre_scores_gemma":[0.9642838,0.00032946293,0.032123834,0.00021095984,0.00007806326,0.00012853381,0.00009762794,0.000060222137,0.0026875047],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886644,0.0005289462,0.000046863446,0.00018920041,0.0002377377,0.00013070481],"domain_scores_gemma":[0.9941339,0.004674593,0.00037493533,0.00020414646,0.00041730198,0.00019513073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026911853,0.0010547301,0.0017768837,0.00043635,0.0004117309,0.00080593803,0.0012066253,0.0011275687,0.0018919016],"category_scores_gemma":[0.009905707,0.0004514746,0.0005272389,0.00049272005,0.0019136074,0.0009938774,0.0012346226,0.0018585356,0.00022792746],"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":[0.00006917918,0.000029197201,0.00045487322,0.000040385657,0.000024641133,0.000035721238,0.000031443382,0.9805854,0.00027737458,0.00997386,0.00033946827,0.008138421],"study_design_scores_gemma":[0.000005778068,0.000014040899,0.0000373475,0.0000023541847,0.0000016893349,0.0000021504466,0.000001602788,0.99661094,0.000050829614,0.0032129427,0.000058653073,0.0000017245147],"about_ca_topic_score_codex":0.012007724,"about_ca_topic_score_gemma":0.0076038647,"teacher_disagreement_score":0.012007724,"about_ca_system_score_codex":0.0020766864,"about_ca_system_score_gemma":0.0014487113,"threshold_uncertainty_score":0.023875654},"labels":[],"label_agreement":null},{"id":"W4315489189","doi":"10.1109/cdc51059.2022.9992884","title":"Finite-time Event-triggered Control for a Class of Nonlinear Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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","funders":"","keywords":"Hamilton–Jacobi–Bellman equation; Riccati equation; Control theory (sociology); Lyapunov function; Nonlinear system; Mathematics; Controller (irrigation); Linear-quadratic-Gaussian control; Differential equation; Computer science; Optimal control; Mathematical optimization; Control (management); Mathematical analysis; Artificial intelligence","score_opus":0.01897881529610653,"score_gpt":0.2593500047105889,"score_spread":0.24037118941448235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315489189","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019066902,0.00015831493,0.9770791,0.00007087842,0.00004161501,0.000032797685,0.00002283496,0.00012383221,0.0034037528],"genre_scores_gemma":[0.96007055,0.00024098722,0.03667317,0.00005290511,0.000030143992,0.00008588829,0.000054947646,0.000015987061,0.0027753825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996774,0.000058994738,0.000014612308,0.00009021087,0.00012122147,0.00003751057],"domain_scores_gemma":[0.9996867,0.00015807846,0.00006158021,0.000025021423,0.0000560599,0.000012586579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046585783,0.00051505823,0.00041473025,0.0001610739,0.00029965406,0.0006577872,0.0007685621,0.0005629827,0.0012305335],"category_scores_gemma":[0.0010037405,0.00013761276,0.00038574188,0.00020496272,0.0005572888,0.00044812268,0.00041615794,0.0006644546,0.000116648946],"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":[0.00009130382,0.000047574824,0.0004466491,0.00013063173,0.000029680707,0.00027022825,0.000114133916,0.9044862,0.011953303,0.051286723,0.0005381896,0.03060543],"study_design_scores_gemma":[0.0000046720147,0.000022664239,0.000052359253,0.0000022637225,0.000002238504,0.000012924339,0.0000038134708,0.99699473,0.00051310315,0.0020023698,0.00038661767,0.000002294217],"about_ca_topic_score_codex":0.0032320295,"about_ca_topic_score_gemma":0.0020269821,"teacher_disagreement_score":0.0032320295,"about_ca_system_score_codex":0.0005626651,"about_ca_system_score_gemma":0.0006290828,"threshold_uncertainty_score":0.0064264536},"labels":[],"label_agreement":null},{"id":"W4315640849","doi":"10.3389/fnbot.2022.1102259","title":"Adaptive optimal output regulation for wheel-legged robot Ollie: A data-driven approach","year":2023,"lang":"en","type":"article","venue":"Frontiers in Neurorobotics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":26,"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":"York University; Tencent","keywords":"Control theory (sociology); Robot; Computer science; Robustness (evolution); Controller (irrigation); Control engineering; Control (management); Artificial intelligence; Engineering","score_opus":0.055405230323865996,"score_gpt":0.26913883205625166,"score_spread":0.21373360173238568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315640849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10126188,0.00032455559,0.8946501,0.00018814046,0.000041878367,0.000062589,0.00004107142,0.000501309,0.0029284868],"genre_scores_gemma":[0.97516316,0.00008710032,0.02350636,0.000050932125,0.000012634279,0.000087648026,0.000040914692,0.000015458363,0.0010357995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979097,0.00002994482,0.000012299108,0.00006216794,0.00006800007,0.000036623995],"domain_scores_gemma":[0.9996742,0.00011605648,0.00007487583,0.000022733755,0.00009826421,0.0000138630585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004581825,0.0005541072,0.0006263977,0.00030253842,0.0003147856,0.00052897155,0.00065063976,0.0005846496,0.00072881853],"category_scores_gemma":[0.0007317645,0.00029776536,0.0003270479,0.0002275123,0.00045276905,0.00039164675,0.00060934765,0.0005476685,0.00010036072],"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":[0.00020695424,0.00009593934,0.0012792497,0.00021206273,0.00005236971,0.00022112275,0.00022263866,0.8946839,0.040051103,0.0031104689,0.00048471958,0.059379473],"study_design_scores_gemma":[0.0000104986675,0.00007929826,0.0002575834,0.0000049053338,0.0000069562375,0.000014958974,0.000012760968,0.996795,0.0021158832,0.0004390597,0.000256994,0.0000061904816],"about_ca_topic_score_codex":0.0057278075,"about_ca_topic_score_gemma":0.0033548912,"teacher_disagreement_score":0.0057278075,"about_ca_system_score_codex":0.00031239356,"about_ca_system_score_gemma":0.00048538615,"threshold_uncertainty_score":0.011388898},"labels":[],"label_agreement":null},{"id":"W4319453072","doi":"10.1109/tac.2023.3243165","title":"An Online Model-Following Projection Mechanism Using Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Reinforcement learning; Projection (relational algebra); Computer science; Control theory (sociology); Online model; Adaptive control; Adaptation (eye); Optimal control; Mathematical optimization; Control (management); Iterative learning control; Projection method; Horizon; Dykstra's projection algorithm; Artificial intelligence; Mathematics; Algorithm","score_opus":0.03278349811512623,"score_gpt":0.2848965783962839,"score_spread":0.2521130802811577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319453072","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008702135,0.00009142783,0.9889876,0.00011285019,0.000041209045,0.00003721816,0.000008316993,0.0004146191,0.001604496],"genre_scores_gemma":[0.8505517,0.00015671452,0.14551584,0.00012884103,0.00004684496,0.00016955323,0.000037263453,0.000037836515,0.003355336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997073,0.00008461439,0.000014652739,0.0000791308,0.00008417029,0.000030194686],"domain_scores_gemma":[0.99960595,0.00014698677,0.00006936531,0.00006605566,0.00007610796,0.000035563437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007970952,0.0006654559,0.00064584956,0.00020193931,0.0003386574,0.00060592266,0.0013274141,0.0009035058,0.002154443],"category_scores_gemma":[0.0013761735,0.0003158552,0.00040756536,0.00018436517,0.00068614265,0.0008980698,0.0010368223,0.0012373633,0.0003557322],"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":[0.0001385787,0.00026284088,0.0007153862,0.0001885819,0.00011284433,0.00025929124,0.00021248845,0.76197916,0.018172024,0.054939467,0.0021590127,0.16086031],"study_design_scores_gemma":[0.000015438396,0.0000655423,0.000049166596,0.000005122519,0.000006598612,0.000033697477,0.000004044285,0.9948754,0.0013081697,0.0030185836,0.00061103795,0.0000071647883],"about_ca_topic_score_codex":0.0018439912,"about_ca_topic_score_gemma":0.0013617916,"teacher_disagreement_score":0.002154443,"about_ca_system_score_codex":0.0002558393,"about_ca_system_score_gemma":0.0009381737,"threshold_uncertainty_score":0.007207334},"labels":[],"label_agreement":null},{"id":"W4324130748","doi":"10.1002/rnc.6662","title":"Robust <i>H</i><sub>∞</sub> tracking of linear <scp>discrete‐time</scp> systems using <scp>Q‐learning</scp>","year":2023,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Algebraic Riccati equation; Riccati equation; Bounded function; Algebraic number; Tracking (education); Control theory (sociology); Mathematics; Reinforcement learning; Discrete time and continuous time; Robust control; Norm (philosophy); Robustness (evolution); Stability (learning theory); Mathematical optimization; Computer science; Control system; Control (management); Differential equation; Artificial intelligence; Engineering","score_opus":0.022273173672116293,"score_gpt":0.250750505202805,"score_spread":0.22847733153068872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324130748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018633952,0.00011817296,0.97778064,0.00012269848,0.000026049202,0.00002886424,0.000023165614,0.00017815869,0.0030882184],"genre_scores_gemma":[0.962685,0.00010072411,0.035420414,0.000052187344,0.000016711589,0.000045566867,0.000037148235,0.000021360733,0.0016207432],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996486,0.000059380924,0.00001813546,0.0000968123,0.0001264033,0.00005070698],"domain_scores_gemma":[0.99945694,0.00021856514,0.00010646216,0.000045362034,0.0001430351,0.000029521128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008569007,0.00054820953,0.00063048315,0.0002342497,0.0003644978,0.0009373579,0.0008466783,0.00053850195,0.0014743445],"category_scores_gemma":[0.0015867068,0.00021481482,0.0004767712,0.00031105443,0.0009400151,0.0006095852,0.00083620386,0.0010084704,0.00018348149],"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":[0.00010432584,0.000050967956,0.0004319195,0.000103271406,0.000034208384,0.00010029408,0.00007414076,0.9284812,0.007667816,0.020953363,0.0008143002,0.04118409],"study_design_scores_gemma":[0.0000044752846,0.000020041196,0.000054954864,0.0000027668993,0.0000031485338,0.0000073247506,0.0000026330679,0.99745864,0.0007719955,0.0014903554,0.00018029164,0.0000034047957],"about_ca_topic_score_codex":0.007307277,"about_ca_topic_score_gemma":0.0030243578,"teacher_disagreement_score":0.007307277,"about_ca_system_score_codex":0.0008938646,"about_ca_system_score_gemma":0.0010973315,"threshold_uncertainty_score":0.014529526},"labels":[],"label_agreement":null},{"id":"W4361026739","doi":"10.1016/j.engappai.2023.106068","title":"Optimal non-autonomous area coverage control with adaptive reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":8,"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 Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Voronoi diagram; Metric (unit); Artificial neural network; Maxima and minima; Mathematical optimization; Centroid; Optimal control; Lyapunov function; Artificial intelligence; Mathematics; Nonlinear system","score_opus":0.012648709307533966,"score_gpt":0.23209989740942874,"score_spread":0.21945118810189476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361026739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06282304,0.00030151792,0.93002284,0.00022650462,0.00009239537,0.00004828549,0.000028001947,0.00024532247,0.006212027],"genre_scores_gemma":[0.9851349,0.000052058807,0.012946999,0.000048046626,0.00002369759,0.000053731976,0.000015606014,0.000014764617,0.0017101452],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999595,0.00010928614,0.000012980321,0.000091636866,0.00009567398,0.00009546864],"domain_scores_gemma":[0.99884343,0.0006772193,0.0001688633,0.0000540519,0.00018659887,0.000069845904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007603553,0.00070512865,0.00092918356,0.0004258726,0.0003402314,0.0007855225,0.0010917563,0.00088879524,0.0013445357],"category_scores_gemma":[0.0021782345,0.000417069,0.00036727096,0.00038496382,0.0010335974,0.00074623094,0.0012922364,0.0007297766,0.00016422554],"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":[0.00009255645,0.000044534056,0.00029247245,0.000032478474,0.000028198552,0.00004643147,0.00003030085,0.98255986,0.0013662262,0.003466762,0.0003827115,0.011657524],"study_design_scores_gemma":[0.000009804641,0.000022079494,0.000050357543,0.0000013916142,0.0000026332498,0.0000054676593,0.0000023337648,0.9990356,0.000098101365,0.0007126145,0.000058082413,0.0000015741783],"about_ca_topic_score_codex":0.0064880853,"about_ca_topic_score_gemma":0.0038281425,"teacher_disagreement_score":0.0064880853,"about_ca_system_score_codex":0.0006609134,"about_ca_system_score_gemma":0.0007001021,"threshold_uncertainty_score":0.0129006505},"labels":[],"label_agreement":null},{"id":"W4364375123","doi":"10.1016/j.eswa.2023.120112","title":"Neural Network-based control using Actor-Critic Reinforcement Learning and Grey Wolf Optimizer with experimental servo system validation","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":126,"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 Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education and Research, Romania; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii; Corporation for National and Community Service","keywords":"Reinforcement learning; Computer science; Artificial neural network; Particle swarm optimization; Gradient descent; Convergence (economics); Process (computing); Controller (irrigation); Mathematical optimization; Servomechanism; Artificial intelligence; Machine learning; Control engineering; Mathematics; Engineering","score_opus":0.015174882540149644,"score_gpt":0.2595307435211804,"score_spread":0.24435586098103074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364375123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29356778,0.00058941124,0.6955472,0.00032888315,0.00014935873,0.0003450553,0.00008878723,0.0009478498,0.008435732],"genre_scores_gemma":[0.9722214,0.000046433302,0.026453359,0.000019273759,0.0000041130074,0.000117255484,0.000031705524,0.00003224178,0.0010742918],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935335,0.0002762162,0.00004552995,0.000078234225,0.00018609544,0.000060587132],"domain_scores_gemma":[0.9968759,0.0017186818,0.00028084766,0.0002103506,0.0008568593,0.000057487894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029458655,0.00088333746,0.0009327244,0.00047183418,0.0005564335,0.00068517524,0.00083085813,0.0013077117,0.0018807926],"category_scores_gemma":[0.005399694,0.00040388523,0.00044112044,0.00029907952,0.0009616219,0.00062432385,0.000817609,0.0010955449,0.00018988572],"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":[0.00018567697,0.000103607104,0.0004655233,0.0001422766,0.000042461714,0.000038514554,0.0000676321,0.97825694,0.004492837,0.0016905162,0.00024908627,0.0142649235],"study_design_scores_gemma":[0.000015231714,0.00004600466,0.00015852584,0.0000062049753,0.0000050916174,0.000004133199,0.000003320964,0.9979431,0.0015878519,0.00016697457,0.000059172526,0.000004389027],"about_ca_topic_score_codex":0.011828065,"about_ca_topic_score_gemma":0.0072491583,"teacher_disagreement_score":0.011828065,"about_ca_system_score_codex":0.0009873732,"about_ca_system_score_gemma":0.0011550884,"threshold_uncertainty_score":0.023518443},"labels":[],"label_agreement":null},{"id":"W4376607624","doi":"10.1109/tsmc.2023.3264552","title":"Robust