{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":117,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":117,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"9d470e2ffb3e","filters":{"topic":"Adaptive Dynamic Programming Control"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006646327283831069,"gpt":0.2161807311212928,"spread":0.2095344038374617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004820779,0.0002737084,0.0003771543,0.0002230279,0.000612219,0.0002646735,0.0002378137,0.0001322665,0.000001841429],"category_scores_gemma":[0.00001690338,0.0002286927,0.00006568386,0.0004871537,0.0001421089,0.0004111968,0.00000514542,0.0005816243,0.000003527122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001283714,"about_ca_system_score_gemma":0.00005190011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004132715,"about_ca_topic_score_gemma":0.00001517156,"domain_scores_codex":[0.9977472,0.000520083,0.0005009798,0.0004500372,0.0003811761,0.0004005703],"domain_scores_gemma":[0.9986014,0.0002262136,0.000448077,0.0002830006,0.000317127,0.0001241895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001123266,0.00002800468,0.0001128123,0.00003825957,0.0000911016,0.000003939789,0.0004411284,0.9454861,0.0001592682,0.000242258,0.000002728733,0.05328212],"study_design_scores_gemma":[0.00117705,0.001783256,0.00008631256,0.0001775765,0.00004179279,0.00006555676,0.000126202,0.9959875,0.00002471137,3.13216e-7,0.0003014204,0.0002282916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01090692,0.0003521061,0.9868983,0.00007878843,0.0007392174,0.000765677,8.180486e-7,0.0002292851,0.00002888328],"genre_scores_gemma":[0.9985393,0.00003356736,0.0005840731,0.00003217577,0.0003234045,0.00008598298,0.000004370433,0.00002875924,0.0003683418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9876324,"threshold_uncertainty_score":0.9325817,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006590390268237936,"gpt":0.2214699010147289,"spread":0.214879510746491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007298517,0.000396166,0.0005265113,0.0002654455,0.0003335553,0.0006574792,0.000735161,0.0001995608,0.00007274446],"category_scores_gemma":[0.00002189299,0.0003602442,0.0002440562,0.0007566151,0.00004939054,0.002138428,0.00001106261,0.0003877014,0.0002003602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003466259,"about_ca_system_score_gemma":0.0001008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004170291,"about_ca_topic_score_gemma":0.000006181112,"domain_scores_codex":[0.9970745,0.0001962003,0.0008771374,0.0005215736,0.0006753388,0.0006552417],"domain_scores_gemma":[0.9978063,0.0005248147,0.0003441877,0.0009463464,0.0001857126,0.0001926506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001111865,0.0003011156,0.00004862812,0.00003600491,0.000243741,0.000002963665,0.000329844,0.6588897,0.0006953157,0.001041559,0.0000321241,0.3382678],"study_design_scores_gemma":[0.005417902,0.0001610652,0.0006896498,0.00009407811,0.00007181546,0.00001791645,0.00006664491,0.9927353,0.00008741263,0.0001171309,0.000167281,0.0003738023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01532939,0.00002240425,0.9807597,0.0002625393,0.0009669216,0.001698386,0.00002427834,0.0008619356,0.00007442544],"genre_scores_gemma":[0.9790278,0.000001712119,0.01985493,0.000738323,0.00003996473,0.0002579949,0.00002006262,0.00002521078,0.00003399032],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9636984,"threshold_uncertainty_score":0.999885,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.009236036983152505,"gpt":0.2210814403115666,"spread":0.2118454033284141,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000220691,0.000223811,0.0002988975,0.0001746528,0.0001271518,0.00007851372,0.0003880321,0.0001074578,0.000008389435],"category_scores_gemma":[0.000004187186,0.0002048854,0.00009157255,0.0003518274,0.00007821956,0.0002824537,0.000006892122,0.0002989393,0.00004149703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002589643,"about_ca_system_score_gemma":0.00009505002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001114432,"about_ca_topic_score_gemma":0.0000104207,"domain_scores_codex":[0.9983357,0.00009001292,0.0003924385,0.0003737748,0.0004980206,0.0003100441],"domain_scores_gemma":[0.9987833,0.0001119133,0.0002715271,0.0005453208,0.0002115954,0.00007628662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004886964,0.00004748647,0.00004815929,0.00002585362,0.00007060875,0.000001602188,0.000267196,0.9925767,0.0009848162,0.002200963,6.952109e-7,0.003727091],"study_design_scores_gemma":[0.0006707042,0.0006743278,0.00005939414,0.0001312147,0.00005210214,0.00001616909,0.00005753947,0.9970777,0.0008823477,0.000009718563,0.0001352555,0.0002335321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06811907,0.00001433037,0.930522,0.00003264903,0.0003056104,0.0005023485,0.00000413216,0.0001360873,0.0003637435],"genre_scores_gemma":[0.9428082,0.000002904211,0.053389,0.000009933794,0.00002023783,0.00001120303,0.000005184946,0.0000292577,0.003724102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.877133,"threshold_uncertainty_score":0.8354985,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01517488254014964,"gpt":0.2595307435211804,"spread":0.2443558609810307,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003427774,0.0002934615,0.0003468468,0.0001394927,0.0006241458,0.0004272615,0.0003769122,0.00007242877,0.000001432337],"category_scores_gemma":[0.000007679695,0.0002383075,0.00004181279,0.0006824944,0.00009127535,0.0004400292,0.00007007579,0.0001578546,0.00001421157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002686635,"about_ca_system_score_gemma":0.0001023299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001839903,"about_ca_topic_score_gemma":0.000003090484,"domain_scores_codex":[0.9978552,0.000175377,0.0003807634,0.0006155946,0.0004498485,0.0005232234],"domain_scores_gemma":[0.9986292,0.0001766943,0.0002647018,0.0005401484,0.0002071966,0.0001821285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006188562,0.00003191,0.001466954,0.00006707534,0.00008602951,0.0000150758,0.0005114914,0.9852293,0.002166573,0.009899206,0.00004229003,0.0004221698],"study_design_scores_gemma":[0.00166389,0.0001911389,0.0000715889,0.000172636,0.00002248344,0.00006360534,0.0009324583,0.9954854,0.0001764272,0.000001897046,0.0009142016,0.0003042775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009770974,0.000473082,0.9861659,0.000169242,0.0001197617,0.002271989,0.000002288169,0.0009193888,0.0001073189],"genre_scores_gemma":[0.9801533,0.000001574053,0.01615902,0.00007048986,0.0001817531,0.00325486,0.00003318865,0.0000433539,0.0001025159],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9703823,"threshold_uncertainty_score":0.9717899,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008061752130508127,"gpt":0.2324828822992374,"spread":0.2244211301687292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007264479,0.000444009,0.001145964,0.000601619,0.0001827985,0.0001131783,0.0009341275,0.0001277859,0.000260821],"category_scores_gemma":[0.00006414254,0.000281864,0.0004973133,0.001544965,0.000380693,0.0006906688,0.000004625329,0.0001810152,0.00006083838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002672852,"about_ca_system_score_gemma":0.0002115796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006619543,"about_ca_topic_score_gemma":0.0001480299,"domain_scores_codex":[0.996577,0.0004019541,0.0008608961,0.0007561859,0.0007824229,0.0006215675],"domain_scores_gemma":[0.995425,0.002066581,0.0004625143,0.001461752,0.0003468878,0.0002373074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002215993,0.002611919,0.001272265,0.0000969093,0.01804241,0.00005742908,0.001267952,0.08772583,0.0454606,0.00356512,0.00002618149,0.8376574],"study_design_scores_gemma":[0.007058157,0.001078409,0.002144423,0.00008371926,0.001820734,0.000004994794,0.00003085266,0.9861073,0.001192033,0.00005134521,0.00003242839,0.0003956028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04178369,0.00001268658,0.9545543,0.001131252,0.0001392628,0.001376465,0.0004251974,0.0005036169,0.0000734916],"genre_scores_gemma":[0.9912183,0.000001869534,0.008146562,0.0001050594,0.00001374132,0.0003797693,0.000002982018,0.00002897641,0.0001027062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9494346,"threshold_uncertainty_score":0.9999633,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01443954020173