Self-Learning Fault-Tolerant Control for Hypersonic Flight Vehicle Based on ADHDP","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":43,"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":"National Natural Science Foundation of China","keywords":"Control theory (sociology); Robustness (evolution); Computer science; Fault tolerance; Controller (irrigation); Lyapunov stability; Actuator; Hypersonic flight; Control engineering; Engineering; Artificial intelligence; Hypersonic speed; Control (management)","score_opus":0.018320908262551026,"score_gpt":0.2175829276640776,"score_spread":0.19926201940152657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376607624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042924155,0.0004901294,0.95018667,0.00022375738,0.00012422942,0.000051381758,0.00003717224,0.0004415915,0.005520918],"genre_scores_gemma":[0.9817842,0.00017801733,0.015901186,0.0000733453,0.000028295744,0.00007683142,0.000056955414,0.0000121048315,0.0018889934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975365,0.00002588171,0.000014049183,0.00007362839,0.00009226257,0.000040474282],"domain_scores_gemma":[0.999821,0.000036113786,0.000045767538,0.000012278721,0.000073012336,0.000011771878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026318888,0.00068919134,0.00055700523,0.00025845895,0.00038003485,0.0006033633,0.0008364975,0.0005655718,0.00088940683],"category_scores_gemma":[0.00042012584,0.00017315835,0.00032876726,0.00025888562,0.0004031328,0.0004612674,0.00059184345,0.000582697,0.00011473473],"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":[0.000087180575,0.000047566893,0.00061039487,0.00013227941,0.00003449145,0.00020557827,0.000080505146,0.91616637,0.012928316,0.00756101,0.0010831663,0.061063174],"study_design_scores_gemma":[0.000008226472,0.00007170308,0.00013797623,0.000002962595,0.0000044568073,0.00001940411,0.0000057245975,0.9981188,0.000748094,0.00049205014,0.00038722137,0.000003354842],"about_ca_topic_score_codex":0.007073411,"about_ca_topic_score_gemma":0.0036381728,"teacher_disagreement_score":0.007073411,"about_ca_system_score_codex":0.00047213043,"about_ca_system_score_gemma":0.0006576436,"threshold_uncertainty_score":0.014064491},"labels":[],"label_agreement":null},{"id":"W4379983008","doi":"10.1002/rnc.6825","title":"Adaptive control for stochastic nonlinear systems with time‐varying delays via multidimensional Taylor network","year":2023,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Ministry of Education and Child Care","funders":"Fundamental Research Funds for the Central Universities; Shanghai Aerospace Science and Technology Innovation Foundation; Priority Academic Program Development of Jiangsu Higher Education Institutions; National Natural Science Foundation of China","keywords":"Control theory (sociology); Nonlinear system; Computer science; Kalman filter; Covariance; Convergence (economics); Tracking error; Covariance matrix; Mathematical optimization; Mathematics; Control (management); Algorithm","score_opus":0.013318982818162699,"score_gpt":0.2383035412986893,"score_spread":0.2249845584805266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379983008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035359573,0.00015191712,0.9617997,0.00013008915,0.000033205757,0.000024645451,0.000017426695,0.000121863995,0.0023616801],"genre_scores_gemma":[0.96404505,0.00022705962,0.033299226,0.00004015377,0.000019679712,0.00010642019,0.000029605219,0.000017217973,0.002215569],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997136,0.000094820636,0.000013653148,0.00006238304,0.00008646536,0.000028906748],"domain_scores_gemma":[0.9995103,0.00022482972,0.000107577376,0.000020509035,0.00012026615,0.000016521646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064496964,0.0004953794,0.0005728479,0.00029079145,0.00040470576,0.00051765476,0.00053928455,0.000549733,0.0008463415],"category_scores_gemma":[0.0011900238,0.00033909726,0.00036258213,0.0003193424,0.00055700104,0.0007364728,0.0006238995,0.0006156916,0.000094359355],"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":[0.00002900211,0.000009977503,0.00016412945,0.000019454355,0.000009260636,0.000027269085,0.00002574134,0.9845633,0.0019831331,0.0058054556,0.00013527484,0.007227991],"study_design_scores_gemma":[0.0000010129063,0.000007794153,0.000015952519,6.5788925e-7,8.756799e-7,0.0000019676734,0.0000010986316,0.99947745,0.00010692843,0.00033017574,0.00005517148,0.0000010546469],"about_ca_topic_score_codex":0.006913692,"about_ca_topic_score_gemma":0.0040010265,"teacher_disagreement_score":0.006913692,"about_ca_system_score_codex":0.00068282953,"about_ca_system_score_gemma":0.0007269169,"threshold_uncertainty_score":0.013746917},"labels":[],"label_agreement":null},{"id":"W4383506070","doi":"10.1016/j.automatica.2023.111162","title":"Model-free policy iteration approach to NCE-based strategy design for linear quadratic Gaussian games","year":2023,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Carleton University","funders":"","keywords":"Mathematics; Applied mathematics; Mathematical optimization; Ode; Algebraic equation; Nonlinear system","score_opus":0.05972795425387742,"score_gpt":0.3052582785002979,"score_spread":0.2455303242464205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383506070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025676314,0.00008660287,0.99460816,0.00014580872,0.000027692007,0.00004144095,0.00001547189,0.00006943344,0.0024378474],"genre_scores_gemma":[0.81671286,0.00029519704,0.17355923,0.0003635639,0.000099044715,0.00062348734,0.0001174049,0.00014779493,0.008081486],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99824154,0.0008466363,0.00006556036,0.0002436188,0.00040593356,0.00019666973],"domain_scores_gemma":[0.9938997,0.0045649647,0.00030070866,0.00017820188,0.00086571684,0.00019070126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003722644,0.0016755596,0.0024370607,0.0009685524,0.0006686756,0.001567735,0.0019391296,0.0022105093,0.003787159],"category_scores_gemma":[0.010825396,0.0012284116,0.0010115366,0.00059115223,0.0021809808,0.0012710976,0.0025596786,0.0027089342,0.0005579216],"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":[0.00006302449,0.000047926438,0.00014478219,0.00006566078,0.000037032423,0.00003387379,0.000057273464,0.966614,0.00043925532,0.022363588,0.00048656316,0.009646993],"study_design_scores_gemma":[0.0000073201745,0.000017638398,0.000014431217,0.00000455333,0.0000033613237,0.0000040774707,0.000002744966,0.99553585,0.00010835849,0.0041702995,0.0001277858,0.000003481733],"about_ca_topic_score_codex":0.008634915,"about_ca_topic_score_gemma":0.0067830444,"teacher_disagreement_score":0.008634915,"about_ca_system_score_codex":0.0018539125,"about_ca_system_score_gemma":0.0031503951,"threshold_uncertainty_score":0.019687414},"labels":[],"label_agreement":null},{"id":"W4386883033","doi":"10.1109/tnnls.2023.3309326","title":"Adaptive Event-Triggered Bipartite Formation for Multiagent Systems via Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"York University","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project","keywords":"Bipartite graph; Lyapunov function; Computer science; Reinforcement learning; Linearization; Adaptive control; Nonlinear system; Controller (irrigation); Artificial neural network; Convergence (economics); Control theory (sociology); Multi-agent system; Graph; Feedback linearization; Artificial intelligence; Control (management); Theoretical computer science","score_opus":0.02109190720631195,"score_gpt":0.24532823544262422,"score_spread":0.22423632823631226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386883033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014152146,0.00008550514,0.9839951,0.00007932617,0.000022086646,0.000026466592,0.000008054339,0.0001267324,0.0015046395],"genre_scores_gemma":[0.9605136,0.000092617425,0.037556432,0.000056653054,0.000017842593,0.00009429915,0.000024645473,0.0000143738225,0.0016294287],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996166,0.00012626976,0.00001704567,0.00008556617,0.000105267456,0.000049213988],"domain_scores_gemma":[0.999406,0.0002692694,0.00012952946,0.00004504142,0.00010442883,0.000045734752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089708803,0.000650504,0.00054420653,0.0002609128,0.0003732743,0.0004919762,0.0008604074,0.0006139433,0.001146017],"category_scores_gemma":[0.0015842309,0.00023919284,0.0003944891,0.00024590112,0.0007320044,0.00072139193,0.0011622034,0.0007827074,0.00015084131],"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":[0.000050832663,0.000044375698,0.000355635,0.000048889488,0.000030412071,0.0000928688,0.000069089045,0.957042,0.0034396725,0.018014278,0.0002958652,0.02051605],"study_design_scores_gemma":[0.0000061246888,0.000022029846,0.00003440513,0.0000012320949,0.0000021486112,0.0000064654387,0.0000031449867,0.99744725,0.00021951046,0.002129776,0.0001258713,0.0000020920022],"about_ca_topic_score_codex":0.0028031839,"about_ca_topic_score_gemma":0.0023429126,"teacher_disagreement_score":0.0028031839,"about_ca_system_score_codex":0.00053452316,"about_ca_system_score_gemma":0.00067760516,"threshold_uncertainty_score":0.005573809},"labels":[],"label_agreement":null},{"id":"W4388430254","doi":"10.1109/tsusc.2023.3330573","title":"Parallel Trajectory Training of Recurrent Neural Network Controllers With Levenberg–Marquardt and Forward Accumulation Through Time in Closed-Loop Control Systems","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Sustainable Computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Artificial Intelligence in Medicine (Canada)","funders":"Directorate for Computer and Information Science and Engineering; National Science Foundation","keywords":"Levenberg–Marquardt algorithm; Trajectory; Control theory (sociology); Closed loop; Artificial neural network; Computer science; Loop (graph theory); Control engineering; Control (management); Artificial intelligence; Engineering; Mathematics; Physics","score_opus":0.028079199821574342,"score_gpt":0.2676599859668572,"score_spread":0.23958078614528286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388430254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015257939,0.0001511195,0.981874,0.00006637249,0.000038178507,0.00004124233,0.000011452865,0.0010102902,0.0015493915],"genre_scores_gemma":[0.7747533,0.00016077481,0.22156784,0.00007924,0.000034002816,0.0001810666,0.00007526529,0.00017010768,0.00297844],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994443,0.00011259579,0.000046947745,0.00013810399,0.00018999245,0.00006798842],"domain_scores_gemma":[0.99924266,0.00024750858,0.000104964674,0.00010615073,0.0002693579,0.00002938779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013440677,0.00094666297,0.00091233855,0.00043135037,0.0005547498,0.00070407544,0.0011370471,0.0008001591,0.0015827578],"category_scores_gemma":[0.002330331,0.0005687233,0.00060585915,0.0004053073,0.0007203683,0.0009959779,0.00084161636,0.0011260257,0.00037747252],"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":[0.00013052515,0.000058117104,0.00038657023,0.00007090305,0.00005002798,0.0000714503,0.00009064074,0.8939921,0.005610536,0.004361471,0.0005175613,0.09465999],"study_design_scores_gemma":[0.0000044078974,0.000025963243,0.000029408426,0.0000019139375,0.0000032105222,0.000005613092,0.0000019317633,0.99818075,0.0011328858,0.00043019143,0.00018093115,0.0000026830521],"about_ca_topic_score_codex":0.011310544,"about_ca_topic_score_gemma":0.0078082425,"teacher_disagreement_score":0.011310544,"about_ca_system_score_codex":0.00067078864,"about_ca_system_score_gemma":0.0012540402,"threshold_uncertainty_score":0.022489429},"labels":[],"label_agreement":null},{"id":"W4388571386","doi":"10.1016/j.neucom.2023.127013","title":"Decentralized optimal control of large-scale partially unknown nonlinear mismatched interconnected systems based on dynamic event-triggered control","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Saskatchewan","funders":"","keywords":"Control theory (sociology); Computer science; Optimal control; Nonlinear system; Reinforcement learning; Decentralised system; Filter (signal processing); Stability (learning theory); Control (management); Artificial neural network; Bounded function; Scale (ratio); Mathematical optimization; Mathematics; Artificial intelligence","score_opus":0.00823570730478461,"score_gpt":0.2573743442197518,"score_spread":0.24913863691496718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388571386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07292136,0.00029867998,0.9198278,0.0003886067,0.00015514788,0.000055668126,0.000064845226,0.00022497457,0.0060630348],"genre_scores_gemma":[0.99194056,0.000079726386,0.0066435616,0.000032772547,0.000024468189,0.000042975826,0.000026467853,0.000009326369,0.0012000819],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995708,0.00010357338,0.00001898809,0.00012594876,0.00010910938,0.00007156196],"domain_scores_gemma":[0.9994411,0.00024557268,0.00013162383,0.000032911736,0.00011222151,0.000036556336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000578851,0.0007877992,0.0010413071,0.00023545619,0.00045288337,0.0010863692,0.000736405,0.0009363051,0.0013339365],"category_scores_gemma":[0.0014100134,0.00033661583,0.00043477595,0.00035910087,0.00090372615,0.0007274984,0.0012227782,0.0008537576,0.00012173964],"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":[0.00017276841,0.000049819646,0.00027216316,0.00007966033,0.000043105443,0.00012699043,0.0000706701,0.9683164,0.0052174386,0.011954464,0.00051580276,0.013180709],"study_design_scores_gemma":[0.000012310351,0.000031821943,0.00009717874,0.0000021235242,0.000003625458,0.0000063438456,0.000004372933,0.99783355,0.0002811488,0.0016224989,0.000101893645,0.000003085343],"about_ca_topic_score_codex":0.0031736826,"about_ca_topic_score_gemma":0.00273313,"teacher_disagreement_score":0.0031736826,"about_ca_system_score_codex":0.0005105827,"about_ca_system_score_gemma":0.00079876493,"threshold_uncertainty_score":0.0063104033},"labels":[],"label_agreement":null},{"id":"W4388785240","doi":"10.1016/j.neucom.2023.127042","title":"Dynamic event-triggered-based online IRL algorithm for the decentralized control of the input and state constrained large-scale unmatched interconnected system","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"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","funders":"","keywords":"Computer science; Interconnection; Control theory (sociology); Decentralised system; State (computer science); Scale (ratio); Stability (learning theory); Computation; Mathematical optimization; Function (biology); Optimal control; Control (management); Mathematics; Algorithm; Artificial intelligence","score_opus":0.008015808123454937,"score_gpt":0.24752368198896935,"score_spread":0.23950787386551442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388785240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009445726,0.00017203775,0.9859439,0.00018164674,0.00006919432,0.000058209916,0.000029151166,0.00043968888,0.0036605434],"genre_scores_gemma":[0.8965238,0.0001367575,0.09889648,0.00024685348,0.00006509448,0.00025020866,0.00009721913,0.000070809205,0.0037127743],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950206,0.000104176754,0.000026041582,0.00012606301,0.0001543826,0.00008720329],"domain_scores_gemma":[0.9994081,0.00023009225,0.00010964223,0.000043671396,0.00016251505,0.000045983656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009848521,0.0007593778,0.0012953929,0.00031849442,0.00055989984,0.0011871606,0.0012888715,0.0010454276,0.004952009],"category_scores_gemma":[0.0013939774,0.00034776892,0.00042529328,0.00038184936,0.00072876574,0.0008506622,0.0014088745,0.0013451915,0.00065353647],"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":[0.0005179104,0.00018811571,0.0004380747,0.00024758044,0.000056158002,0.00018881955,0.0001934046,0.83517426,0.007601095,0.016644757,0.0036694799,0.13508035],"study_design_scores_gemma":[0.000031094125,0.00005023574,0.000044070897,0.0000045141765,0.0000037016982,0.000012571025,0.000006151693,0.9981505,0.00040817572,0.0010140416,0.00027041094,0.000004493508],"about_ca_topic_score_codex":0.0030537231,"about_ca_topic_score_gemma":0.0042221327,"teacher_disagreement_score":0.004952009,"about_ca_system_score_codex":0.0006651126,"about_ca_system_score_gemma":0.0013895703,"threshold_uncertainty_score":0.016566157},"labels":[],"label_agreement":null},{"id":"W4390187516","doi":"10.1109/tim.2023.3346524","title":"Model-Free Force Control of Cable-Driven Parallel Manipulators for Weight-Shift Aircraft Actuation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Reinforcement learning; Control theory (sociology); Trajectory; Actuator; Control engineering; Controller (irrigation); Inverse dynamics; Torque; Optimal control; Kinematics; Parallel manipulator; Computer science; Engineering; Heuristic; Robot; Control (management); Artificial intelligence","score_opus":0.04563645080383398,"score_gpt":0.2600250896028202,"score_spread":0.21438863879898623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390187516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11536739,0.00016084517,0.8775898,0.00014159303,0.000053016836,0.00004203026,0.000025628737,0.0004449009,0.006174809],"genre_scores_gemma":[0.96724606,0.00006948285,0.03076171,0.000017327926,0.000012373427,0.00004579555,0.000015593669,0.000011850158,0.0018198111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999211,0.000014775046,0.0000025684142,0.000015819583,0.000035980913,0.00000974552],"domain_scores_gemma":[0.9998574,0.000036353256,0.000048031903,0.000018903867,0.000025976193,0.000013266632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018820936,0.0004124726,0.00017549138,0.000119769764,0.00019210034,0.00022415655,0.000479962,0.00024967943,0.0012138464],"category_scores_gemma":[0.00033289802,0.00015408234,0.00017835971,0.000097742704,0.00036339206,0.00025526743,0.00045325654,0.00042054095,0.00019996655],"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":[0.00008161315,0.000053765452,0.00041323635,0.00007640023,0.000018667679,0.00012453305,0.00006571975,0.91427,0.041381944,0.006451067,0.00047729068,0.036585845],"study_design_scores_gemma":[0.000011968933,0.00012811979,0.00013772341,0.0000027335138,0.0000028420277,0.000023562014,0.000004412494,0.9948991,0.0030822973,0.0010167265,0.00068650243,0.0000039753545],"about_ca_topic_score_codex":0.0013288669,"about_ca_topic_score_gemma":0.001325968,"teacher_disagreement_score":0.0013288669,"about_ca_system_score_codex":0.00017687597,"about_ca_system_score_gemma":0.00031290564,"threshold_uncertainty_score":0.0040607452},"labels":[],"label_agreement":null},{"id":"W4390733893","doi":"10.1002/rnc.7189","title":"Efficient off‐policy Q‐learning for multi‐agent systems by solving dual games","year":2024,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Dual (grammatical number); Bounded function; Synchronization (alternating current); Nash equilibrium; Tracking (education); Mathematical optimization; Zero-sum game; Tracking error; Zero (linguistics); Multi-agent system; Potential game; Game theory; Control (management); Artificial neural network; Control theory (sociology); Artificial intelligence; Mathematics; Mathematical economics; Channel (broadcasting)","score_opus":0.015961719390741532,"score_gpt":0.28417058159568964,"score_spread":0.2682088622049481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390733893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016450133,0.0001581011,0.9806908,0.00020065319,0.000029082641,0.000046357953,0.000011795427,0.00009277689,0.0023202666],"genre_scores_gemma":[0.94514316,0.00013550057,0.052097164,0.00013363041,0.000028968976,0.000166486,0.000031396023,0.000023692815,0.002239964],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925,0.00027666424,0.000033189055,0.00014719978,0.00015722893,0.00013564172],"domain_scores_gemma":[0.99876463,0.00071974087,0.00015319696,0.00005305496,0.0002281366,0.00008127242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018328906,0.00092915783,0.0014158404,0.00047689304,0.00057526794,0.0012209609,0.0010937778,0.0011184174,0.0015137424],"category_scores_gemma":[0.003150873,0.0005175109,0.00049380877,0.00038591036,0.0013534604,0.0009606265,0.0015165161,0.00127526,0.00017100855],"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":[0.000052133924,0.000041501295,0.00037336067,0.00004580179,0.000022193122,0.00004659339,0.000046189114,0.97369576,0.00074027857,0.014068304,0.00032483364,0.01054299],"study_design_scores_gemma":[0.000006377641,0.000011669978,0.000015518173,0.000001595516,0.0000014354079,0.0000022373667,0.0000026807845,0.9981831,0.00006670005,0.0016348731,0.000072550465,0.0000012333661],"about_ca_topic_score_codex":0.005834642,"about_ca_topic_score_gemma":0.0027605495,"teacher_disagreement_score":0.005834642,"about_ca_system_score_codex":0.0012203295,"about_ca_system_score_gemma":0.0019021191,"threshold_uncertainty_score":0.011601329},"labels":[],"label_agreement":null},{"id":"W4390757324","doi":"10.22190/fume231011044z","title":"Q-LEARNING, POLICY ITERATION AND ACTOR-CRITIC REINFORCEMENT LEARNING COMBINED WITH METAHEURISTIC ALGORITHMS IN SERVO SYSTEM CONTROL","year":2023,"lang":"en","type":"article","venue":"Facta Universitatis Series Mechanical Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":48,"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; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","keywords":"Reinforcement learning; Initialization; Computer science; Artificial neural network; Metaheuristic; Servomechanism; Algorithm; Mathematical optimization; Parametric statistics; Artificial intelligence; Machine learning; Mathematics; Control engineering; Engineering","score_opus":0.004149845208367344,"score_gpt":0.18436468813074813,"score_spread":0.1802148429223808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390757324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027822806,0.0018168027,0.9665845,0.00029965283,0.00006824667,0.000038242877,0.000007968437,0.0001732525,0.0031885575],"genre_scores_gemma":[0.9193789,0.0008103973,0.07765776,0.00008182077,0.000064495405,0.00008527859,0.000014149183,0.000039064536,0.0018681671],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912816,0.000461612,0.000040750347,0.00007741978,0.0002188943,0.00007318928],"domain_scores_gemma":[0.99857175,0.0009997556,0.00013041303,0.00006153787,0.00019916492,0.000037260517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026734597,0.0007049993,0.0009790629,0.0005233223,0.0003179786,0.0009616118,0.00068486383,0.0009971362,0.0005532127],"category_scores_gemma":[0.0037192695,0.0003509038,0.00045898638,0.00058446574,0.0011923749,0.00083162414,0.00058686524,0.0010082129,0.00010344463],"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":[0.000044665067,0.000032780852,0.000401058,0.00005985243,0.000051114293,0.00002807732,0.000031150037,0.9605875,0.00074668706,0.0108907735,0.00017459004,0.026951844],"study_design_scores_gemma":[0.000004297654,0.000037159076,0.00007284128,0.0000040156647,0.000004184329,0.000006121371,0.000002566748,0.99726546,0.00024905978,0.0021872795,0.00016449684,0.0000025028744],"about_ca_topic_score_codex":0.0037464313,"about_ca_topic_score_gemma":0.0016989745,"teacher_disagreement_score":0.0037464313,"about_ca_system_score_codex":0.0008413225,"about_ca_system_score_gemma":0.0009829478,"threshold_uncertainty_score":0.014138758},"labels":[],"label_agreement":null},{"id":"W4391019820","doi":"10.1109/cdc49753.2023.10383832","title":"Data-Driven Output Regulation Using Single-Gain Tuning Regulators","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Toronto","funders":"","keywords":"Control theory (sociology); Regulator; Computer science; MIMO; Control engineering; Convex optimization; Scalar (mathematics); Controller (irrigation); Linear system; Regular polygon; Engineering; Control (management); Mathematics; Channel (broadcasting)","score_opus":0.09231915592367608,"score_gpt":0.2936539176518024,"score_spread":0.2013347617281263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391019820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053226855,0.00014709662,0.9913696,0.00006846208,0.00003439287,0.000021360089,0.000010415528,0.00035490625,0.0026710697],"genre_scores_gemma":[0.84029704,0.00036025938,0.15523943,0.00021277979,0.000075031574,0.0001662305,0.00004668044,0.000108993125,0.0034935693],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916625,0.00013977861,0.000039976727,0.00024477692,0.00035235874,0.00005688105],"domain_scores_gemma":[0.99915886,0.00040669466,0.00012768872,0.00012468382,0.0001631868,0.000018883671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009131234,0.00047551648,0.00063777965,0.00031635427,0.0002942291,0.0010156309,0.00088350876,0.0007088366,0.0011789174],"category_scores_gemma":[0.0027926483,0.00029462774,0.000386871,0.00035426457,0.00084185146,0.0008062787,0.00093772507,0.0010484823,0.00048358325],"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":[0.00030866105,0.00015454754,0.00062041613,0.0004315671,0.000068226225,0.00014917919,0.00031278454,0.5107975,0.16569787,0.082692884,0.0024695722,0.23629673],"study_design_scores_gemma":[0.000023740144,0.00013603708,0.00012530995,0.000026813817,0.0000114223,0.000049604856,0.000011093692,0.96277624,0.021180363,0.0114563005,0.0041770246,0.000026016467],"about_ca_topic_score_codex":0.00050747907,"about_ca_topic_score_gemma":0.00041818808,"teacher_disagreement_score":0.0011789174,"about_ca_system_score_codex":0.0003934694,"about_ca_system_score_gemma":0.000427619,"threshold_uncertainty_score":0.0048291683},"labels":[],"label_agreement":null},{"id":"W4391306093","doi":"10.1109/rose60297.2023.10410776","title":"An Online Model-Free Reinforcement Learning Approach for 6-DOF Robot Manipulators","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Controller (irrigation); Control theory (sociology); Robot; Adaptive control; MATLAB; Robot manipulator; Tracking error; Kernel (algebra); Degrees of freedom (physics and chemistry); Control (management); Control engineering; Artificial intelligence; Mathematics; Engineering","score_opus":0.05925569399817362,"score_gpt":0.2849001201848312,"score_spread":0.22564442618665756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391306093","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008756326,0.00008486941,0.9891857,0.000059705857,0.000017447694,0.000020573234,0.00000727068,0.00025543504,0.0016126202],"genre_scores_gemma":[0.8485413,0.00012746095,0.14727762,0.000068988804,0.000034068296,0.00014027607,0.000037721715,0.000055515215,0.003717006],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997379,0.000059096183,0.000012272071,0.000054897206,0.00010315721,0.00003259489],"domain_scores_gemma":[0.9996644,0.00013264392,0.00007240794,0.000036922167,0.00006967762,0.000023872028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006758026,0.0005982772,0.0006422844,0.00019973521,0.00027972757,0.00040588493,0.0010682059,0.000627992,0.0016504853],"category_scores_gemma":[0.0009554943,0.00031350466,0.0004146087,0.00015315587,0.0005508077,0.00048292495,0.00076110644,0.0010822997,0.00029822133],"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":[0.000039192983,0.000033480403,0.00017777178,0.00005855933,0.000016734926,0.00006234078,0.00005345206,0.9533989,0.0042729876,0.005182318,0.0002945389,0.03640972],"study_design_scores_gemma":[0.0000038865464,0.00002583258,0.000026298005,0.0000021825097,0.0000016936435,0.000007705696,0.0000017472489,0.99872786,0.0003744461,0.00058651087,0.00023956882,0.0000022550716],"about_ca_topic_score_codex":0.003690706,"about_ca_topic_score_gemma":0.002671518,"teacher_disagreement_score":0.003690706,"about_ca_system_score_codex":0.00038078826,"about_ca_system_score_gemma":0.0006677452,"threshold_uncertainty_score":0.0073384643},"labels":[],"label_agreement":null},{"id":"W4391306300","doi":"10.1109/rose60297.2023.10410754","title":"Behavior Replication of Cascaded Dynamic Systems Using Machine Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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","funders":"","keywords":"Computer science; Reinforcement learning; Reference model; Convergence (economics); Process (computing); Replicate; Sensitivity (control systems); System dynamics; Replication (statistics); Projection (relational algebra); Component (thermodynamics); Control theory (sociology); Artificial intelligence; Control (management); Algorithm; Engineering; Mathematics","score_opus":0.030782973909780756,"score_gpt":0.29952938967637954,"score_spread":0.2687464157665988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391306300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019068653,0.000085971194,0.9792879,0.000046947636,0.000017835277,0.00004049054,0.000011332922,0.00033347978,0.0011073584],"genre_scores_gemma":[0.8542049,0.00009867267,0.14382094,0.00004102128,0.00002200031,0.0001663734,0.0000506709,0.0000647284,0.0015307841],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957186,0.00011053239,0.00002893602,0.00013395942,0.00011541748,0.000039258564],"domain_scores_gemma":[0.9988626,0.0005538844,0.00017917987,0.00022740995,0.00012982711,0.00004706966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009934527,0.0006779859,0.0007209641,0.00042731178,0.00041893963,0.00071108056,0.001341563,0.00076384126,0.0011385151],"category_scores_gemma":[0.0025172853,0.0004916279,0.0007671886,0.00029529756,0.0009328342,0.00094007916,0.0012181307,0.000916363,0.00018960565],"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":[0.000025975793,0.000026680113,0.00049412774,0.000047406164,0.000030505611,0.000068698326,0.00008039043,0.95958745,0.0033151242,0.0065925433,0.000117338204,0.02961375],"study_design_scores_gemma":[0.0000016361362,0.00001087955,0.00002956799,0.0000018860821,0.000001860592,0.000005199045,0.0000021412545,0.99835205,0.0003526412,0.0011198111,0.000120325945,0.0000020108437],"about_ca_topic_score_codex":0.0031445571,"about_ca_topic_score_gemma":0.0022714767,"teacher_disagreement_score":0.0031445571,"about_ca_system_score_codex":0.0008040112,"about_ca_system_score_gemma":0.0006217186,"threshold_uncertainty_score":0.0062525272},"labels":[],"label_agreement":null},{"id":"W4391450137","doi":"10.1115/1.4064601","title":"Nonlinear Filtering and Reinforcement Learning Based Consensus Achievement of Uncertain Multi-Agent Systems","year":2024,"lang":"en","type":"article","venue":"Journal of Dynamic Systems Measurement and Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Nonlinear system; Multi-agent system; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology; Physics","score_opus":0.027248676278643084,"score_gpt":0.24938680326290075,"score_spread":0.22213812698425767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391450137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03527064,0.00009682416,0.9623051,0.000116515104,0.00002498519,0.000023689545,0.000007969937,0.00015553959,0.0019988199],"genre_scores_gemma":[0.9679502,0.000042938183,0.031088946,0.000027935295,0.000014086994,0.000034771972,0.000011190375,0.000010086251,0.0008198356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963176,0.00011023908,0.000023820443,0.00008635906,0.00009865647,0.00004915521],"domain_scores_gemma":[0.9990702,0.000422956,0.00018439979,0.00007175179,0.00020772345,0.00004296586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010023343,0.0004744281,0.00062645745,0.0003059349,0.00041577272,0.00046504545,0.00070678437,0.0006542859,0.00080475974],"category_scores_gemma":[0.0022584554,0.00020005637,0.00037201104,0.00019134716,0.00066930166,0.0005915375,0.00074008026,0.0005512917,0.0001126817],"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":[0.000040761228,0.000025301233,0.0003848038,0.000035783814,0.000023017294,0.00006241433,0.00005484055,0.96797454,0.0034851697,0.0064108865,0.00023124828,0.021271182],"study_design_scores_gemma":[0.0000025709871,0.000013417748,0.000039470666,0.0000010944049,0.0000014960394,0.0000043625823,0.00000218334,0.9988134,0.00030257742,0.0007486075,0.00006932009,0.0000015261049],"about_ca_topic_score_codex":0.0049053174,"about_ca_topic_score_gemma":0.002170811,"teacher_disagreement_score":0.0049053174,"about_ca_system_score_codex":0.00064242125,"about_ca_system_score_gemma":0.00063284975,"threshold_uncertainty_score":0.009753525},"labels":[],"label_agreement":null},{"id":"W4391495714","doi":"10.1109/etfg55873.2023.10407820","title":"Integral Reinforcement Learning Control for a Class of Unknown Nonlinear Systems with an Application to a Microgrid System","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Saskatchewan","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Microgrid; Reinforcement learning; Nonlinear system; Class (philosophy); Computer science; Control (management); Control theory (sociology); Reinforcement; Control system; Control engineering; Artificial intelligence; Engineering; Structural engineering; Electrical engineering; Physics","score_opus":0.008847576481085459,"score_gpt":0.24376432971334683,"score_spread":0.23491675323226135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391495714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021250075,0.00039808397,0.97323215,0.00015458067,0.00005421658,0.000038790175,0.000012192165,0.00015797144,0.004701873],"genre_scores_gemma":[0.9564334,0.00029154672,0.03987087,0.00005413746,0.00004575378,0.000068221,0.000018853989,0.00001943021,0.0031976781],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974614,0.00006374194,0.000011330847,0.00006277946,0.00007918482,0.000036904312],"domain_scores_gemma":[0.99971527,0.00014482594,0.0000455002,0.000016134522,0.000061681654,0.000016495715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071017543,0.0006049296,0.0005462148,0.00023798402,0.0003562226,0.0006459838,0.00064409495,0.00058196485,0.001301393],"category_scores_gemma":[0.0008571134,0.00015594398,0.0003645009,0.00022491034,0.00075037155,0.0003999414,0.0006052381,0.00087337353,0.0001330564],"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":[0.000069920294,0.00004793829,0.0004970393,0.00016103454,0.000036334415,0.00021233987,0.00012644278,0.91634053,0.0050609754,0.020193797,0.000722693,0.056530964],"study_design_scores_gemma":[0.0000046170894,0.000027614145,0.000058749887,0.000002418523,0.0000032399269,0.000016330272,0.00000419123,0.99810934,0.0003174956,0.0010932899,0.00035996942,0.0000026914504],"about_ca_topic_score_codex":0.004082089,"about_ca_topic_score_gemma":0.002339026,"teacher_disagreement_score":0.004082089,"about_ca_system_score_codex":0.0004909816,"about_ca_system_score_gemma":0.0005082592,"threshold_uncertainty_score":0.0081166625},"labels":[],"label_agreement":null},{"id":"W4392622485","doi":"10.1142/s1793962324500296","title":"An online model-free adaptive learning control solution for robotic arms","year":2024,"lang":"en","type":"article","venue":"Advances in Complex Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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; University of Ottawa","funders":"","keywords":"Computer science; Control (management); Adaptive control; Artificial intelligence","score_opus":0.04593087607144463,"score_gpt":0.3124840809376537,"score_spread":0.26655320486620904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392622485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007824477,0.00013405494,0.98912513,0.00009008009,0.000027949349,0.000022374561,0.000007296602,0.00022993654,0.0025386799],"genre_scores_gemma":[0.85589105,0.00020276998,0.13478012,0.00011993668,0.000050236114,0.0001946577,0.000040752264,0.000055345754,0.008665099],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998031,0.000035043606,0.000008532603,0.00004986632,0.00007720273,0.000026213027],"domain_scores_gemma":[0.9997831,0.00008912756,0.00004264056,0.0000151976255,0.000057754,0.0000121270195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041008941,0.000596532,0.00056605804,0.00020983968,0.00030611726,0.0004692875,0.00078130094,0.0008707113,0.0017289354],"category_scores_gemma":[0.0007984442,0.00027501836,0.00039386644,0.00020520402,0.0005594395,0.00044378013,0.0007868955,0.00094557944,0.00027880765],"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":[0.000038249604,0.0000369795,0.00013098797,0.00007357962,0.000017134234,0.00006170899,0.0000756419,0.9280631,0.0042810044,0.010272936,0.00069182436,0.05625694],"study_design_scores_gemma":[0.000007358166,0.000030236655,0.000027783812,0.0000035981525,0.00000203195,0.000009407576,0.0000028592303,0.9978751,0.00041619918,0.0011834794,0.00043886213,0.0000030060362],"about_ca_topic_score_codex":0.0037414923,"about_ca_topic_score_gemma":0.0021976158,"teacher_disagreement_score":0.0037414923,"about_ca_system_score_codex":0.0003951463,"about_ca_system_score_gemma":0.0008201989,"threshold_uncertainty_score":0.0074394345},"labels":[],"label_agreement":null},{"id":"W4392897838","doi":"10.32920/25412560.v1","title":"Deep Reinforcement Learning Controller Design for Unmanned Aerial Vehicles","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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","funders":"","keywords":"PID controller; Control theory (sociology); Reinforcement learning; Controller (irrigation); Computer science; Trajectory; Linearization; Path (computing); Drone; Control engineering; Artificial intelligence; Control (management); Engineering; Nonlinear system; Physics","score_opus":0.025447196896500837,"score_gpt":0.265665793396314,"score_spread":0.2402185964998132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392897838","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01954146,0.0003753853,0.9755275,0.00022447733,0.000080341786,0.000054170538,0.00003311451,0.0005306805,0.003632836],"genre_scores_gemma":[0.9248258,0.00018829736,0.06892926,0.00013481284,0.000036745227,0.0001888563,0.000070071495,0.000054369455,0.005571835],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999826,0.000032921173,0.000008784352,0.00004075564,0.00005834502,0.000033061468],"domain_scores_gemma":[0.99954224,0.00017196972,0.00006636805,0.000025243642,0.00016364864,0.000030637908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007137522,0.00060555316,0.0004705812,0.00021862735,0.00022038141,0.0006325305,0.0007470025,0.00071785296,0.0017790638],"category_scores_gemma":[0.0014884567,0.0003657767,0.00024127305,0.00015507964,0.00047506616,0.00034706265,0.00066129776,0.001011511,0.00031467428],"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":[0.00003100147,0.000022379472,0.00021767696,0.000044146473,0.000018638502,0.00003607858,0.000029900615,0.9685574,0.0023725582,0.0031234447,0.0005820076,0.024964828],"study_design_scores_gemma":[0.000004136748,0.000014429556,0.000022888024,0.0000023846092,0.0000012627514,0.0000019630456,0.000001438381,0.9990094,0.00022027924,0.00053859956,0.00018232626,9.877818e-7],"about_ca_topic_score_codex":0.006972771,"about_ca_topic_score_gemma":0.0056774644,"teacher_disagreement_score":0.006972771,"about_ca_system_score_codex":0.0006889238,"about_ca_system_score_gemma":0.0009327204,"threshold_uncertainty_score":0.013864338},"labels":[],"label_agreement":null},{"id":"W4392910934","doi":"10.32920/25412560","title":"Deep Reinforcement Learning Controller Design for Unmanned Aerial Vehicles","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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","funders":"","keywords":"PID controller; Control theory (sociology); Reinforcement learning; Controller (irrigation); Trajectory; Computer science; Linearization; Path (computing); Track (disk drive); Drone; Tracking (education); Control engineering; Artificial intelligence; Engineering; Control (management); Nonlinear system; Physics","score_opus":0.025447196896500837,"score_gpt":0.265665793396314,"score_spread":0.2402185964998132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392910934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01954146,0.0003753853,0.9755275,0.00022447733,0.000080341786,0.000054170538,0.00003311451,0.0005306805,0.003632836],"genre_scores_gemma":[0.9248258,0.00018829736,0.06892926,0.00013481284,0.000036745227,0.0001888563,0.000070071495,0.000054369455,0.005571835],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999826,0.000032921173,0.000008784352,0.00004075564,0.00005834502,0.000033061468],"domain_scores_gemma":[0.99954224,0.00017196972,0.00006636805,0.000025243642,0.00016364864,0.000030637908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007137522,0.00060555316,0.0004705812,0.00021862735,0.00022038141,0.0006325305,0.0007470025,0.00071785296,0.0017790638],"category_scores_gemma":[0.0014884567,0.0003657767,0.00024127305,0.00015507964,0.00047506616,0.00034706265,0.00066129776,0.001011511,0.00031467428],"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":[0.00003100147,0.000022379472,0.00021767696,0.000044146473,0.000018638502,0.00003607858,0.000029900615,0.9685574,0.0023725582,0.0031234447,0.0005820076,0.024964828],"study_design_scores_gemma":[0.000004136748,0.000014429556,0.000022888024,0.0000023846092,0.0000012627514,0.0000019630456,0.000001438381,0.9990094,0.00022027924,0.00053859956,0.00018232626,9.877818e-7],"about_ca_topic_score_codex":0.006972771,"about_ca_topic_score_gemma":0.0056774644,"teacher_disagreement_score":0.006972771,"about_ca_system_score_codex":0.0006889238,"about_ca_system_score_gemma":0.0009327204,"threshold_uncertainty_score":0.013864338},"labels":[],"label_agreement":null},{"id":"W4393026775","doi":"","title":"Intelligent control for future and complex systems: editorial","year":2022,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 de Sherbrooke","funders":"","keywords":"Computer science; Control (management); Cognitive science; Psychology; Artificial intelligence","score_opus":0.010919122132462105,"score_gpt":0.2206457712815301,"score_spread":0.209726649149068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393026775","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005553051,0.016741289,0.0006391837,0.016641513,0.96452546,0.000012448354,0.000027394726,0.000044206292,0.0013131305],"genre_scores_gemma":[0.0013559414,0.015318932,0.0003369299,0.008084201,0.9688561,0.000018899027,0.000021468732,0.000039778304,0.005967841],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974485,0.00038696555,0.00028603373,0.0004198179,0.0012908883,0.00016778355],"domain_scores_gemma":[0.98886347,0.004299691,0.0007457711,0.0004241037,0.0045839995,0.0010830136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036027248,0.0033251466,0.0028188452,0.0020431187,0.0015883091,0.005746104,0.0023015004,0.009587644,0.0070636314],"category_scores_gemma":[0.008567152,0.000774334,0.0019101778,0.0011815751,0.0025230318,0.003369279,0.0015114695,0.010881143,0.0033949567],"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":[0.00006982176,0.000024589675,0.000033653243,0.00056239194,0.00003854417,0.00007808348,0.000015417027,0.00027243004,0.0002598564,0.00095032074,0.98082775,0.01686711],"study_design_scores_gemma":[0.00007293973,0.00006003826,0.00042404712,0.0006345357,0.00008312029,0.00017055972,0.000036946472,0.0008224092,0.00025944825,0.0025715625,0.994836,0.000028271328],"about_ca_topic_score_codex":0.0010780056,"about_ca_topic_score_gemma":0.0022827217,"teacher_disagreement_score":0.009587644,"about_ca_system_score_codex":0.0014701916,"about_ca_system_score_gemma":0.0016661182,"threshold_uncertainty_score":0.023630202},"labels":[],"label_agreement":null},{"id":"W4393103270","doi":"10.1016/j.automatica.2024.111642","title":"Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behavior","year":2024,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Honeywell (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Modular design; Stability (learning theory); Reinforcement; Control (management); Computer science; Control theory (sociology); Control engineering; Engineering; Artificial intelligence; Machine learning; Structural engineering","score_opus":0.017381132492226135,"score_gpt":0.2899690171600185,"score_spread":0.2725878846677924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393103270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016355109,0.000041697556,0.9968899,0.00006629479,0.000011674082,0.000016970467,0.000011470852,0.00014090785,0.0011855367],"genre_scores_gemma":[0.5991974,0.00032892768,0.39487752,0.00026352363,0.00009860521,0.000524994,0.000092709946,0.00022162839,0.0043947087],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936193,0.0001668459,0.000031652475,0.00016556929,0.00020569107,0.00006821603],"domain_scores_gemma":[0.9993198,0.00026825428,0.00009671117,0.000115617055,0.00014254922,0.000057005687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001782557,0.0012218021,0.00089620677,0.0004945056,0.00035007665,0.0012254226,0.0018886018,0.0011072878,0.0029194898],"category_scores_gemma":[0.002628082,0.0004657815,0.0007414246,0.00035861594,0.001987974,0.0011587196,0.0018865266,0.0021089069,0.0006060982],"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":[0.000040606155,0.00003676975,0.00018289394,0.00007265803,0.000040096427,0.000045353383,0.00006949309,0.8412629,0.0044823675,0.12331071,0.0009295395,0.02952664],"study_design_scores_gemma":[0.000009109641,0.000029027871,0.000019130799,0.000007412438,0.0000046599475,0.0000060630305,0.0000032963464,0.97325146,0.00056495634,0.025557498,0.0005416706,0.0000057427383],"about_ca_topic_score_codex":0.0016426594,"about_ca_topic_score_gemma":0.0018930709,"teacher_disagreement_score":0.0029194898,"about_ca_system_score_codex":0.0010285631,"about_ca_system_score_gemma":0.0014594357,"threshold_uncertainty_score":0.009766698},"labels":[],"label_agreement":null},{"id":"W4394930988","doi":"10.1049/cth2.12663","title":"An analytical adaptive optimal control approach without solving HJB equation for nonlinear systems with input constraints","year":2024,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Carleton University","funders":"","keywords":"Hamilton–Jacobi–Bellman equation; Nonlinear