,"gpt":0.2358165193500147,"spread":0.2213769791482847,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002892789,0.0004189312,0.0003168505,0.00031562,0.0004235445,0.000135215,0.0006915094,0.0002040388,0.00002225251],"category_scores_gemma":[0.00001945514,0.0004137735,0.0002357611,0.0005215288,0.0003801333,0.0002814698,0.000005179082,0.0005984151,0.0002023663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00036445,"about_ca_system_score_gemma":0.0003123199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001599659,"about_ca_topic_score_gemma":0.00006917866,"domain_scores_codex":[0.9971793,0.0001335954,0.0003935723,0.0008660631,0.000785697,0.0006418314],"domain_scores_gemma":[0.9979177,0.0003583516,0.0001633765,0.0008369252,0.000487749,0.0002358812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005915494,0.0008558883,0.000007007808,0.000005118742,0.0001370143,0.00001096427,0.0002422424,0.8772695,0.000186937,0.001880747,0.00006304107,0.11875],"study_design_scores_gemma":[0.002217538,0.00243869,0.0001358404,0.00004790682,0.00007655918,0.000007437991,0.00002206039,0.9931522,0.0005256954,0.0007431299,0.000250222,0.0003827137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004754764,0.00001060521,0.9959368,0.0005989567,0.0008691679,0.000838486,0.0001123737,0.0005971235,0.0005610235],"genre_scores_gemma":[0.8477375,0.000001979948,0.150741,0.0007573437,0.00009998155,0.0001973588,0.000005032484,0.00004469456,0.0004151362],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.847262,"threshold_uncertainty_score":0.9998314,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007921224045344375,"gpt":0.2191847700500824,"spread":0.211263546004738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004951254,0.0003505471,0.0002909404,0.0002100388,0.0004481878,0.0002308138,0.0006023116,0.0001606096,0.000001979764],"category_scores_gemma":[0.00001195411,0.000290506,0.0001914798,0.0003839147,0.0001304724,0.0002209894,0.00000661278,0.0004833188,0.00002718039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003733061,"about_ca_system_score_gemma":0.00009617294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002660544,"about_ca_topic_score_gemma":0.0000835295,"domain_scores_codex":[0.9977982,0.0001183568,0.0003695146,0.0007193924,0.0004765805,0.0005179778],"domain_scores_gemma":[0.9979287,0.0007814731,0.0001804154,0.0008015906,0.0001802424,0.0001275396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002800474,0.0002729067,0.00004993775,0.0001232382,0.0001329427,0.000007026171,0.0005127892,0.664888,0.0006987239,0.004233475,0.000003087632,0.3287978],"study_design_scores_gemma":[0.001483971,0.001101173,0.0002566977,0.0002261266,0.0001156382,0.00002182591,0.0002808369,0.9956645,0.0001919444,0.0001146377,0.0002742035,0.0002684401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01099495,0.0001149583,0.9844792,0.0005427347,0.00115797,0.002183032,0.00005326343,0.0004324427,0.00004137969],"genre_scores_gemma":[0.9381726,0.00001734253,0.06116694,0.0000874617,0.00002460131,0.0003317215,0.000003899992,0.0000483804,0.0001469922],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9271777,"threshold_uncertainty_score":0.9999547,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03467231661912773,"gpt":0.3130906819506749,"spread":0.2784183653315472,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003962808,0.0001953444,0.0002494083,0.0000861023,0.0008064196,0.0001792063,0.001100736,0.00008792395,0.000006761138],"category_scores_gemma":[0.00005786114,0.0002087872,0.0001125481,0.0004961216,0.0001312053,0.0003807997,0.00002685796,0.0003751583,0.000004648353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008943716,"about_ca_system_score_gemma":0.00005825222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000021086,"about_ca_topic_score_gemma":0.00001372022,"domain_scores_codex":[0.9983627,0.0004929765,0.0003808937,0.0003590375,0.0001116339,0.0002927928],"domain_scores_gemma":[0.9976309,0.0008742348,0.0001730462,0.0009335223,0.000203513,0.000184769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003949696,0.00007824972,0.000004659868,0.00001650153,0.00008126676,2.268658e-7,0.0008348122,0.8430474,0.0008772339,0.00843057,0.000006993629,0.1465826],"study_design_scores_gemma":[0.001017025,0.0001543323,0.00001192897,0.00001730823,0.00005309659,0.000001704834,0.0000888592,0.9950805,0.0007918607,0.0001318703,0.002443239,0.0002082518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005413306,0.000123343,0.989764,0.008756427,0.00009347905,0.0007561928,0.00001900429,0.0003999856,0.00003347487],"genre_scores_gemma":[0.5523112,0.0002956831,0.4467357,0.0002907122,0.000007183801,0.0002651855,0.00005570806,0.0000144735,0.00002418829],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.552257,"threshold_uncertainty_score":0.8514095,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.009988373953563707,"gpt":0.2409104974390513,"spread":0.2309221234854876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002151993,0.0001965609,0.0003059036,0.0001265548,0.00005919811,0.0002253125,0.0008327547,0.00008262914,0.00006485546],"category_scores_gemma":[0.0002114044,0.0001713601,0.00007404223,0.0003393056,0.00008200503,0.0005853847,0.0002850438,0.0001966507,0.0005220434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000659126,"about_ca_system_score_gemma":0.0000652949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000196269,"about_ca_topic_score_gemma":0.00003001162,"domain_scores_codex":[0.9982748,0.0001634327,0.0004319058,0.0003772438,0.0003034566,0.0004491347],"domain_scores_gemma":[0.9987228,0.0002629347,0.0001199271,0.0007023371,0.0000736748,0.0001183596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001678486,0.0009584652,0.01283092,0.0001930606,0.0001657432,0.0000899419,0.004341112,0.0005283568,0.002101446,0.187752,0.0008831192,0.7901391],"study_design_scores_gemma":[0.0004141154,0.000141713,0.0564101,0.00003643093,0.00000616738,0.000002817615,0.00002734778,0.9356006,0.0000525522,0.006967905,0.0001355594,0.0002047098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3786938,0.00003409657,0.6184509,0.001042268,0.0001716316,0.0004775153,0.000001183584,0.0004165859,0.000711949],"genre_scores_gemma":[0.9071442,0.000002316264,0.09246229,0.0001130181,0.00003866366,0.0001464118,0.000003194237,0.00001133652,0.00007858854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9350722,"threshold_uncertainty_score":0.6987861,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004149845208367344,"gpt":0.1843646881307481,"spread":0.1802148429223808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002737512,0.000237157,0.0003354177,0.0004270031,0.0001569028,0.0001637893,0.0003110416,0.00007728941,0.000002473287],"category_scores_gemma":[0.0002326015,0.0002421123,0.00003907815,0.0008328305,0.00002497529,0.0008415338,0.000191505,0.0003489773,0.000009433037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002968205,"about_ca_system_score_gemma":0.00005877617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008636097,"about_ca_topic_score_gemma":0.0000142118,"domain_scores_codex":[0.9985327,0.0001078897,0.0002359047,0.0003817099,0.0002831705,0.0004586286],"domain_scores_gemma":[0.9992022,0.0002836371,0.00008462312,0.000193338,0.00008753432,0.0001486619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001485317,0.00001841087,0.0002260587,0.000245463,0.0001843388,0.0004792929,0.002196113,0.5689987,0.003349237,0.4198808,0.000005990868,0.004267027],"study_design_scores_gemma":[0.001612378,0.000856215,0.0007252793,0.0001267198,0.00002367599,0.0000266118,0.0009233522,0.9950506,0.00006455342,0.00005638882,0.0002723548,0.0002618621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02208812,0.00001585583,0.9760763,0.0004677481,0.0001101696,0.0003567356,0.000002890345,0.0008212299,0.00006094581],"genre_scores_gemma":[0.9902481,0.00001033981,0.009354164,0.00001602285,0.00002213525,0.00001932893,0.00001947367,0.0000237781,0.000286662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.96816,"threshold_uncertainty_score":0.9873052,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.01146694965448446,"gpt":0.2295948023311984,"spread":0.2181278526767139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001568303,0.0001616906,0.0003311794,0.0001222505,0.0002185193,0.00008629113,0.0005196423,0.00005931792,0.00001522007],"category_scores_gemma":[0.0001755516,0.0001343665,0.0001408559,0.0001489626,0.000146149,0.0003764224,0.00003036802,0.0003203056,0.000007416056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004454765,"about_ca_system_score_gemma":0.00008662419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002318598,"about_ca_topic_score_gemma":3.738521e-7,"domain_scores_codex":[0.9984888,0.0003395713,0.0004946895,0.0001956075,0.0002282714,0.0002530599],"domain_scores_gemma":[0.9978818,0.0008721536,0.0005119843,0.000203934,0.0003658444,0.0001642803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007190771,0.0002303964,0.0001374168,0.000009042871,0.0002435045,0.000009064615,0.0005484312,0.002715978,0.001108054,0.9314384,0.00005299844,0.06278762],"study_design_scores_gemma":[0.02129278,0.003657979,0.00169918,0.0001842276,0.0006964713,0.0002148926,0.0007039381,0.6269658,0.001037548,0.3203205,0.02224546,0.0009812412],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004508774,0.0008583937,0.9970558,0.0002900377,0.00003833829,0.0004277687,0.000001964728,0.00004421797,0.0008326611],"genre_scores_gemma":[0.9949584,0.00001130602,0.004069007,0.0006401126,0.00006920567,0.0001007241,5.595607e-7,0.00001089538,0.000139807],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9945075,"threshold_uncertainty_score":0.5479307,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.005472723485347404,"gpt":0.2031684351469034,"spread":0.197695711661556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002781152,0.0001785817,0.0003802846,0.00008610889,0.0001929222,0.00006345574,0.0009594376,0.00002639783,0.000009883095],"category_scores_gemma":[0.00009584519,0.0001468208,0.0000464944,0.0002254236,0.0002089096,0.0002741622,0.0006057485,0.0001466398,0.000004906896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007571077,"about_ca_system_score_gemma":0.0001051827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003004917,"about_ca_topic_score_gemma":0.000001344789,"domain_scores_codex":[0.9984453,0.0001720573,0.0002769168,0.000393401,0.0004322759,0.0002800731],"domain_scores_gemma":[0.9983096,0.0004817165,0.0002714187,0.0007285756,0.000117653,0.00009109327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006214969,0.0009697709,0.0006994579,0.0002146216,0.001669865,0.000137794,0.01742964,0.3613494,0.003883391,0.5592153,0.001675407,0.05213385],"study_design_scores_gemma":[0.001545397,0.0004696646,0.0003879746,0.00002411295,0.00003868133,0.00002999041,0.0002413564,0.9963269,0.00002824985,0.000640495,0.00008667986,0.0001804691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01791653,0.0001828049,0.9796624,0.0004390115,0.00002725383,0.0008306293,0.0002580978,0.0002513204,0.0004319955],"genre_scores_gemma":[0.9112527,0.000001036789,0.08808421,0.00005684419,0.000008509615,0.0004587302,0.000006124767,0.0000149729,0.0001169248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8933361,"threshold_uncertainty_score":0.5987177,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.01832090826255103,"gpt":0.2175829276640776,"spread":0.1992620194015266,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008846211,0.0004117252,0.0005969975,0.0004025029,0.0005605968,0.0005561509,0.0005513473,0.0002200571,0.000001351735],"category_scores_gemma":[0.0000129226,0.0003827545,0.0002105493,0.000546387,0.00005729768,0.0001660673,0.000004280595,0.0003860163,0.0001328903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001969747,"about_ca_system_score_gemma":0.00008961336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001815609,"about_ca_topic_score_gemma":0.00001897151,"domain_scores_codex":[0.9968767,0.0003918142,0.0005906236,0.0008332038,0.000596297,0.0007113831],"domain_scores_gemma":[0.9978834,0.0007524736,0.0002435572,0.000668311,0.0001992623,0.0002529882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009675753,0.0001994707,0.00005254466,0.0003489924,0.0002108513,0.00003507035,0.0007954368,0.9876642,0.0005352871,0.004512858,0.0002295894,0.005318921],"study_design_scores_gemma":[0.002934116,0.0007655582,0.00006457062,0.0003063817,0.00007259702,0.00002716303,0.0004351164,0.9876902,0.00006373115,0.000008536479,0.007218844,0.0004132386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007162731,0.0002263049,0.9862997,0.0003308682,0.002328163,0.002032671,0.00004591661,0.00123376,0.0003398965],"genre_scores_gemma":[0.9956115,0.00001752455,0.0006422498,0.0000955662,0.0001489339,0.0008501732,0.000004920993,0.00006723525,0.002561901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9884487,"threshold_uncertainty_score":0.9998624,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0121960861024255,"gpt":0.2383362696693834,"spread":0.2261401835669579,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004588389,0.0001892844,0.0001809565,0.000285427,0.0001804345,0.000110527,0.0003110017,0.0001491714,0.000004250354],"category_scores_gemma":[0.0000416848,0.0002070248,0.0001022636,0.0004041345,0.00003986378,0.0001733783,0.000002705304,0.0003778372,0.00001487952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001410071,"about_ca_system_score_gemma":0.00003978191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002977621,"about_ca_topic_score_gemma":0.0001210644,"domain_scores_codex":[0.998575,0.0001169003,0.0003192964,0.0003834724,0.0002681226,0.0003372],"domain_scores_gemma":[0.9989289,0.0004024737,0.0001295392,0.0003837344,0.00008021521,0.00007513063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007460607,0.00007952553,0.00001136166,0.00002223915,0.00001430939,3.346423e-7,0.0002103877,0.8795409,0.0001002978,0.02200549,0.000002848114,0.09793777],"study_design_scores_gemma":[0.001046869,0.000807424,0.0001072142,0.00007554243,0.00002150268,9.767749e-7,0.00001796893,0.9878755,0.0005674595,0.008573116,0.0006969709,0.0002094308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000622586,0.000006418154,0.997417,0.000315964,0.0006072083,0.0006190858,0.000001184935,0.0002373939,0.000173111],"genre_scores_gemma":[0.81176,0.000002022842,0.1875453,0.0003029879,0.00003115107,0.0002223935,0.000003587957,0.00001879427,0.0001137023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8111374,"threshold_uncertainty_score":0.8442227,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02109190720631195,"gpt":0.2453282354426242,"spread":0.2242363282363123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009336879,0.0002931749,0.0003632465,0.0002711778,0.001027585,0.0004016253,0.0002731266,0.0001390578,0.000001050828],"category_scores_gemma":[0.00001784508,0.000271971,0.0001596166,0.0005807638,0.00003898946,0.0005791038,0.000008362919,0.0006329655,0.00002020396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001238698,"about_ca_system_score_gemma":0.00001771469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001237492,"about_ca_topic_score_gemma":0.000008433679,"domain_scores_codex":[0.9975026,0.0004636483,0.0005695841,0.0005008487,0.0003462954,0.0006170249],"domain_scores_gemma":[0.9985371,0.0005492927,0.0003349319,0.0002630058,0.0001541887,0.0001614826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006249908,0.00001767149,0.00001290597,0.00005705099,0.00006679641,0.000006134986,0.0004492117,0.9569518,0.0001135995,0.0002660163,0.00005471684,0.04194158],"study_design_scores_gemma":[0.0008845145,0.0007368431,0.00002889943,0.0001475109,0.0000330821,0.00002289712,0.0004152777,0.9956423,0.00001754971,0.000004513561,0.001783222,0.0002833966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003760656,0.0003322013,0.9915389,0.0001042503,0.002033424,0.001437486,0.000002218136,0.0007762325,0.00001456325],"genre_scores_gemma":[0.9969115,0.00006418247,0.0002810108,0.00002871011,0.0001609016,0.0006853695,0.00001448947,0.00003453229,0.001819253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9931509,"threshold_uncertainty_score":0.9999732,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01076070531881443,"gpt":0.2283681326764064,"spread":0.217607427357592,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004312271,0.0004910839,0.0008248123,0.00005792909,0.0009654347,0.001493461,0.001979876,0.0001957031,0.000004016252],"category_scores_gemma":[0.0002311512,0.0003941291,0.0002081555,0.0001188445,0.0005774763,0.0007647434,0.0003700767,0.0004641788,0.00001884561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005201903,"about_ca_system_score_gemma":0.0001137551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007477547,"about_ca_topic_score_gemma":0.00001931863,"domain_scores_codex":[0.9971046,0.0001337377,0.000477