system; Optimal control; Control theory (sociology); Control (management); Computer science; Mathematical optimization; Applied mathematics; Mathematics; Artificial intelligence; Physics","score_opus":0.01645973642543845,"score_gpt":0.27292137618894996,"score_spread":0.2564616397635115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394930988","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005363625,0.00050810626,0.987495,0.00018662633,0.000058484926,0.000031247695,0.000017141016,0.000068697256,0.006270949],"genre_scores_gemma":[0.8345956,0.0013394967,0.15123473,0.00019666103,0.00017300362,0.0003483921,0.00007849157,0.000077180695,0.011956442],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997433,0.00007445475,0.000012248611,0.0000470597,0.0000954482,0.000027472963],"domain_scores_gemma":[0.9997378,0.00013085689,0.000035762514,0.00001383367,0.00007243985,0.000009237296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079864543,0.00077867607,0.0008809579,0.00046381433,0.0004841397,0.0009979308,0.0008060621,0.0010626627,0.0023619584],"category_scores_gemma":[0.0011437769,0.00047705878,0.0006515299,0.00047780148,0.00074343325,0.00068942463,0.0008361449,0.0010839604,0.0002585462],"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":[0.00002134609,0.000019819363,0.000101581594,0.00010561797,0.000021604797,0.000080369,0.000053265034,0.94655764,0.002471046,0.03340651,0.00054121617,0.01661994],"study_design_scores_gemma":[0.0000022295653,0.000008432817,0.000018849752,0.0000041367857,0.0000024827996,0.000004857059,0.0000028060067,0.997661,0.00011995427,0.001875082,0.00029817133,0.0000020223458],"about_ca_topic_score_codex":0.0073690726,"about_ca_topic_score_gemma":0.0048436513,"teacher_disagreement_score":0.0073690726,"about_ca_system_score_codex":0.0008207822,"about_ca_system_score_gemma":0.0013771784,"threshold_uncertainty_score":0.014652371},"labels":[],"label_agreement":null},{"id":"W4399968983","doi":"10.1007/s44196-024-00560-2","title":"Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"International Journal of Computational Intelligence Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"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":"Wenzhou University; McGill University","keywords":"Reinforcement learning; Temporal difference learning; Generalization; Convergence (economics); Computer science; Stability (learning theory); Algorithm; Set (abstract data type); Rate of convergence; Mathematical optimization; Mathematics; Artificial intelligence; Machine learning; Key (lock)","score_opus":0.027518540415417264,"score_gpt":0.3322516421591333,"score_spread":0.30473310174371604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399968983","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00781761,0.0001764577,0.98983264,0.00012031512,0.000048217724,0.000038507646,0.000010734529,0.00027566735,0.0016797665],"genre_scores_gemma":[0.80414176,0.00019019142,0.19104902,0.00015824955,0.00005023736,0.0002370829,0.000072230876,0.00008519615,0.004015975],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994523,0.00019297452,0.000026983418,0.0000969805,0.00016273349,0.00006804929],"domain_scores_gemma":[0.9990055,0.0005202887,0.00009486161,0.000060311508,0.00025085642,0.00006824836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015714347,0.000874219,0.001464313,0.00049625913,0.00039532204,0.0007810173,0.0015795135,0.0010668057,0.002076878],"category_scores_gemma":[0.0028734913,0.00045324815,0.00044276429,0.00039943805,0.00089741935,0.0006811932,0.0010994645,0.0015895474,0.00043760362],"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":[0.00007558585,0.00004702062,0.00034806514,0.000048465587,0.000030723688,0.00005180147,0.000039134928,0.9487655,0.0010912638,0.008502521,0.0008752001,0.04012473],"study_design_scores_gemma":[0.000005910664,0.00000823023,0.000013685565,0.0000015392694,0.0000013205164,0.0000037348088,9.220659e-7,0.99913955,0.000092415066,0.0006287626,0.000102798294,0.0000012118109],"about_ca_topic_score_codex":0.004708102,"about_ca_topic_score_gemma":0.0029098117,"teacher_disagreement_score":0.004708102,"about_ca_system_score_codex":0.00085189583,"about_ca_system_score_gemma":0.0013260355,"threshold_uncertainty_score":0.009361386},"labels":[],"label_agreement":null},{"id":"W4402264024","doi":"10.23919/acc60939.2024.10644694","title":"Synchronization Error Elimination for Heterogeneous Discrete-Time Multi-Agent Systems: A Reinforcement Learning Design Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Reinforcement learning; Computer science; Synchronization (alternating current); Multi-agent system; Discrete time and continuous time; Distributed computing; Control theory (sociology); Artificial intelligence; Control (management); Mathematics; Computer network","score_opus":0.029447153371063337,"score_gpt":0.2701662081594358,"score_spread":0.24071905478837247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402264024","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00543023,0.00009698183,0.9928,0.00010291527,0.00002179274,0.000021821068,0.00000393153,0.0000508666,0.0014714753],"genre_scores_gemma":[0.9024085,0.0002535169,0.09474688,0.0001166136,0.00005597727,0.00015419575,0.000020516263,0.0000230936,0.0022207121],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995797,0.00015289227,0.000024099632,0.00008308163,0.00012233866,0.00003791198],"domain_scores_gemma":[0.9994754,0.00024588694,0.00010312521,0.000039132472,0.00010551429,0.000030829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010222095,0.00057863386,0.0006241731,0.0002516955,0.00034040437,0.00060108094,0.000858496,0.0006564704,0.0010208028],"category_scores_gemma":[0.0014488547,0.00023063092,0.0004013272,0.00024166213,0.00082121725,0.00055980484,0.00090314855,0.0008997614,0.00014349556],"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":[0.000049718128,0.000049111906,0.00032091574,0.00007842442,0.000045112854,0.000110884575,0.00008284604,0.92655325,0.003817482,0.032707836,0.00042927222,0.03575524],"study_design_scores_gemma":[0.0000111419795,0.000029914694,0.000028072065,0.0000034931102,0.000005048302,0.000007777183,0.0000033201668,0.99690944,0.0003699438,0.002312001,0.00031710093,0.0000027268006],"about_ca_topic_score_codex":0.002033429,"about_ca_topic_score_gemma":0.0012091859,"teacher_disagreement_score":0.002033429,"about_ca_system_score_codex":0.00050602615,"about_ca_system_score_gemma":0.0007529882,"threshold_uncertainty_score":0.005406022},"labels":[],"label_agreement":null},{"id":"W4403677871","doi":"10.1109/case59546.2024.10711789","title":"An Application of Model-Free Reinforcement Learning to the Control of Aerial Vehicles With Slung Payloads","year":2024,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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","funders":"","keywords":"Reinforcement learning; Computer science; Drone; Aeronautics; Aerodynamics; Aerospace engineering; Control engineering; Marine engineering; Engineering; Artificial intelligence; Biology","score_opus":0.007227896043263617,"score_gpt":0.2377574844089583,"score_spread":0.23052958836569468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403677871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046073515,0.00020282141,0.9479841,0.00018090958,0.000048466143,0.000036130124,0.000014513035,0.00049456593,0.004965035],"genre_scores_gemma":[0.9777484,0.00006926373,0.021132186,0.000028394485,0.000011346615,0.000024589954,0.000009854557,0.000012301984,0.00096378825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99988663,0.000037199374,0.000004537835,0.000019929872,0.00003695014,0.000014735264],"domain_scores_gemma":[0.9997414,0.0001522607,0.00003228427,0.000022284916,0.00003682886,0.000014982658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031688373,0.00038839717,0.00030278484,0.00013454082,0.00018417138,0.0003456069,0.00041439018,0.00038567826,0.0007894781],"category_scores_gemma":[0.0010168744,0.00012995224,0.0002548866,0.000091699345,0.00044884734,0.00023489517,0.0004904021,0.00052698795,0.00009625502],"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":[0.000034103505,0.00002221813,0.00022331237,0.000035739213,0.0000141085,0.00007343589,0.00003833435,0.97317296,0.0039009543,0.0046567093,0.0001902246,0.017637823],"study_design_scores_gemma":[0.0000057690236,0.000047968424,0.000041301828,0.0000023000594,0.0000021048595,0.0000101239675,0.0000021805658,0.9980495,0.0007165268,0.00085564074,0.0002644624,0.000002076401],"about_ca_topic_score_codex":0.0034056394,"about_ca_topic_score_gemma":0.0021308428,"teacher_disagreement_score":0.0034056394,"about_ca_system_score_codex":0.0002357599,"about_ca_system_score_gemma":0.00043294852,"threshold_uncertainty_score":0.006771624},"labels":[],"label_agreement":null},{"id":"W4404688066","doi":"10.1109/tac.2024.3505812","title":"Linear Convergent Distributed Nash Equilibrium Seeking With Compression","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Carleton University","funders":"","keywords":"Nash equilibrium; Mathematical economics; Epsilon-equilibrium; Compression (physics); Best response; Mathematics; Computer science; Mathematical optimization; Thermodynamics; Physics","score_opus":0.010352131341741634,"score_gpt":0.2418424198324642,"score_spread":0.2314902884907226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404688066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029272879,0.00019301847,0.96649027,0.00018709456,0.000028299579,0.00008103114,0.000040175117,0.0001271055,0.0035800282],"genre_scores_gemma":[0.87784445,0.00025195227,0.11646221,0.00016479826,0.00003716353,0.00025288772,0.00009551309,0.000041827778,0.004849179],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993923,0.00019724958,0.00002708319,0.00011934607,0.00020348087,0.00006061157],"domain_scores_gemma":[0.9974728,0.0018139152,0.00020465853,0.00014011137,0.00030177506,0.000066656336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001148034,0.00081973604,0.00092293473,0.0004932316,0.00035187826,0.00065409695,0.0009120396,0.000892681,0.0017431928],"category_scores_gemma":[0.006190807,0.00029759193,0.000337795,0.00056100613,0.0010384336,0.0013383981,0.0014035433,0.0010457658,0.00022241232],"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":[0.00012292339,0.00004081213,0.000388929,0.000100022786,0.000026575735,0.000105114676,0.000097323165,0.9106919,0.0033548374,0.049204405,0.0006668567,0.03520027],"study_design_scores_gemma":[0.000012739603,0.00003067729,0.00003775214,0.000005478729,0.000003302469,0.000021179778,0.000010448765,0.9885513,0.0007488923,0.010312091,0.00026180773,0.000004341237],"about_ca_topic_score_codex":0.0020044968,"about_ca_topic_score_gemma":0.0015413059,"teacher_disagreement_score":0.0020044968,"about_ca_system_score_codex":0.0008177669,"about_ca_system_score_gemma":0.0008577266,"threshold_uncertainty_score":0.0060714483},"labels":[],"label_agreement":null},{"id":"W4404940644","doi":"10.1007/s11071-024-10698-5","title":"Constrained predictive control for consensus of nonlinear multi-agent systems by using game Q-learning","year":2024,"lang":"en","type":"article","venue":"Nonlinear Dynamics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Nonlinear system; Model predictive control; Control theory (sociology); Computer science; Multi-agent system; Control (management); Mathematics; Artificial intelligence; Machine learning; Physics","score_opus":0.01627242911429019,"score_gpt":0.27279503223025864,"score_spread":0.2565226031159685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404940644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013385931,0.000121188794,0.98426455,0.00013550333,0.000037183298,0.000039676313,0.000011706963,0.00009103035,0.001913139],"genre_scores_gemma":[0.9434032,0.00013136507,0.053725466,0.00009921405,0.00003330501,0.00016440802,0.000036886664,0.000032856962,0.0023733892],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944526,0.00019950535,0.000025303376,0.00011563432,0.0001358684,0.000078515295],"domain_scores_gemma":[0.9984907,0.00095732074,0.00012955704,0.00006622114,0.000290979,0.00006526073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015140993,0.00084302906,0.0012461216,0.0004898772,0.0006444173,0.0011215712,0.0013209204,0.00096684915,0.0017344938],"category_scores_gemma":[0.0038851094,0.00044444136,0.0005883609,0.0005686293,0.0013104073,0.0011802089,0.0018598808,0.0011463533,0.00017960383],"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":[0.0000499465,0.000048043064,0.0001544392,0.0000484498,0.000028255561,0.000036821322,0.00006807471,0.9684258,0.0008209608,0.0141036045,0.00040178368,0.015813872],"study_design_scores_gemma":[0.000005237533,0.000011524173,0.00001791297,0.0000016313405,0.0000019464317,0.000001909152,0.0000019358556,0.9976306,0.00006112186,0.0022096965,0.00005473914,0.0000016924056],"about_ca_topic_score_codex":0.0135534825,"about_ca_topic_score_gemma":0.008155203,"teacher_disagreement_score":0.0135534825,"about_ca_system_score_codex":0.0010335166,"about_ca_system_score_gemma":0.0017117929,"threshold_uncertainty_score":0.026949167},"labels":[],"label_agreement":null},{"id":"W4405166175","doi":"10.1007/s12555-024-0321-6","title":"Output Feedback Control of Variable-loaded Four-joint Manipulators With Unknown Saturated Actuator Dynamics","year":2024,"lang":"en","type":"article","venue":"International Journal of Control Automation and Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Guelph; Memorial University of Newfoundland","funders":"","keywords":"Mechatronics; Robotics; Control theory (sociology); Dynamics (music); Actuator; Variable (mathematics); Joint (building); Control (management); Robot manipulator; Artificial intelligence; Control engineering; Feedback control; Computer science; Engineering; Mathematics; Robot; Physics; Mathematical analysis; Structural engineering","score_opus":0.012951002446884024,"score_gpt":0.2280800964824202,"score_spread":0.21512909403553618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405166175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40675274,0.00040703596,0.58160245,0.00035402636,0.00015564323,0.000056861896,0.00006848115,0.0004445188,0.010158199],"genre_scores_gemma":[0.9950807,0.000054617143,0.0030187592,0.000013961649,0.000010415984,0.000023157185,0.000012972746,0.0000073329084,0.0017780259],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997824,0.000046951354,0.000013137334,0.00004621326,0.00006897145,0.0000423106],"domain_scores_gemma":[0.99949515,0.00017768223,0.00014292494,0.000031943648,0.00012465384,0.000027565518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044656306,0.00083948753,0.00055537245,0.00027203996,0.0005903877,0.0008185679,0.0009247401,0.0007961854,0.0016413954],"category_scores_gemma":[0.00097583147,0.00036437516,0.00024216865,0.00030059746,0.00080019643,0.00055432454,0.0010902898,0.00044354034,0.00021612964],"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":[0.00082421384,0.00013030229,0.00103803,0.0006075306,0.00010665819,0.0007472202,0.00068741105,0.83123827,0.090468146,0.007993905,0.0010143846,0.065143935],"study_design_scores_gemma":[0.000050270126,0.0002715826,0.00063466636,0.00001536614,0.000020614632,0.000040348055,0.00004348032,0.99303716,0.0040208506,0.0012631612,0.00059016445,0.000012290309],"about_ca_topic_score_codex":0.0039548064,"about_ca_topic_score_gemma":0.004621507,"teacher_disagreement_score":0.0039548064,"about_ca_system_score_codex":0.00039452262,"about_ca_system_score_gemma":0.0004330445,"threshold_uncertainty_score":0.007863581},"labels":[],"label_agreement":null},{"id":"W4406053750","doi":"10.1016/j.isatra.2024.12.045","title":"Fuzzy