908,0.0009171941,0.000377241,0.0009893627],"domain_scores_gemma":[0.9965848,0.0008063347,0.0006737105,0.001185544,0.0004783524,0.0002712918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00374033,0.0004066573,0.001748513,0.00004038331,0.000767753,0.0005702626,0.0002607205,0.6729456,0.0003162816,0.01732123,0.003308147,0.2985741],"study_design_scores_gemma":[0.005243727,0.001353563,0.0005617791,0.00004740639,0.000053085,0.0001002406,0.00001090282,0.9889861,0.000003751211,0.00002432667,0.003167183,0.0004478987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008118566,0.0001812608,0.986325,0.001495313,0.0008456204,0.002173085,0.00003756444,0.0004209831,0.0004026469],"genre_scores_gemma":[0.9490756,0.000002422082,0.04862387,0.000601134,0.0006933521,0.0002409536,0.00001583301,0.00005961264,0.0006872272],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.940957,"threshold_uncertainty_score":0.999851,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02230628527935432,"gpt":0.2466972457208165,"spread":0.2243909604414622,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000812477,0.0003573595,0.0007594259,0.0001556509,0.0001691299,0.0002615683,0.001187442,0.0001607233,0.00000110469],"category_scores_gemma":[0.0003960631,0.0003394231,0.0001239242,0.0002310402,0.0001416283,0.0007098541,0.0004809919,0.0004178047,0.000002460197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002952849,"about_ca_system_score_gemma":0.00004467211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004730096,"about_ca_topic_score_gemma":0.000009932401,"domain_scores_codex":[0.9974034,0.00007112353,0.0007636352,0.0005306156,0.0004296482,0.0008015621],"domain_scores_gemma":[0.9979028,0.0003290697,0.0005233526,0.0009584288,0.0001551398,0.0001311754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002136464,0.0003919469,0.00008151675,0.0004031224,0.00008501216,0.00003209391,0.0003852491,0.9489706,0.007023911,0.0351623,3.172522e-7,0.00744258],"study_design_scores_gemma":[0.001028499,0.0001660248,0.0001759546,0.001270099,0.00002785306,0.00003042719,0.00006003203,0.9949433,0.0001199485,0.00184086,0.000008171196,0.000328817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03632172,0.000187694,0.9617837,0.0000430547,0.0002222776,0.001184971,0.00000796023,0.0002021933,0.00004639632],"genre_scores_gemma":[0.7667185,0.000001490688,0.2331315,0.000003264353,0.00003993397,0.00005915858,0.000002079403,0.00003823779,0.000005803321],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7303968,"threshold_uncertainty_score":0.9999058,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.055405230323866,"gpt":0.2691388320562517,"spread":0.2137336017323857,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006367714,0.0003207487,0.000470341,0.0004412676,0.0001791657,0.0001919344,0.002546987,0.0001548824,4.559549e-7],"category_scores_gemma":[0.0003075643,0.0003454876,0.0001081056,0.001180338,0.0001329686,0.0008681583,0.000991612,0.0003309435,0.00001506815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001581942,"about_ca_system_score_gemma":0.0001438876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007756044,"about_ca_topic_score_gemma":0.00000545522,"domain_scores_codex":[0.9969223,0.0001855392,0.0004838831,0.001172061,0.0004565183,0.0007797382],"domain_scores_gemma":[0.997657,0.0002033087,0.0002225979,0.001645264,0.0001380061,0.0001338486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007938318,0.0001217399,0.0008150171,0.00002795989,0.00006470515,0.00002929468,0.0005173351,0.9313877,0.00003849985,0.006703526,0.02613494,0.03407989],"study_design_scores_gemma":[0.001180783,0.000165973,0.003622786,0.00002082647,0.00002970346,0.000006815584,0.0001307668,0.9911435,0.000004199967,0.00169213,0.001668616,0.0003338865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00026282,0.00009358475,0.9948314,0.0009510102,0.001879282,0.001222963,0.00004919066,0.0005658785,0.0001438961],"genre_scores_gemma":[0.1161676,0.0000195718,0.8821953,0.0001487457,0.0001413925,0.0001163254,0.0002285274,0.00005277634,0.0009297834],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1159047,"threshold_uncertainty_score":0.9998997,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00934140909909165,"gpt":0.2502950338054101,"spread":0.2409536247063184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001134537,0.0001540126,0.0002707421,0.00005702247,0.0002586309,0.00006635275,0.0008657099,0.00005209126,0.000007599848],"category_scores_gemma":[0.000127087,0.0001149297,0.0001175768,0.0001485741,0.000110688,0.000195871,0.0001110354,0.0001539011,0.000007016674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002426382,"about_ca_system_score_gemma":0.00006584277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004964292,"about_ca_topic_score_gemma":0.000001327013,"domain_scores_codex":[0.9988028,0.000106649,0.0003404632,0.0003070212,0.0001659003,0.0002771965],"domain_scores_gemma":[0.9966432,0.002103607,0.0002368386,0.0008151141,0.0001415067,0.0000596632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005315749,0.00005509213,0.0000616807,0.0000224848,0.0001200247,7.582766e-8,0.0002224333,0.1366059,0.001191215,0.808854,0.000009094768,0.0528049],"study_design_scores_gemma":[0.002635878,0.0001140556,0.0001883701,0.00001800776,0.00008078009,0.000002153583,0.0001099768,0.9267985,0.00002740731,0.06852565,0.001380156,0.0001190555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001316221,0.0004703699,0.9941258,0.001174726,0.00004009063,0.002459451,0.00002018822,0.0001669651,0.0002261233],"genre_scores_gemma":[0.9894792,0.000006880064,0.007694304,0.0005471357,0.00005006274,0.001301,0.000005727876,0.00001343677,0.0009022546],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.988163,"threshold_uncertainty_score":0.4686698,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04272873070935691,"gpt":0.2788022614981229,"spread":0.236073530788766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005846396,0.0002904069,0.0003694322,0.0001652043,0.0004948436,0.0002028367,0.001460767,0.000125937,0.000001445898],"category_scores_gemma":[0.0003032313,0.0002901478,0.0001632269,0.0003157354,0.0001790725,0.0005750712,0.0002477738,0.0002446013,0.00002435843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001501153,"about_ca_system_score_gemma":0.0001835641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000183738,"about_ca_topic_score_gemma":0.00005073391,"domain_scores_codex":[0.9977605,0.0001197786,0.0003327226,0.000675633,0.0003461055,0.0007652442],"domain_scores_gemma":[0.997964,0.0002732767,0.0001940294,0.0008416136,0.0005085688,0.0002185575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001362908,0.000111357,0.0001071752,0.000007921158,0.00005364542,0.000002699462,0.000403503,0.8428468,0.0004703416,0.1416721,0.0001932371,0.01399496],"study_design_scores_gemma":[0.002851745,0.001471162,0.0000491076,0.00002861095,0.00003843878,0.000002298249,0.0000476573,0.9785676,0.0002264203,0.01596048,0.0004088283,0.0003476836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007051557,0.00004176247,0.9964438,0.0008071029,0.0003173775,0.0006796616,0.000006472188,0.0006538521,0.0003448325],"genre_scores_gemma":[0.5471864,3.085244e-7,0.451866,0.0003568881,0.000140664,0.00004157597,0.000005653998,0.00002853323,0.0003740086],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5464813,"threshold_uncertainty_score":0.9999551,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01861807992229806,"gpt":0.2851494187181415,"spread":0.2665313387958434,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007938656,0.0001733603,0.0003195744,0.0002384487,0.0002826632,0.00119688,0.002704629,0.00006314085,0.00000212375],"category_scores_gemma":[0.0003473727,0.0001456131,0.0002367818,0.00002946741,0.00006879555,0.0008060453,0.0003242718,0.0002469877,0.000007312574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002428324,"about_ca_system_score_gemma":0.0001297287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007767003,"about_ca_topic_score_gemma":0.00000418198,"domain_scores_codex":[0.997686,0.00008414678,0.0007125905,0.0002329709,0.0009955635,0.000288689],"domain_scores_gemma":[0.9965863,0.0001558743,0.001609883,0.0003654852,0.001149534,0.0001329753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002828223,0.000268897,0.002138134,0.00004586506,0.002197987,0.0004676587,0.00180165,0.009310816,0.001473935,0.1631846,0.003132235,0.8156954],"study_design_scores_gemma":[0.005935461,0.001249646,0.004563272,0.0005645682,0.00007453244,0.0008342367,0.0002731917,0.9499681,0.0002590768,0.004243817,0.03154238,0.0004917098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005271317,0.0002130235,0.984767,0.001102725,0.007536478,0.0002816671,0.000007576497,0.00003380097,0.0007863859],"genre_scores_gemma":[0.9806486,0.00002065453,0.01636706,0.00003118543,0.001790008,0.00002768865,0.000004806814,0.0000139255,0.001096035],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9753773,"threshold_uncertainty_score":0.99984,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01483512746151684,"gpt":0.2457696793008887,"spread":0.2309345518393719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001274824,0.0001683561,0.0004415975,0.0001698444,0.0001848201,0.000325835,0.0005290094,0.00008947674,0.000004865256],"category_scores_gemma":[0.0002639256,0.0001535429,0.0002090048,0.0003498181,0.00002704967,0.000786253,0.00009505692,0.000385935,0.00001317597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000323551,"about_ca_system_score_gemma":0.0001908938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003229963,"about_ca_topic_score_gemma":0.000002698904,"domain_scores_codex":[0.9974141,0.0004651552,0.0008601488,0.0002284594,0.0006637613,0.0003683381],"domain_scores_gemma":[0.9974234,0.0001489846,0.001017704,0.000319923,0.0009169798,0.000173036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007853097,0.0001169016,0.003489396,0.00007806715,0.0003346615,0.0006225512,0.0007028345,0.9327328,0.03454915,0.0111728,0.00003713243,0.01608523],"study_design_scores_gemma":[0.001890575,0.0002718435,0.0004375235,0.000157025,0.00003705009,0.0005918456,0.000315366,0.994637,0.0004021972,0.00009096546,0.001011037,0.0001576009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03996191,0.001013384,0.9572172,0.0002954854,0.001126051,0.000228419,2.470053e-7,0.0000491156,0.0001081496],"genre_scores_gemma":[0.9941618,0.000007529377,0.005149916,0.00007703849,0.0003706875,0.000005375927,6.361768e-7,0.00001583048,0.0002112171],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9541999,"threshold_uncertainty_score":0.6261297,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0888835926429212,"gpt":0.3256896554819136,"spread":0.2368060628389924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001885558,0.000280401,0.0004180069,0.0001076776,0.0001805709,0.0002012646,0.001080574,0.0000628207,0.00007196194],"category_scores_gemma":[0.0008410765,0.0002610228,0.0002074195,0.0005713238,0.00007722726,0.0004870576,0.000336941,0.000321671,0.000792449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000204653,"about_ca_system_score_gemma":0.000222072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001022243,"about_ca_topic_score_gemma":0.000009547462,"domain_scores_codex":[0.9970272,0.000306409,0.0008104813,0.0006017138,0.0006847344,0.0005694792],"domain_scores_gemma":[0.9982266,0.0001498012,0.0002964796,0.00069485,0.0003147048,0.000317559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006657117,0.00006758144,0.00001104973,0.0001274136,0.0000197314,0.00004491833,0.0002503665,0.02860586,0.0001148116,0.01913219,0.00008666343,0.9515328],"study_design_scores_gemma":[0.00005453851,0.0001674712,0.000002925498,0.0007124033,0.00002405546,0.00000800097,0.00004233008,0.9756024,0.001770957,0.001291164,0.02000455,0.0003192128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00006333844,0.01015159,0.9866174,0.001172487,0.0005628252,0.000730596,4.482994e-7,0.0002902358,0.0004110359],"genre_scores_gemma":[0.8897086,0.002787557,0.1045224,0.002154686,0.0002536546,0.0002291533,0.00001972073,0.00003860888,0.000285653],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9512135,"threshold_uncertainty_score":0.9999856,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03350929300342959,"gpt":0.2669293575365366,"spread":0.233420064533107,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005469957,0.0001729292,0.0001476504,0.0001107782,0.0009690858,0.0005005496,0.0009796222,0.00006254482,0.00001048671],"category_scores_gemma":[0.0003110458,0.0001510371,0.00009523543,0.00008579067,0.00005582266,0.0004828775,0.0002220032,0.0002266947,0.0000845626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001315327,"about_ca_system_score_gemma":0.00007333457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005583973,"about_ca_topic_score_gemma":0.000001513189,"domain_scores_codex":[0.9985195,0.00008049042,0.0002293225,0.0004820458,0.0003747108,0.0003138939],"domain_scores_gemma":[0.998246,0.00004522785,0.000243652,0.001233906,0.0001292595,0.0001019674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003427613,0.0003224541,0.0001893313,0.0000184469,0.00005141721,0.000003169311,0.0003116681,0.7554111,0.001729594,0.158367,0.0001791154,0.08338247],"study_design_scores_gemma":[0.000947081,0.0001865661,0.002667042,0.00001211417,0.00001070951,9.563381e-7,0.00003365351,0.9947104,0.0001384928,0.00009870841,0.00101491,0.0001793465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004794846,0.000003773309,0.9793389,0.0007368524,0.0002895971,0.0004961696,2.107193e-7,0.0003599287,0.01829507],"genre_scores_gemma":[0.6938025,3.278089e-7,0.3030628,0.0002696084,0.0000327467,0.0001008987,0.000008373823,0.000008812286,0.002713921],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6933231,"threshold_uncertainty_score":0.7453523,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006489728805762793,"gpt":0.2164662553620484,"spread":0.2099765265562856,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001052196,0.0004356242,0.0008165016,0.0002200474,0.0001996797,0.0003070701,0.0009009858,0.000160967,9.410525e-7],"category_scores_gemma":[0.00005026648,0.0004529179,0.0001394444,0.0005291578,0.0001831807,0.0002712612,0.0003760613,0.0004350982,0.00001279213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008438754,"about_ca_system_score_gemma":0.0001271073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003035576,"about_ca_topic_score_gemma":0.00000144677,"domain_scores_codex":[0.9966663,0.00008400283,0.0008840149,0.0009963169,0.0005360033,0.0008333243],"domain_scores_gemma":[0.9974406,0.0007274275,0.0007338211,0.0006825059,0.0002384684,0.0001772281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004253887,0.0002743241,0.001928626,0.0002977636,0.0002817414,0.00002208222,0.001004496,0.007338793,0.06507227,0.06660792,0.000003479935,0.8571259],"study_design_scores_gemma":[0.003264434,0.0001488174,0.0005659653,0.0001300038,0.00002924086,0.00008014249,0.0001449943,0.994817,0.0000710251,0.0001722525,0.0001473261,0.0004287849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08557717,0.0002716788,0.9115156,0.00008377778,0.0003725534,0.001616797,0.000005713373,0.0004547825,0.0001019525],"genre_scores_gemma":[0.7736704,9.858244e-7,0.2260664,0.000118112,0.00006504371,0.00002667497,0.000004882158,0.00003632232,0.00001113879],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9874782,"threshold_uncertainty_score":0.9997923,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01630035951098792,"gpt":0.2153603773335627,"spread":0.1990600178225748,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000272697,0.0003386902,0.000421964,0.00003360416,0.0004713762,0.000399678,0.0009905396,0.00006670385,0.00000232814],"category_scores_gemma":[0.00006997266,0.0003102319,0.000106325,0.0006756097,0.0001226434,0.0004470144,0.0003488458,0.0005336301,0.00003839055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004566935,"about_ca_system_score_gemma":0.00009143545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000218962,"about_ca_topic_score_gemma":0.000004833363,"domain_scores_codex":[0.99726,0.000305743,0.0003691992,0.0008840076,0.0004634759,0.0007176294],"domain_scores_gemma":[0.9983938,0.0004054135,0.0003223288,0.0004147435,0.0001868374,0.0002768835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001502097,0.0000411059,0.003934095,0.000009578539,0.00004977324,0.0001371366,0.0006999903,0.9303216,0.0004534702,0.005640693,0.0001160151,0.05844636],"study_design_scores_gemma":[0.001496714,0.0007087033,0.01259221,0.00001917885,0.00001750936,0.00004049053,0.00001721594,0.9841832,0.00002241416,0.0001078048,0.00048237,0.0003121748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05611816,0.00003803039,0.9387875,0.003314025,0.0001827595,0.0006490861,0.000001745761,0.0007663681,0.0001423135],"genre_scores_gemma":[0.8308002,2.459757