reinforcement learning based control of linear systems with input saturation","year":2025,"lang":"en","type":"article","venue":"ISA Transactions","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Control theory (sociology); Artificial intelligence; Control engineering; Control (management); Engineering","score_opus":0.006506808054315666,"score_gpt":0.2226989623850349,"score_spread":0.21619215433071923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406053750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10369233,0.0005119128,0.88487035,0.00034838,0.00017846322,0.00008382425,0.000024874955,0.0003545046,0.009935319],"genre_scores_gemma":[0.98825336,0.000073487055,0.009684074,0.000033415832,0.000017848448,0.000042106032,0.000009859886,0.00000941855,0.0018763088],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975413,0.00007507288,0.000012726577,0.00003632057,0.00007091163,0.000050824907],"domain_scores_gemma":[0.99935657,0.00033522374,0.00007812875,0.000027275973,0.00016746367,0.00003522953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082482747,0.00051847595,0.0005849969,0.0002554844,0.00038169924,0.00070064573,0.0006930101,0.0006168272,0.0017496455],"category_scores_gemma":[0.001826461,0.00023432722,0.00026535272,0.00021931448,0.00081809686,0.00042519157,0.0007549137,0.00069446035,0.00019590638],"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":[0.00019863478,0.00006883042,0.00030772813,0.000108662614,0.00003563622,0.00010565886,0.000098100456,0.9520846,0.006975018,0.00910245,0.0005510292,0.030363657],"study_design_scores_gemma":[0.000013613839,0.00004291752,0.00006395338,0.000004300694,0.0000041691187,0.0000066869757,0.0000035253008,0.998009,0.0005581266,0.0011395526,0.0001513529,0.0000028455713],"about_ca_topic_score_codex":0.0069750454,"about_ca_topic_score_gemma":0.004989906,"teacher_disagreement_score":0.0069750454,"about_ca_system_score_codex":0.00070243614,"about_ca_system_score_gemma":0.0007624137,"threshold_uncertainty_score":0.013868928},"labels":[],"label_agreement":null},{"id":"W4406274801","doi":"10.1007/s40998-024-00782-2","title":"Robust $${H}_{\\infty }$$ Output Consensus in Heterogeneous Multi-agent Discrete-Time Systems Using Q-Learning Algorithm","year":2025,"lang":"en","type":"article","venue":"Iranian Journal of Science and Technology Transactions of Electrical Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"University of Alberta","funders":"","keywords":"Robustness (evolution); Computer science; Upper and lower bounds; Discrete time and continuous time; Multi-agent system; Stability theory; Control theory (sociology); Stability (learning theory); System dynamics; Algorithm; Mathematical optimization; Mathematics; Control (management); Nonlinear system; Artificial intelligence; Machine learning","score_opus":0.009852557882422003,"score_gpt":0.22272833942317066,"score_spread":0.21287578154074865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406274801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017611582,0.00013194214,0.9798117,0.00020156492,0.000039255472,0.000037701786,0.00002354707,0.00015116237,0.0019915414],"genre_scores_gemma":[0.94323915,0.00011793265,0.05362049,0.00009886832,0.000037225913,0.0001426936,0.00007662221,0.000043829477,0.0026231285],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993018,0.00021342294,0.000036247224,0.0002081254,0.00012931628,0.00011110654],"domain_scores_gemma":[0.99817693,0.0010843567,0.00020491845,0.00008985017,0.0003731396,0.00007081887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019588124,0.0009261108,0.0018453501,0.00041196824,0.00064876233,0.0014217638,0.0014580048,0.001311506,0.002199168],"category_scores_gemma":[0.0032747814,0.00038990166,0.0006755766,0.0005119975,0.0011763957,0.00096753985,0.0016950978,0.0011790431,0.00027023454],"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":[0.00008735197,0.000047453548,0.00025081175,0.00006477328,0.00004501093,0.00004556879,0.000050892704,0.9722502,0.0009992967,0.0073545673,0.00050658913,0.018297408],"study_design_scores_gemma":[0.000007807339,0.000016782047,0.00003393172,0.0000018657535,0.0000029564444,0.000002700639,0.0000033321417,0.99862707,0.00011430123,0.0011412102,0.00004595504,0.000002049262],"about_ca_topic_score_codex":0.009247545,"about_ca_topic_score_gemma":0.0046160505,"teacher_disagreement_score":0.009247545,"about_ca_system_score_codex":0.0011550797,"about_ca_system_score_gemma":0.0014646198,"threshold_uncertainty_score":0.018387437},"labels":[],"label_agreement":null},{"id":"W4407949080","doi":"10.1109/cdc56724.2024.10886170","title":"Leveraging Control Inputs to Enforce Constraints in Differential Dynamic Programming for Nonlinear Optimization*","year":2024,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Differential dynamic programming; Nonlinear system; Dynamic programming; Differential (mechanical device); Control theory (sociology); Nonlinear programming; Mathematical optimization; Control (management); Algorithm; Mathematics; Artificial intelligence; Engineering","score_opus":0.009406045092775307,"score_gpt":0.26468479950902857,"score_spread":0.25527875441625325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407949080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059205177,0.000110194575,0.99118924,0.00009524811,0.000033121076,0.000029738081,0.000013321654,0.00009493108,0.002513627],"genre_scores_gemma":[0.7110193,0.0004376668,0.2843362,0.00017570256,0.000060210965,0.000277822,0.000072698764,0.00013645377,0.0034840938],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996184,0.00014427926,0.00001969807,0.0000613053,0.00011833088,0.000038034912],"domain_scores_gemma":[0.9992668,0.0004636479,0.00008172703,0.0000682588,0.0000857889,0.00003376723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009102377,0.0010515482,0.000682834,0.0003915973,0.0004110836,0.00090508215,0.0008348587,0.00083701295,0.0017840755],"category_scores_gemma":[0.002642741,0.00045915227,0.0004579177,0.00043830954,0.0012303893,0.0007977054,0.001839926,0.0013973768,0.00029122535],"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":[0.000029880057,0.000028062866,0.00021164193,0.00008196062,0.000013457932,0.00005921756,0.000040228075,0.9455796,0.0030411999,0.024103561,0.00039335975,0.0264179],"study_design_scores_gemma":[0.0000030164701,0.000016823811,0.000018513414,0.0000060382667,0.0000015083407,0.00000551906,0.0000027188921,0.99590826,0.0005544086,0.0029957958,0.00048431053,0.0000030663227],"about_ca_topic_score_codex":0.0027818482,"about_ca_topic_score_gemma":0.0023937342,"teacher_disagreement_score":0.0027818482,"about_ca_system_score_codex":0.0005320112,"about_ca_system_score_gemma":0.0007936694,"threshold_uncertainty_score":0.005968392},"labels":[],"label_agreement":null},{"id":"W4408017106","doi":"10.1109/tcns.2025.3546785","title":"Distributed Fixed-Time Nash Equilibrium Seeking for Noncooperative Games","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Victoria","funders":"National Natural Science Foundation of China","keywords":"Nash equilibrium; Epsilon-equilibrium; Computer science; Mathematical optimization; Game theory; Best response; Mathematical economics; Mathematics","score_opus":0.00811472733126547,"score_gpt":0.23666487334137398,"score_spread":0.2285501460101085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408017106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029548781,0.00027327528,0.96619564,0.000117179894,0.000045715555,0.000046276404,0.000012433976,0.00005341525,0.0037072035],"genre_scores_gemma":[0.9640795,0.00032335464,0.032067485,0.000051190927,0.000027188386,0.00012441585,0.000023942877,0.000017223185,0.0032856045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988368,0.00043087997,0.00004601776,0.00025357463,0.00031562115,0.00011713934],"domain_scores_gemma":[0.9981048,0.0011059439,0.00026790923,0.000075510645,0.0003547505,0.000090931775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016387048,0.0013213942,0.0010545759,0.0005409252,0.00055747584,0.0010887857,0.001366099,0.00107586,0.001053351],"category_scores_gemma":[0.0048910095,0.00033207232,0.00067774113,0.00052027893,0.0015728942,0.0013996928,0.0011442634,0.0010213961,0.0001813906],"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":[0.00008625514,0.000055711644,0.00044652086,0.0001438165,0.00006924493,0.00031793304,0.0002550175,0.87547,0.0060244175,0.1011843,0.00047367887,0.015473084],"study_design_scores_gemma":[0.000008930038,0.00004877954,0.000048860977,0.0000041775133,0.0000066426874,0.000030354675,0.00002284074,0.9847494,0.00045700677,0.014349664,0.00026580112,0.0000075180687],"about_ca_topic_score_codex":0.0032712282,"about_ca_topic_score_gemma":0.0019775906,"teacher_disagreement_score":0.0032712282,"about_ca_system_score_codex":0.0014131792,"about_ca_system_score_gemma":0.0010956775,"threshold_uncertainty_score":0.01025337},"labels":[],"label_agreement":null},{"id":"W4408346432","doi":"10.1016/j.conengprac.2025.106313","title":"Two-stage three-phase photovoltaic grid-connected inverter control method based on off-policy integral reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Control Engineering Practice","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Photovoltaic system; Inverter; Grid; Reinforcement learning; Control theory (sociology); Stage (stratigraphy); Phase (matter); Three-phase; Control (management); Computer science; Electronic engineering; Engineering; Mathematics; Electrical engineering; Physics; Voltage; Artificial intelligence; Biology","score_opus":0.007856394716716102,"score_gpt":0.30010370410503107,"score_spread":0.29224730938831495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408346432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03717323,0.00026801875,0.9527757,0.000112819595,0.000135235,0.00009466411,0.000020903328,0.00046179185,0.008957616],"genre_scores_gemma":[0.94204843,0.000117533105,0.053976346,0.00006853749,0.00003064888,0.00011107284,0.000031213644,0.000025129299,0.0035910583],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975187,0.000046878962,0.000014517467,0.0000638142,0.00009460585,0.000028305287],"domain_scores_gemma":[0.9998265,0.00004896825,0.000020565436,0.000016034073,0.000074135154,0.00001381317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035409236,0.00044782486,0.00089019956,0.00018807211,0.0005719916,0.0007062054,0.00097223354,0.00061837526,0.0025100017],"category_scores_gemma":[0.0004129148,0.00024263201,0.0004002097,0.00031632138,0.0003686666,0.0004022574,0.00048991037,0.0005950213,0.00029404825],"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":[0.0007761771,0.0003841694,0.0019853115,0.00064110145,0.00019883117,0.00042673992,0.00042087142,0.5171565,0.04296895,0.017442148,0.0034736865,0.41412553],"study_design_scores_gemma":[0.000054444507,0.00013963165,0.00037562265,0.000009943707,0.000026151274,0.00005308601,0.000009936578,0.99567336,0.0020099403,0.000787274,0.0008506557,0.000010006435],"about_ca_topic_score_codex":0.0031908415,"about_ca_topic_score_gemma":0.0045601833,"teacher_disagreement_score":0.0031908415,"about_ca_system_score_codex":0.00037517885,"about_ca_system_score_gemma":0.0006380782,"threshold_uncertainty_score":0.008396804},"labels":[],"label_agreement":null},{"id":"W4409785434","doi":"10.61091/jcmcc127b-506","title":"Reinforcement learning-based state space dimensionality reduction and optimal control strategy design in robot navigation systems","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"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":"Reinforcement learning; Dimensionality reduction; State space; Computer science; Reduction (mathematics); Control (management); State (computer science); Robot; Artificial intelligence; Curse of dimensionality; Space (punctuation); Robot learning; Control engineering; Control theory (sociology); Engineering; Mobile robot; Mathematics; Algorithm","score_opus":0.012314661775984894,"score_gpt":0.25544694319744843,"score_spread":0.24313228142146354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409785434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009101889,0.0002652973,0.988638,0.00013506917,0.000026741722,0.000031258573,0.000010322445,0.00014347467,0.0016479073],"genre_scores_gemma":[0.91872257,0.0002967675,0.07879433,0.00010896643,0.000029017463,0.00021475749,0.00003872356,0.000032464035,0.0017623832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951315,0.00013312961,0.00003161913,0.00010861496,0.0001509732,0.000062521205],"domain_scores_gemma":[0.999485,0.0002079455,0.00008333617,0.000034327684,0.00016251796,0.000026897176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008866058,0.00066331826,0.00093461305,0.00029956893,0.00035959075,0.00069456163,0.00067515014,0.000604188,0.00097480376],"category_scores_gemma":[0.0015516719,0.00042271678,0.00052866526,0.00028865543,0.0008224016,0.00061807124,0.00071972294,0.0008830787,0.0001408933],"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":[0.00003466896,0.000027764805,0.00034614498,0.00005923926,0.000030065752,0.00004298915,0.00006308237,0.95573026,0.0021005499,0.011418521,0.00040554372,0.029741256],"study_design_scores_gemma":[0.0000061049777,0.000019518424,0.000047615842,0.000002618509,0.0000033016845,0.000005671817,0.0000025849833,0.9978126,0.00027671584,0.0016490038,0.00017093797,0.000003168239],"about_ca_topic_score_codex":0.006740356,"about_ca_topic_score_gemma":0.0034516614,"teacher_disagreement_score":0.006740356,"about_ca_system_score_codex":0.00082948967,"about_ca_system_score_gemma":0.0014397406,"threshold_uncertainty_score":0.013402283},"labels":[],"label_agreement":null},{"id":"W4413337006","doi":"10.1002/rnc.70150","title":"Strategic Learning for Disturbance Rejection in Multi‐Agent Systems: Nash and Minmax in Graphical Games","year":2025,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Queen's University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada","keywords":"Minimax; Computer science; Nash equilibrium; Disturbance (geology); Mathematical optimization; Artificial intelligence; Mathematical economics; Mathematics; Biology","score_opus":0.018026759236959483,"score_gpt":0.2772433489958614,"score_spread":0.25921658975890194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413337006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01876786,0.0001544466,0.9775409,0.00025409143,0.000031194475,0.00003371673,0.000010736291,0.00007610278,0.003130985],"genre_scores_gemma":[0.9785619,0.0001191486,0.019026296,0.00010541987,0.0000234675,0.0000852056,0.000011240036,0.000022874283,0.0020444812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986816,0.00071294344,0.000045804925,0.00018598525,0.0002149654,0.00015862576],"domain_scores_gemma":[0.997778,0.0014793845,0.00027663,0.00008908099,0.00024184262,0.0001350856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002443582,0.0012208167,0.0011808854,0.00047251064,0.0004557801,0.0013758007,0.0013179001,0.0011326515,0.0016284356],"category_scores_gemma":[0.004951022,0.0004191909,0.00066394376,0.0004089832,0.0019184675,0.0014077694,0.00193892,0.001497386,0.00019139079],"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":[0.00007860687,0.00003578385,0.00027348718,0.000057709898,0.000034560202,0.00007789547,0.00008276334,0.9357537,0.00087825884,0.05481256,0.00030322693,0.007611385],"study_design_scores_gemma":[0.000009203864,0.000020923488,0.000031409007,0.0000037934417,0.0000035598246,0.00000587398,0.000008250282,0.9916958,0.00013102086,0.007977053,0.00010938091,0.0000038121373],"about_ca_topic_score_codex":0.0043802317,"about_ca_topic_score_gemma":0.002365434,"teacher_disagreement_score":0.0043802317,"about_ca_system_score_codex":0.0011487971,"about_ca_system_score_gemma":0.001052921,"threshold_uncertainty_score":0.012923062},"labels":[],"label_agreement":null},{"id":"W4415054220","doi":"10.1016/j.oceaneng.2025.123056","title":"Value decomposition reinforcement learning-based formation control for multi-USVs with incomplete information","year":2025,"lang":"en","type":"article","venue":"Ocean Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Concordia University","funders":"Shanghai Municipal Education Commission; National Natural Science Foundation of China; Natural Science Foundation of Shanghai","keywords":"Control theory (sociology); Reinforcement learning; Complete information; Convergence (economics); Controller (irrigation); Kalman filter; Position (finance); Filter (signal processing); Observer (physics); Decomposition","score_opus":0.005645907648123808,"score_gpt":0.22253361206875372,"score_spread":0.2168877044206299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415054220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022387959,0.00025477924,0.9741475,0.00022545298,0.000070630456,0.00003128253,0.000031892527,0.00012922595,0.002721214],"genre_scores_gemma":[0.9596399,0.00013354495,0.037022468,0.00009205383,0.000034843728,0.00011599389,0.000060331924,0.000032694465,0.0028680607],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996172,0.00009698549,0.000016464333,0.00009132308,0.000103924496,0.00007407787],"domain_scores_gemma":[0.99910307,0.00043042348,0.00015368796,0.000046713718,0.00020887294,0.000057332738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012018782,0.0008587685,0.0014032344,0.0003882744,0.00044085813,0.0008583021,0.0011247719,0.0010536496,0.0015853748],"category_scores_gemma":[0.002198215,0.00059532135,0.0005621762,0.00042849733,0.0011367054,0.0008671023,0.0016786252,0.0012698622,0.00017892575],"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":[0.000043386564,0.0000151541835,0.0001759386,0.000028657603,0.000019265988,0.000025741652,0.000025768204,0.9858935,0.00073006115,0.0031303505,0.00030303598,0.009609052],"study_design_scores_gemma":[0.000005955279,0.000016094056,0.00003474497,0.0000025719496,0.0000027912336,0.000002846427,0.000002516298,0.99875855,0.00011023495,0.00097216666,0.000089361696,0.0000021389808],"about_ca_topic_score_codex":0.010114377,"about_ca_topic_score_gemma":0.006163048,"teacher_disagreement_score":0.010114377,"about_ca_system_score_codex":0.00090265006,"about_ca_system_score_gemma":0.0012752655,"threshold_uncertainty_score":0.020111024},"labels":[],"label_agreement":null},{"id":"W4415820437","doi":"10.1109/tase.2025.3628059","title":"Distributed ADP-Based Optimal Security Control of Multiagent Systems Against DoS Attacks Within Differential Adversarial Game Framework","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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","funders":"Liaoning Revitalization Talents Program","keywords":"Optimal control; Differential game; Adversarial system; Multi-agent system; Nash equilibrium; Differential (mechanical device); State (computer science); Control (management); Game theory","score_opus":0.006941797571003428,"score_gpt":0.23688986323388997,"score_spread":0.22994806566288653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415820437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011647263,0.00018818192,0.9839951,0.00018338057,0.000052145268,0.0000340383,0.00001709633,0.00009177712,0.0037910163],"genre_scores_gemma":[0.9679179,0.00017524419,0.029084982,0.000073716306,0.000030575036,0.000103526785,0.00002479175,0.000015477246,0.0025738035],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992091,0.00023115438,0.000041358016,0.00021289029,0.00019491154,0.00011066649],"domain_scores_gemma":[0.99931264,0.0003076262,0.000121266494,0.000041348732,0.00017062009,0.00004655432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011483737,0.001093595,0.0011329758,0.00035812994,0.0005596653,0.0013579588,0.0011843279,0.0010729383,0.0013245645],"category_scores_gemma":[0.0015628568,0.00041604927,0.0006130268,0.0004088602,0.001217847,0.00081770914,0.0014333983,0.0013666559,0.00017496242],"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":[0.000041270363,0.000015696944,0.00018636681,0.000039618222,0.000026196789,0.00008060619,0.000045491273,0.97572494,0.0011199912,0.014612888,0.00024009547,0.007866877],"study_design_scores_gemma":[0.0000057609313,0.00002058902,0.000026902793,0.00000223631,0.0000045412366,0.0000075610697,0.0000036484469,0.997141,0.00015523982,0.002480454,0.00014920313,0.000002843384],"about_ca_topic_score_codex":0.004796414,"about_ca_topic_score_gemma":0.0023623945,"teacher_disagreement_score":0.004796414,"about_ca_system_score_codex":0.00088860973,"about_ca_system_score_gemma":0.0012113509,"threshold_uncertainty_score":0.009536982},"labels":[],"label_agreement":null},{"id":"W4416394014","doi":"10.1016/j.ifacol.2025.11.073","title":"An adaptive extremum-seeking control approach to reinforcement learning","year":2025,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Reinforcement learning; Control theory (sociology); Adaptive control; Nonlinear system; Convergence (economics); Basis (linear algebra); Stability (learning theory); Parametrization (atmospheric modeling); Optimal control","score_opus":0.011354211083284825,"score_gpt":0.2549083754554547,"score_spread":0.24355416437216987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416394014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072329957,0.00030131792,0.99018466,0.00014204218,0.000037616366,0.0000257407,0.0000071872105,0.000058364916,0.0020099685],"genre_scores_gemma":[0.903281,0.00042339836,0.09237069,0.00014573187,0.00007885989,0.00021032394,0.000024457093,0.000023965622,0.0034416104],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995332,0.00020875571,0.000017087114,0.00008875688,0.00011041286,0.00004178516],"domain_scores_gemma":[0.99945635,0.00029062334,0.000076036646,0.00002575766,0.00011997043,0.000031300275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011811744,0.00083747815,0.0009949887,0.00037836313,0.00030608635,0.00071895245,0.0012235938,0.0010648373,0.0014105211],"category_scores_gemma":[0.0018984664,0.00029255197,0.0005221676,0.00032541662,0.0010350182,0.0005671632,0.00090078,0.0012374623,0.00016238671],"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":[0.000045827852,0.000048350892,0.00026862771,0.00010461846,0.000059172547,0.00009875253,0.00008770985,0.93448716,0.0029001727,0.038284525,0.00050673255,0.02310836],"study_design_scores_gemma":[0.0000064063656,0.00003691823,0.000025583511,0.000004568666,0.0000041194044,0.000008496037,0.0000028567224,0.9967212,0.00018576537,0.0027324068,0.00026783397,0.0000037595985],"about_ca_topic_score_codex":0.00234765,"about_ca_topic_score_gemma":0.0012240637,"teacher_disagreement_score":0.00234765,"about_ca_system_score_codex":0.00070451945,"about_ca_system_score_gemma":0.0007030174,"threshold_uncertainty_score":0.006246686},"labels":[],"label_agreement":null},{"id":"W4416513177","doi":"10.1109/tcyb.2025.3630679","title":"HSMS-Based Event-Triggered Adaptive Dynamic Programming for Pursuit–Evasion Differential Games of Multiagent Systems","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Liaoning Revitalization Talents Program","keywords":"Pursuer; Multi-agent system; Dynamic programming; Graph; Artificial neural network; Optimal control; Algebraic connectivity; Decentralised system; Differential game","score_opus":0.013725855747029034,"score_gpt":0.2699817020915951,"score_spread":0.25625584634456605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416513177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021265753,0.00019018346,0.97333556,0.00017747516,0.000050551193,0.000050195507,0.000023059003,0.00008891102,0.0048181806],"genre_scores_gemma":[0.9676458,0.00017134052,0.028281212,0.00006918816,0.000024211591,0.0001549238,0.000034294484,0.000016724545,0.0036022738],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995827,0.000137362,0.00001911149,0.00009395529,0.00010819552,0.000058764217],"domain_scores_gemma":[0.9993949,0.00034618407,0.00009072765,0.000019823949,0.000109138266,0.000039203987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008733639,0.0009585831,0.0009123486,0.00034792596,0.00031153284,0.00088092557,0.00090006075,0.00091324525,0.0017545419],"category_scores_gemma":[0.0014872354,0.000335518,0.0005684919,0.00031445475,0.0008643944,0.00054702885,0.0011936533,0.0011643491,0.00013865212],"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":[0.000024785475,0.000018265297,0.00017462499,0.000034051114,0.000016825783,0.0000500361,0.000041010546,0.9830268,0.0008106479,0.010029774,0.00019227994,0.0055808662],"study_design_scores_gemma":[0.000003133839,0.000014787201,0.000019850666,0.0000011573827,0.0000016107301,0.0000025458742,0.0000030961237,0.9988452,0.00007410888,0.000948463,0.000084781626,0.0000012474375],"about_ca_topic_score_codex":0.0056521283,"about_ca_topic_score_gemma":0.0033609264,"teacher_disagreement_score":0.0056521283,"about_ca_system_score_codex":0.0008235011,"about_ca_system_score_gemma":0.0010100434,"threshold_uncertainty_score":0.011238456},"labels":[],"label_agreement":null},{"id":"W4416551961","doi":"10.1049/cth2.70091","title":"Q‐Learning‐Based Controller Design for Logarithmic Quantised Input Systems","year":2025,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Dimension (graph theory); Control theory (sociology); Logarithm; Controller (irrigation); Scaling; Quadratic equation; Optimal control; Selection (genetic algorithm); Dynamical systems theory","score_opus":0.010001194281100637,"score_gpt":0.25917201403705514,"score_spread":0.2491708197559545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416551961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011021641,0.00013175342,0.98633796,0.000105108316,0.000030013458,0.000047628357,0.000015623642,0.00012717332,0.0021831426],"genre_scores_gemma":[0.9532429,0.00011559312,0.044558022,0.00008835093,0.000019643529,0.00014315054,0.000023655064,0.0000180583,0.0017906657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957985,0.000119901975,0.000025144614,0.00009550125,0.00012974562,0.00004989076],"domain_scores_gemma":[0.9992168,0.00041582104,0.00011576511,0.000050035378,0.00017397055,0.000027481155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011732511,0.00061625696,0.0005535168,0.00028533343,0.00026348137,0.0008773884,0.00096260867,0.0006372186,0.0021453898],"category_scores_gemma":[0.0021998964,0.00027355496,0.00028806104,0.0002491888,0.0010714536,0.00068684435,0.00082639774,0.0009505112,0.00025802857],"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":[0.00006341522,0.000042020478,0.00023108862,0.00010856656,0.000020826137,0.00004790704,0.000060478334,0.9560841,0.0051874337,0.014804947,0.00037061606,0.02297877],"study_design_scores_gemma":[0.000009004986,0.000026498137,0.000027846505,0.0000046494256,0.0000022370505,0.0000039291012,0.000002605879,0.9977975,0.00048520102,0.0014393879,0.00019895926,0.0000022530764],"about_ca_topic_score_codex":0.0033280696,"about_ca_topic_score_gemma":0.0021763772,"teacher_disagreement_score":0.0033280696,"about_ca_system_score_codex":0.00079190236,"about_ca_system_score_gemma":0.00094625715,"threshold_uncertainty_score":0.0071769953},"labels":[],"label_agreement":null},{"id":"W4416937974","doi":"10.1103/5591-xjfr","title":"Reinforcement learning for optimal control of spin magnetometers","year":2025,"lang":"en","type":"article","venue":"Physical review. A/Physical review, A","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Hamiltonian (control theory); Reinforcement learning; Control theory (sociology); Quantum; Optimal control; Magnetometer; Quantum decoherence; Sensitivity (control systems); Quantum sensor","score_opus":0.01122195449124617,"score_gpt":0.3546552700581199,"score_spread":0.34343331556687373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416937974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060241714,0.001003127,0.93205667,0.00076793245,0.00013032515,0.000078710545,0.00004030245,0.00034155985,0.0053396556],"genre_scores_gemma":[0.95748454,0.00025642334,0.040227678,0.00013292175,0.0000377958,0.00012522488,0.000034504923,0.00003490706,0.0016659717],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956447,0.00021241004,0.000017022492,0.000075743126,0.00007889036,0.00005149184],"domain_scores_gemma":[0.9977393,0.0016883478,0.00023698868,0.000081725935,0.00018759885,0.00006594917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016153919,0.00079868955,0.00093465217,0.00037474095,0.00028874818,0.0007686715,0.00079192605,0.00082076073,0.0014423459],"category_scores_gemma":[0.0063732835,0.00040330656,0.00043460255,0.00023452635,0.001523016,0.000569172,0.00077580597,0.0013658603,0.00014286127],"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":[0.000032386695,0.000017062424,0.0002126437,0.000041669664,0.000019893243,0.000016108886,0.000016212101,0.98559004,0.0007053248,0.00765062,0.00015614452,0.0055419346],"study_design_scores_gemma":[0.0000081003245,0.000013476594,0.000041708885,0.0000049265136,0.0000025901973,0.0000020322705,0.0000015480468,0.99680907,0.00017790234,0.0028301347,0.000106148516,0.000002402858],"about_ca_topic_score_codex":0.004594304,"about_ca_topic_score_gemma":0.0031504265,"teacher_disagreement_score":0.004594304,"about_ca_system_score_codex":0.0012398378,"about_ca_system_score_gemma":0.0010873569,"threshold_uncertainty_score":0.009135127},"labels":[],"label_agreement":null},{"id":"W6889105574","doi":"10.25384/sage.19100454.v1","title":"sj-docx-1-cjk-10.1177_20543581211072330 – Supplemental material for Designing an App for Immunosuppression Adherence and Communication: A Qualitative Approach","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Immunosuppression; Kidney disease; Qualitative research; Disease; mHealth; Kidney transplant","score_opus":0.07274771029118997,"score_gpt":0.33899621623686726,"score_spread":0.2662485059456773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889105574","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063656555,0.00081681734,0.028968144,0.009219207,0.0031860163,0.011367575,0.47418597,0.02499141,0.4408991],"genre_scores_gemma":[0.044918656,0.0016066621,0.08721057,0.008993587,0.0006358864,0.046053186,0.13532625,0.019983625,0.65527165],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99912316,0.0003087846,0.00008031119,0.00008234519,0.00031674275,0.000088741035],"domain_scores_gemma":[0.9774316,0.016648153,0.0002808362,0.0006014118,0.0043136314,0.00072441483],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027090195,0.0006806876,0.000596962,0.00147957,0.0012131354,0.0024430903,0.0015118876,0.0017495272,0.84619886],"category_scores_gemma":[0.024644403,0.0005808397,0.00044522923,0.0014145776,0.00061850675,0.0025343685,0.0020062784,0.0016626455,0.34882846],"study_design_candidate":"qualitative","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":[0.000083995656,0.00010561219,0.00018455896,0.0010430405,0.000002900055,0.000054621636,0.0009394212,0.00008998511,0.00024068893,0.0015261987,0.96811754,0.0276115],"study_design_scores_gemma":[0.00021233778,0.00010138105,0.002056319,0.0012092978,0.000014933084,0.00013582206,0.0026167869,0.00038879007,0.00072600576,0.0047329445,0.9877517,0.000053643435],"about_ca_topic_score_codex":0.006600544,"about_ca_topic_score_gemma":0.015359651,"teacher_disagreement_score":0.84619886,"about_ca_system_score_codex":0.0017581191,"about_ca_system_score_gemma":0.0026418224,"threshold_uncertainty_score":0.21937865},"labels":[],"label_agreement":null},{"id":"W6892972884","doi":"10.5281/zenodo.13312339","title":"Quantum