e-7,0.1652251,0.003598152,0.0003263548,0.00001403604,0.000002472475,0.00002871682,0.000004809199],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.774682,"threshold_uncertainty_score":0.999935,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01066522790033608,"gpt":0.2329612270568643,"spread":0.2222959991565282,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008267053,0.0001562504,0.0003824785,0.0001073836,0.0001817323,0.00006734415,0.000796493,0.00003330499,0.00001122056],"category_scores_gemma":[0.00006005398,0.0001601715,0.0001494406,0.0001233477,0.00004460838,0.00007930143,0.000153453,0.0001623831,0.000007348902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001786866,"about_ca_system_score_gemma":0.0001400996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009782207,"about_ca_topic_score_gemma":3.868983e-7,"domain_scores_codex":[0.9985685,0.00006722444,0.0005228881,0.0002506349,0.0002806667,0.0003101396],"domain_scores_gemma":[0.9985179,0.0003869211,0.0004749513,0.000448526,0.0001138593,0.00005781428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001475366,0.0001609631,0.000008910304,0.0001227065,0.00008803892,0.000004160272,0.0004279446,0.9727382,0.0001172292,0.01948236,0.00009314422,0.006741568],"study_design_scores_gemma":[0.001835389,0.0005677395,9.997776e-7,0.00001502832,0.00002679168,0.00001016847,0.0002182174,0.9909456,0.00008561191,0.0001768962,0.005962647,0.0001548515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001153137,0.00005591355,0.9970668,0.0001467772,0.0002328416,0.001083006,0.00003624289,0.0001199285,0.0001053286],"genre_scores_gemma":[0.5071912,4.0938e-7,0.4914794,0.00008534931,0.00004001688,0.0006190186,0.00001582508,0.00002486808,0.0005439176],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.506038,"threshold_uncertainty_score":0.6531605,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02545684966083887,"gpt":0.2856880739314969,"spread":0.260231224270658,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004730342,0.0002985856,0.0003833277,0.00008346829,0.001371243,0.0008673478,0.00192884,0.00009193087,0.000001477134],"category_scores_gemma":[0.0007342118,0.000295581,0.0001774014,0.00008716803,0.0001761948,0.0004575353,0.0003351473,0.0002849682,0.00001418047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005902752,"about_ca_system_score_gemma":0.0001760941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001665786,"about_ca_topic_score_gemma":0.000008226716,"domain_scores_codex":[0.9978766,0.0001173998,0.000340357,0.0007473385,0.0002495956,0.0006686386],"domain_scores_gemma":[0.9971902,0.0007781309,0.0003381984,0.001032861,0.0005213579,0.0001392978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006921131,0.001138868,0.009005235,0.0001864231,0.0005501998,0.0004088597,0.001727547,0.01118981,0.04564162,0.292739,0.002853413,0.6338669],"study_design_scores_gemma":[0.003591154,0.0003740347,0.00178441,0.00004165931,0.00001752271,0.000009899396,0.00001492245,0.9902387,0.0009988957,0.0005929241,0.002022453,0.0003134473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004942614,0.00004015521,0.9907284,0.001915846,0.0005720538,0.001015061,0.00001823399,0.0003092341,0.0004584363],"genre_scores_gemma":[0.7727164,3.177974e-7,0.2255049,0.001401654,0.0002293098,0.00006595747,0.000002461167,0.00002508646,0.00005390097],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9790488,"threshold_uncertainty_score":0.9999496,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Applied mathematics; Mathematical optimization; Ode; Algebraic equation; Nonlinear system","retraction":null,"screen_n_in":null,"score":{"opus":0.05972795425387742,"gpt":0.3052582785002979,"spread":0.2455303242464205,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006194478,0.0002231587,0.0002660087,0.0003637841,0.0001760531,0.0003199774,0.001190708,0.0000838056,9.35943e-7],"category_scores_gemma":[0.0005168523,0.000203889,0.00009576339,0.001031627,0.00004178042,0.0003544368,0.0001438919,0.00008882127,0.00009076203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078787,"about_ca_system_score_gemma":0.0004984707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000165452,"about_ca_topic_score_gemma":0.000004120888,"domain_scores_codex":[0.9981195,0.0001227108,0.000364465,0.0004974708,0.0003436945,0.0005521074],"domain_scores_gemma":[0.9982635,0.0003493376,0.0001048439,0.0009929914,0.0001141892,0.0001751184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001795058,0.0001262976,0.000003887206,0.00009324124,0.00003304918,0.000003381654,0.001239624,0.6233657,0.0005265095,0.3260988,0.002199713,0.04629183],"study_design_scores_gemma":[0.0005920592,0.0002293502,0.0001202691,0.00002802941,0.0000114493,0.000001292172,0.00002521501,0.963003,0.0001413593,0.03553011,0.00009367298,0.0002242098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006386821,0.000009782568,0.9914834,0.004599622,0.00005343964,0.001428271,0.00001242307,0.001207643,0.0005666795],"genre_scores_gemma":[0.4228051,3.263832e-7,0.5758429,0.0004532365,0.0000598697,0.0005386469,0.00001611509,0.00002028431,0.000263567],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4221664,"threshold_uncertainty_score":0.8314353,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00823570730478461,"gpt":0.2573743442197518,"spread":0.2491386369149672,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00132214,0.0005053798,0.0009772639,0.000428061,0.0002373683,0.0002274613,0.001501844,0.0001849867,0.000004863933],"category_scores_gemma":[0.0005233402,0.0004963612,0.0003802797,0.001241777,0.00007978015,0.0002143222,0.0002286525,0.0004722947,0.00006826468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001269302,"about_ca_system_score_gemma":0.0002264005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000235041,"about_ca_topic_score_gemma":0.0000103068,"domain_scores_codex":[0.9950246,0.0007434121,0.001158258,0.001050464,0.0007577501,0.001265511],"domain_scores_gemma":[0.9959643,0.001706298,0.0006943166,0.0009784693,0.0003807521,0.0002757922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005533914,0.0006199031,0.001448891,0.0001610853,0.0002018888,0.0002346761,0.0005228842,0.9585316,0.02483466,0.002150636,0.00008380465,0.01065656],"study_design_scores_gemma":[0.009875977,0.0004440702,0.001493319,0.0002148532,0.00005293639,0.000009668759,0.00004188635,0.986634,0.0003089736,0.000017033,0.0005119006,0.0003953543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1697711,0.00004690919,0.826129,0.0006692601,0.0009087303,0.001321151,0.00004947214,0.001088659,0.00001573592],"genre_scores_gemma":[0.9862796,0.000001727877,0.01279444,0.0006306358,0.0000870903,0.00007833625,0.00003109161,0.00006721853,0.00002982327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8165085,"threshold_uncertainty_score":0.9997488,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0133189828181627,"gpt":0.2383035412986893,"spread":0.2249845584805266,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001150342,0.000295439,0.0005794736,0.0003181725,0.0001777284,0.0002003377,0.0007878077,0.0001063084,0.000003742203],"category_scores_gemma":[0.0002141889,0.0002297867,0.0002002484,0.0002544516,0.0001038162,0.0005532854,0.0001060385,0.0003210733,0.00002145557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000106091,"about_ca_system_score_gemma":0.0001968251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000149213,"about_ca_topic_score_gemma":0.000005040607,"domain_scores_codex":[0.9975131,0.000124651,0.0007098418,0.0003643382,0.0008045969,0.0004834567],"domain_scores_gemma":[0.9956111,0.001454954,0.0007340767,0.0001949733,0.001784812,0.0002200747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00269112,0.0001267832,0.0002917025,0.000009989318,0.001446616,0.0002834315,0.0001173502,0.9768187,0.0005681687,0.001838356,0.0003043847,0.01550342],"study_design_scores_gemma":[0.009785897,0.0007925665,0.0001690497,0.000147157,0.0001155849,0.0004795424,0.00002503189,0.9873573,0.000004388033,0.0001893933,0.0006855104,0.000248586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003425966,0.0004363356,0.9924809,0.001529561,0.001254102,0.0006582121,0.0001102853,0.00009232881,0.00001235944],"genre_scores_gemma":[0.8259293,0.000008822569,0.1712851,0.0003866269,0.002167704,0.0000490027,0.00002360526,0.00004211048,0.0001077833],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8225033,"threshold_uncertainty_score":0.937043,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04563645080383398,"gpt":0.2600250896028202,"spread":0.2143886387989862,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000431987,0.0001703282,0.000199937,0.0002484354,0.0002113899,0.00005133008,0.000287324,0.00006483217,0.000003567462],"category_scores_gemma":[0.00001169056,0.0001702443,0.0001073816,0.0002489953,0.00004216089,0.000383547,0.00000332325,0.00008385873,0.000005307628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001696317,"about_ca_system_score_gemma":0.0001086862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003221558,"about_ca_topic_score_gemma":0.0001122195,"domain_scores_codex":[0.9984249,0.00004508261,0.0003558166,0.0003392358,0.0005794936,0.000255441],"domain_scores_gemma":[0.9991605,0.0000648965,0.0001517294,0.0003433571,0.0001863626,0.00009314045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002881031,0.0002437262,0.0001244944,0.00009529099,0.0003035703,9.85014e-7,0.001668941,0.8066805,0.01323601,0.01703478,0.0001700772,0.1601535],"study_design_scores_gemma":[0.004337845,0.0002612607,0.000461987,0.00003285886,0.00006545305,0.000001090376,0.00007587181,0.9880664,0.002872451,0.003585736,0.00007489921,0.0001641153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006198941,0.00001050699,0.9909759,0.001122713,0.000366548,0.001065606,0.0000368312,0.000186981,0.00003595212],"genre_scores_gemma":[0.9620034,0.00001883758,0.0372835,0.0001537889,0.00001282305,0.0004234051,0.000006055464,0.00001494919,0.00008328947],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9558044,"threshold_uncertainty_score":0.6942361,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0149069629908675,"gpt":0.249528875899656,"spread":0.2346219129087885,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002674721,0.0002032193,0.0002288214,0.00009592845,0.0001321035,0.00005273325,0.000408937,0.00006635468,0.000004471126],"category_scores_gemma":[0.0000154542,0.0001876366,0.0001008962,0.0002443446,0.00005771666,0.001215246,0.00004074323,0.0001957669,0.00006123575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007109426,"about_ca_system_score_gemma":0.00003422112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001644951,"about_ca_topic_score_gemma":0.000002397772,"domain_scores_codex":[0.998443,0.0001300251,0.0002623821,0.0003224844,0.0003479831,0.0004941119],"domain_scores_gemma":[0.9992124,0.0001178953,0.0001422503,0.0002213423,0.0001314199,0.0001747373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004487862,0.0007086013,0.09208392,0.00003039823,0.0002822217,0.00006782627,0.00508361,0.1080588,0.002142084,0.1114346,0.000432252,0.6792269],"study_design_scores_gemma":[0.001138331,0.0001703721,0.04832997,0.000005944351,0.00002247958,0.00003219089,0.00001486617,0.9493071,0.00006466937,0.0003498503,0.0003453405,0.0002189045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07424928,0.0001332666,0.9234692,0.0004215992,0.0006071218,0.0003646841,0.000003486871,0.0003739819,0.0003773922],"genre_scores_gemma":[0.9273462,6.698399e-7,0.07195076,0.0003940019,0.0002032338,0.00003107529,0.000008875194,0.00001552586,0.00004967725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8530969,"threshold_uncertainty_score":0.7651598,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01919894647478068,"gpt":0.2903157640076766,"spread":0.271116817532896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003250318,0.0001383437,0.0002087466,0.0003112329,0.00009374969,0.000237989,0.001015909,0.00004903297,0.000002211098],"category_scores_gemma":[0.0001158784,0.0001240588,0.0001492307,0.000148363,0.00003333373,0.0002606421,0.0001438932,0.000193846,0.000003204082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001612921,"about_ca_system_score_gemma":0.0002262247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007765744,"about_ca_topic_score_gemma":0.000001034701,"domain_scores_codex":[0.9986357,0.00001973206,0.0005600057,0.0002117298,0.0003958229,0.0001770227],"domain_scores_gemma":[0.9980859,0.0001899434,0.0004407985,0.0002231639,0.000964172,0.00009606594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002443526,0.0001240376,0.00008199849,0.000007024999,0.00007997253,2.779127e-7,0.00008149845,0.7159318,0.0002963395,0.2685083,0.00002561143,0.01483868],"study_design_scores_gemma":[0.00106648,0.0001301304,0.00002465271,0.0000340375,0.00001751978,0.00001422195,0.00003841468,0.9831626,0.0001511128,0.01140806,0.003836015,0.0001167266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002499517,0.00009878005,0.9948555,0.003877183,0.0001029072,0.000541639,0.000008442974,0.00003319392,0.000232369],"genre_scores_gemma":[0.6702481,0.00003120262,0.3282704,0.0005647567,0.0002546243,0.00005439355,0.00002639665,0.00001149649,0.0005386446],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6699981,"threshold_uncertainty_score":0.5058971,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03709314385473735,"gpt":0.2992942097126282,"spread":0.2622010658578908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001227671,0.001156751,0.0009923468,0.0007525877,0.0003626016,0.0008672376,0.004663384,0.0004538889,0.000253844],"category_scores_gemma":[0.0001271839,0.001033114,0.0003797055,0.0007291252,0.0005143328,0.001707693,0.0002746081,0.0022608,0.00002936717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004505501,"about_ca_system_score_gemma":0.0001968994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001775888,"about_ca_topic_score_gemma":0.0002165989,"domain_scores_codex":[0.9919214,0.0004348122,0.001740842,0.001848483,0.002556886,0.001497551],"domain_scores_gemma":[0.9934531,0.0007391166,0.001624373,0.001087731,0.00246094,0.000634776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002161627,0.000379807,0.0006843339,0.000007279792,0.0004275815,0.0003557505,0.0001465454,0.8180789,0.0007601393,0.07572316,0.0001116401,0.1011632],"study_design_scores_gemma":[0.003691208,0.002778133,0.0008437037,0.0003288839,0.00004699026,0.0001453911,0.0001135807,0.9897355,0.0004163169,0.0006624128,0.0002155885,0.00102228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04585321,0.00003830146,0.9374736,0.00288023,0.006622402,0.001064992,0.00002811711,0.0005631041,0.005476073],"genre_scores_gemma":[0.9929736,0.0001038951,0.002174152,0.001962417,0.001440199,0.0001234353,0.0002013204,0.00009669091,0.0009243154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9471204,"threshold_uncertainty_score":0.9992119,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01823689569409537,"gpt":0.2903885017887164,"spread":0.2721516060946211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004021776,0.0001043542,0.0001976746,0.0001908316,0.000248551,0.002482251,0.0006101739,0.0000446141,2.559403e-7],"category_scores_gemma":[0.0003341471,0.00008498373,0.00008897758,0.00003399075,0.0001039265,0.00155745,0.0001688234,0.00007375248,6.897074e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005474983,"about_ca_system_score_gemma":0.00009210728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002971185,"about_ca_topic_score_gemma":0.000007547198,"domain_scores_codex":[0.9989647,0.00002123799,0.000382637,0.0001534621,0.0003110657,0.0001668731],"domain_scores_gemma":[0.9984515,0.0001727553,0.0005364639,0.0001470342,0.0005924737,0.0000997377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001621559,0.0002140605,0.0131063,0.00005046123,0.0008325165,0.00006731033,0.0005300673,0.0003523514,0.003009358,0.8616264,0.0002684103,0.1197806],"study_design_scores_gemma":[0.002111187,0.000460359,0.02076397,0.0002207228,0.00002521619,0.0007861616,0.00008982579,0.9271121,0.00001126056,0.04565728,0.002504897,0.0002569959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04954088,0.0005404291,0.9428067,0.006011793,0.0007296972,0.0001879207,0.00003583016,0.000014286,0.0001324839],"genre_scores_gemma":[0.9985179,0.0000498263,0.001014949,0.00004342644,0.0002411812,0.00001076899,0.000004006234,0.000005935352,0.0001120508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.948977,"threshold_uncertainty_score":0.9985533,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01264870930753397,"gpt":0.2320998974094287,"spread":0.2194511881018948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003169799,0.0001926884,0.0002307496,0.0002495615,0.0001276242,0.0000729754,0.0007375943,0.00005453442,0.000005346987],"category_scores_gemma":[0.00005829724,0.0001930524,0.00006543093,0.001097608,0.00007213568,0.0