Étale","year":2024,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"The Journal of Student Science and Technology","funders":"","keywords":"Quantum; Quantum system; Field (mathematics); Work (physics); Quantum entanglement","score_opus":0.04369204971112968,"score_gpt":0.2626687139271764,"score_spread":0.21897666421604672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892972884","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07277307,0.0015608382,0.10651367,0.0057517723,0.0029487517,0.00010858859,0.0012194731,0.000739877,0.80838394],"genre_scores_gemma":[0.7182175,0.001480378,0.021188742,0.0019718353,0.0021237733,0.00017038209,0.0008802465,0.0006088103,0.2533584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99945277,0.00008129894,0.000018349756,0.00014706617,0.00019191418,0.000108559514],"domain_scores_gemma":[0.99966574,0.000065075656,0.000033136337,0.000075578704,0.00009005775,0.00007040961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003028183,0.0006271522,0.0007318349,0.0013370196,0.0026155706,0.0027193052,0.00054546585,0.0012742565,0.03709735],"category_scores_gemma":[0.00090503297,0.00029788094,0.00061979285,0.0008404267,0.0023768356,0.0033495987,0.002125836,0.0026511147,0.004487475],"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":[0.000008934843,0.000005322107,0.000017783466,0.00001043433,0.0000029168775,0.000013660021,0.000025794176,0.00013915055,0.00034037995,0.9948855,0.0024109622,0.0021391162],"study_design_scores_gemma":[0.000011756067,0.0000101614705,0.00013424794,0.0000071950485,0.0000047407616,0.00009465505,0.000042431217,0.0021918167,0.00060660194,0.968048,0.028836634,0.000011797228],"about_ca_topic_score_codex":0.0010260117,"about_ca_topic_score_gemma":0.0007426656,"teacher_disagreement_score":0.03709735,"about_ca_system_score_codex":0.0013531671,"about_ca_system_score_gemma":0.00042091336,"threshold_uncertainty_score":0.12410307},"labels":[],"label_agreement":null},{"id":"W6925069730","doi":"10.17605/osf.io/6z352","title":"Supporting information for Scripts and datasets related to Carturan et al. 2023. Bumble bee pollination and the wildflower/crop trade-off: When do wildflower enhancements improve crop yield?","year":2022,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Wildflower; Pollination; Crop; Scripting language; Pollinator; Moorland","score_opus":0.008014052949171206,"score_gpt":0.2580603256777459,"score_spread":0.2500462727285747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925069730","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000285353,0.000058806567,0.0010512979,0.00012088934,0.00007541982,0.00008415968,0.99267864,0.003056331,0.0025890663],"genre_scores_gemma":[0.004944632,0.00017023922,0.008816272,0.000508478,0.00007579201,0.001959364,0.97160316,0.00628479,0.0056372504],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99864835,0.00034137792,0.00014723369,0.00029910897,0.0003628007,0.00020104395],"domain_scores_gemma":[0.99005896,0.00594447,0.00044425554,0.0014499178,0.0015278044,0.0005745805],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0037558367,0.0019075068,0.0025018025,0.002785222,0.0013873932,0.003218925,0.0033458741,0.0019287834,0.64199257],"category_scores_gemma":[0.02013254,0.00092952483,0.0017954953,0.0040693395,0.00050552207,0.0023596247,0.0019896263,0.0019895344,0.30541894],"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":[0.00024700662,0.00006832456,0.000913282,0.0012396984,0.000075381344,0.000028192191,0.000042328273,0.00071089313,0.00034800844,0.001311858,0.98916036,0.005854762],"study_design_scores_gemma":[0.0015439269,0.00012294622,0.006435051,0.0007995851,0.00018962493,0.00011914163,0.0002551288,0.0035809826,0.0015093338,0.021103235,0.9642149,0.00012601579],"about_ca_topic_score_codex":0.014971242,"about_ca_topic_score_gemma":0.025358746,"teacher_disagreement_score":0.64199257,"about_ca_system_score_codex":0.0013560588,"about_ca_system_score_gemma":0.0027102553,"threshold_uncertainty_score":0.5106541},"labels":[],"label_agreement":null},{"id":"W6979308798","doi":"","title":"Strategic learning for disturbance rejection in multi-agent systems: Nash and Minmax in graphical games","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Basic and Applied Basic Research Foundation of Guangdong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Minimax; Nash equilibrium; Stability (learning theory); Reinforcement learning; Graphical model; Game theory; Control (management)","score_opus":0.03439879304186491,"score_gpt":0.2793073937287574,"score_spread":0.2449086006868925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979308798","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014533692,0.00019925625,0.98212576,0.00025504953,0.000031870808,0.000027040696,0.000009011996,0.0000731748,0.0027451743],"genre_scores_gemma":[0.97072834,0.00021449964,0.026616355,0.00012377663,0.00003580699,0.000091800524,0.000013040189,0.0000321749,0.0021441611],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874014,0.0007061527,0.00004221734,0.00017607963,0.0001946997,0.00014066449],"domain_scores_gemma":[0.99788445,0.0014672573,0.0002338245,0.00009060314,0.00019827667,0.00012549499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024987583,0.0013613215,0.0011662234,0.0004920585,0.00048463925,0.0014438651,0.0012700078,0.0011528296,0.0014622359],"category_scores_gemma":[0.0052433764,0.00043227736,0.00067409186,0.00044865673,0.0021130403,0.0015761865,0.0019297502,0.0016072937,0.00018849796],"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":[0.00008658058,0.000039755778,0.00031456116,0.0000723105,0.000039642277,0.000090775655,0.00010890295,0.9070558,0.0009231576,0.07919416,0.00038739922,0.01168698],"study_design_scores_gemma":[0.000010492227,0.000023589173,0.00003549451,0.0000044956837,0.000004511941,0.0000081004,0.00000977365,0.98532444,0.00014562717,0.0142736565,0.00015543545,0.0000043881964],"about_ca_topic_score_codex":0.0038373708,"about_ca_topic_score_gemma":0.0023273649,"teacher_disagreement_score":0.0038373708,"about_ca_system_score_codex":0.0011614746,"about_ca_system_score_gemma":0.0010593816,"threshold_uncertainty_score":0.013214886},"labels":[],"label_agreement":null},{"id":"W7123338223","doi":"10.1109/cdc57313.2025.11312866","title":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Reinforcement learning; Convergence (economics); Stability (learning theory); Nonlinear system; Representation (politics); Control theory (sociology); Controller (irrigation); Control (management); Artificial neural network","score_opus":0.010934864706497797,"score_gpt":0.24366932706177477,"score_spread":0.23273446235527698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123338223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017614508,0.00032559983,0.97817284,0.0004224348,0.000039675677,0.00003923023,0.000022047108,0.00031599417,0.003047638],"genre_scores_gemma":[0.96729547,0.00026437562,0.02991538,0.00014021735,0.000055268833,0.00013928999,0.000041910156,0.00006174899,0.0020864746],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990645,0.00033576877,0.000041650375,0.00014043335,0.000311543,0.000106060375],"domain_scores_gemma":[0.99590755,0.0028002085,0.00048018075,0.00014261904,0.0005482842,0.000121141304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021520394,0.0011480356,0.0009801161,0.0004930609,0.00052664545,0.0008980514,0.000837311,0.0009860467,0.0021330644],"category_scores_gemma":[0.008736051,0.00043676177,0.00040520434,0.00035543015,0.0017767679,0.00082602346,0.0013530337,0.0015771706,0.00030772193],"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":[0.000041379466,0.000022025648,0.00020814154,0.00005619664,0.000016814785,0.000040852392,0.000031578522,0.97622967,0.00076477404,0.015635232,0.00034257426,0.006610673],"study_design_scores_gemma":[0.000007834078,0.000011415682,0.000023018607,0.000003402632,0.0000012624125,0.0000031224456,0.0000015226774,0.99591833,0.00011830273,0.003828838,0.00008111272,0.0000017856279],"about_ca_topic_score_codex":0.0062669353,"about_ca_topic_score_gemma":0.0032581198,"teacher_disagreement_score":0.0062669353,"about_ca_system_score_codex":0.0014249146,"about_ca_system_score_gemma":0.0019217792,"threshold_uncertainty_score":0.012460887},"labels":[],"label_agreement":null},{"id":"W7123346315","doi":"10.1109/cdc57313.2025.11312819","title":"Complementary Tracking Control for Linear Systems Subject to External Disturbances and Stochastic Noise","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Control theory (sociology); Noise (video); Tracking (education); Controller (irrigation); Linear system; Robust control; Robustness (evolution); Noise measurement","score_opus":0.017747322238096663,"score_gpt":0.2869506044502084,"score_spread":0.26920328221211176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123346315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013871016,0.00017175905,0.98285705,0.00008422348,0.0000432812,0.000023590204,0.000011738103,0.00014723476,0.0027900909],"genre_scores_gemma":[0.93965834,0.00043892773,0.05326157,0.00013883287,0.00008250756,0.00019323772,0.0000760917,0.00004414829,0.0061063464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988439,0.00027342138,0.00003977311,0.00021225246,0.0005228114,0.00010773237],"domain_scores_gemma":[0.9991635,0.00043626054,0.00016182085,0.0000448753,0.00016552157,0.000027923348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012449328,0.0009187305,0.00074374146,0.00039361385,0.00038196295,0.0010946675,0.00069812726,0.0007687184,0.0010951572],"category_scores_gemma":[0.002504441,0.00031076424,0.0005826098,0.000440386,0.000768487,0.00058903755,0.0010270517,0.000887978,0.00020594023],"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":[0.00018623621,0.00006665995,0.00038769492,0.0002094565,0.000082309816,0.00015730473,0.00015048234,0.9059454,0.012848773,0.031751562,0.0007008615,0.04751313],"study_design_scores_gemma":[0.000011585809,0.000090156966,0.00012618849,0.000008062715,0.000010806003,0.000013101314,0.000008211754,0.9951309,0.0012134186,0.0028448545,0.0005363264,0.000006411296],"about_ca_topic_score_codex":0.00461455,"about_ca_topic_score_gemma":0.003342251,"teacher_disagreement_score":0.00461455,"about_ca_system_score_codex":0.00087577093,"about_ca_system_score_gemma":0.0015766803,"threshold_uncertainty_score":0.00917542},"labels":[],"label_agreement":null},{"id":"W7123357605","doi":"10.1109/cdc57313.2025.11312431","title":"Convergence of regularized agent-state-based Q-learning in POMDPs","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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":"Convergence (economics); Salient; Regularization (linguistics); Reinforcement learning; State (computer science); Fixed point; Stationary point","score_opus":0.007703628012805853,"score_gpt":0.24500675620056078,"score_spread":0.23730312818775492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123357605","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037014835,0.00021228188,0.9594768,0.00037054304,0.000031623167,0.000065721426,0.000042870117,0.00017929947,0.0026059137],"genre_scores_gemma":[0.89138657,0.0001974962,0.105859056,0.00016931359,0.000027800093,0.00023628998,0.000100257785,0.00009323866,0.0019299567],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985648,0.0007752973,0.00006735646,0.00020966263,0.00022619552,0.00015671588],"domain_scores_gemma":[0.98825455,0.0094165085,0.00068896165,0.00043716954,0.00089629577,0.0003064833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005508339,0.000779616,0.0013295639,0.0006283317,0.00050487876,0.0011013316,0.0014640542,0.0013478467,0.002725217],"category_scores_gemma":[0.024207784,0.0006139585,0.00066595647,0.00040129968,0.0022995851,0.0016973887,0.0018004494,0.0018568937,0.00026054712],"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":[0.00004132995,0.000027518186,0.00057426275,0.000046306635,0.000025441524,0.000042241638,0.000066853354,0.94638777,0.0002713708,0.04733,0.00027477683,0.0049120192],"study_design_scores_gemma":[0.000007354297,0.000012598041,0.000032654465,0.000004641394,0.0000017395687,0.0000038907515,0.0000050020594,0.9853615,0.00006575588,0.014412802,0.000089617,0.0000023527903],"about_ca_topic_score_codex":0.006648969,"about_ca_topic_score_gemma":0.00273533,"teacher_disagreement_score":0.006648969,"about_ca_system_score_codex":0.0018259916,"about_ca_system_score_gemma":0.0021370966,"threshold_uncertainty_score":0.029131174},"labels":[],"label_agreement":null},{"id":"W7123361893","doi":"10.1109/cdc57313.2025.11312082","title":"Discrete-Time Mean-Field-Type Control Problems with Higher-Order Costs","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","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 du Québec à Trois-Rivières","funders":"Air Force Office of Scientific Research","keywords":"Multiplicative function; Optimal control; Quadratic equation; Key (lock); Control (management); State (computer science)","score_opus":0.005777589889421146,"score_gpt":0.23194398901574464,"score_spread":0.2261663991263235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123361893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011487636,0.00027640245,0.9818333,0.00041765865,0.00007114264,0.000041923635,0.000066876964,0.000056452198,0.005748758],"genre_scores_gemma":[0.8804447,0.0006940532,0.102183625,0.00026020294,0.00016410042,0.0002856566,0.00016322544,0.000103659826,0.015700802],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99908936,0.00025728258,0.000042657288,0.00021109347,0.0002605014,0.0001391591],"domain_scores_gemma":[0.9967424,0.0023681514,0.00033333316,0.00013335874,0.00030891906,0.00011380017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00206256,0.001432463,0.0016082588,0.0006742782,0.0005387995,0.0021177703,0.0011163034,0.0019079127,0.0034500526],"category_scores_gemma":[0.004843851,0.00054240646,0.001032202,0.0007359613,0.0016468524,0.0015352952,0.0014287008,0.0026495277,0.000201973],"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":[0.000035714213,0.000041372754,0.0002230621,0.00011591563,0.00002883701,0.000065434644,0.00004739186,0.8854018,0.0007410645,0.106049106,0.00067176577,0.006578589],"study_design_scores_gemma":[0.0000060875095,0.000011178346,0.000053104784,0.000004219579,0.0000035068717,0.000007371305,0.0000054476045,0.9860103,0.00013216362,0.013519951,0.0002422897,0.00000440065],"about_ca_topic_score_codex":0.0073624374,"about_ca_topic_score_gemma":0.0051104,"teacher_disagreement_score":0.0073624374,"about_ca_system_score_codex":0.0020172908,"about_ca_system_score_gemma":0.0020111373,"threshold_uncertainty_score":0.014639139},"labels":[],"label_agreement":null}]}