002171314,0.0001242289,0.0002353231,0.0001113178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007771865,"about_ca_system_score_gemma":0.00007752854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003216066,"about_ca_topic_score_gemma":0.000002446473,"domain_scores_codex":[0.9985476,0.00001465969,0.0003945318,0.0003962464,0.0002775592,0.0003694291],"domain_scores_gemma":[0.9987747,0.0002609182,0.0001616987,0.0005193586,0.0001895531,0.00009374019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000158266,0.00002493343,0.00002006824,0.000008145056,0.0000383164,0.000003880754,0.0002793236,0.8790365,0.001455331,0.06934465,0.00000442723,0.04976864],"study_design_scores_gemma":[0.00006110868,0.0002197598,0.00009783673,0.00002528108,0.00001134634,0.000003613289,0.00008983034,0.9930444,0.005284373,0.0004032497,0.0005569611,0.0002021835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003849939,0.00002147666,0.9946219,0.0001259692,0.00005119848,0.0006468865,0.000003371416,0.0005195418,0.0001596743],"genre_scores_gemma":[0.9429949,0.000007042398,0.05631499,0.00001305559,0.00003866504,0.0005028036,0.000007901503,0.00001948105,0.0001011559],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.939145,"threshold_uncertainty_score":0.787245,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Control theory (sociology); Artificial intelligence; Control engineering; Control (management); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.006506808054315666,"gpt":0.2226989623850349,"spread":0.2161921543307192,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001897676,0.0001146586,0.0001842943,0.0001658584,0.0001790545,0.00005630129,0.0002481442,0.00005422961,0.000003047489],"category_scores_gemma":[0.00001622982,0.000100063,0.00006413617,0.0004331142,0.00005060565,0.0002450071,0.000003269261,0.000194809,0.000004296393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007628494,"about_ca_system_score_gemma":0.0001780619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001142928,"about_ca_topic_score_gemma":0.00003191875,"domain_scores_codex":[0.9990537,0.0000855909,0.0002580001,0.0002151895,0.0002113051,0.0001762629],"domain_scores_gemma":[0.9992061,0.0001556885,0.0001121771,0.0002957337,0.0001911542,0.00003915614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000536163,0.00004554635,0.0001068915,0.00003980762,0.00009655675,0.000002001191,0.0001786316,0.9745917,0.001067315,0.01463593,0.000005764613,0.009176221],"study_design_scores_gemma":[0.001360406,0.0001828336,0.0002142726,0.00008559974,0.00004966482,0.000002154067,0.00005508293,0.9957982,0.0004874462,0.0000381329,0.001628875,0.0000973375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002673359,0.00007240441,0.9969329,0.0006409084,0.0002254486,0.0004218337,0.000002263975,0.0001698804,0.001267036],"genre_scores_gemma":[0.990175,0.000001971002,0.008905487,0.00009209676,0.00001341347,0.00008072543,0.000003592509,0.000005834799,0.0007218897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9899077,"threshold_uncertainty_score":0.408045,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01738113249222614,"gpt":0.2899690171600185,"spread":0.2725878846677924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007851662,0.0002641902,0.0003410704,0.0001489612,0.0002036009,0.0007553005,0.0006779648,0.0001236669,0.00003432445],"category_scores_gemma":[0.00035527,0.0002498341,0.000198789,0.0002897215,0.00004985316,0.0007112919,0.000217511,0.0003710538,0.00004482116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002232415,"about_ca_system_score_gemma":0.0001214938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001994062,"about_ca_topic_score_gemma":0.000001265988,"domain_scores_codex":[0.9977325,0.00008123798,0.0004588138,0.0005914769,0.000419331,0.0007167084],"domain_scores_gemma":[0.9982968,0.0007620331,0.0001143353,0.000597173,0.0000901629,0.0001395186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002147523,0.0001034563,0.0001331205,0.0002726217,0.0003567144,0.00008870938,0.002908494,0.06795014,0.003427955,0.8457384,0.0001925341,0.07880634],"study_design_scores_gemma":[0.0004993014,0.0002078615,0.000116637,0.0002027755,0.0001005665,0.000008008171,0.00005684089,0.9829187,0.00009458934,0.009220579,0.006282474,0.0002916743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004116178,0.0004718861,0.9913583,0.0006349716,0.0004457641,0.001180531,0.000003381238,0.001589906,0.0001990115],"genre_scores_gemma":[0.6090257,0.000003565403,0.3900344,0.0002025531,0.00005157268,0.0004719739,0.000004677914,0.0000317072,0.000173906],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9149686,"threshold_uncertainty_score":0.9999954,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Adaptive control; Control (management); Reinforcement; Artificial intelligence; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02325165548238078,"gpt":0.2321184257896034,"spread":0.2088667703072226,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000612983,0.0002546371,0.0003243318,0.0001359411,0.0001219506,0.0001620355,0.00147472,0.0000889181,0.00001685804],"category_scores_gemma":[0.00007606505,0.0002157877,0.0001400373,0.000253559,0.00005346028,0.0007300015,0.00056512,0.0003914765,0.000068735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002172557,"about_ca_system_score_gemma":0.0001350332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009600831,"about_ca_topic_score_gemma":0.000003224837,"domain_scores_codex":[0.9979759,0.0001206891,0.0003098425,0.0005789577,0.0004531024,0.0005615427],"domain_scores_gemma":[0.9985558,0.0001016832,0.0001609923,0.0008985621,0.0001612198,0.0001217413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002824684,0.00002577237,0.000245617,0.000004194841,0.00005044473,0.000001837856,0.0002550575,0.6946893,0.0004838618,0.2974132,0.00002556338,0.006776927],"study_design_scores_gemma":[0.001681494,0.0001836106,0.00002819925,0.00001251599,0.00001347954,0.000009463589,0.0001375514,0.995307,0.00002826526,0.002212422,0.0001061606,0.0002798433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002614184,0.00003151079,0.9728317,0.0001091437,0.0001339505,0.0006374713,6.370778e-7,0.0003686634,0.02327275],"genre_scores_gemma":[0.6909654,4.516478e-7,0.3063436,0.0002437929,0.00002241855,0.00001920923,0.000001622788,0.00001356985,0.002389878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6883512,"threshold_uncertainty_score":0.8799568,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01035213134174163,"gpt":0.2418424198324642,"spread":0.2314902884907226,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000292748,0.0003345424,0.0003881252,0.0002245822,0.0001881064,0.0003329169,0.0006342906,0.0001011487,0.00007343341],"category_scores_gemma":[0.00000912339,0.0002624348,0.0001910197,0.0006071867,0.00009628732,0.0005065103,0.000005480728,0.0003304491,0.000205266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001916352,"about_ca_system_score_gemma":0.0001863327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002208671,"about_ca_topic_score_gemma":0.00001261417,"domain_scores_codex":[0.9977556,0.0001556853,0.0004233854,0.0006162925,0.0005461726,0.0005028192],"domain_scores_gemma":[0.9983902,0.0005223293,0.00009230859,0.0006974629,0.0001058767,0.0001918267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002757077,0.001122977,0.00003697836,0.0005483641,0.001905622,0.0007672662,0.00172398,0.147856,0.03299313,0.006166813,0.0007642498,0.8058389],"study_design_scores_gemma":[0.00160186,0.0002982053,0.00008861936,0.0003445233,0.0001062488,0.00006322836,0.00001820376,0.9949852,0.0009148039,0.0001565634,0.001113566,0.0003089399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004668036,0.0001141409,0.9890913,0.001733719,0.001202452,0.0007482179,0.00006997739,0.00230655,0.00006556528],"genre_scores_gemma":[0.9874924,0.000002595501,0.01175078,0.0002392642,0.00005070233,0.0001862787,0.000005388252,0.00003726512,0.0002353082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9828244,"threshold_uncertainty_score":0.9999828,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02227317367211629,"gpt":0.250750505202805,"spread":0.2284773315306887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001780951,0.0003646261,0.0007871382,0.0007672474,0.0001880843,0.0004023935,0.001419273,0.0001963611,0.000001182738],"category_scores_gemma":[0.002051373,0.0003334544,0.0003807713,0.0006014421,0.0001557719,0.0009952036,0.0002905435,0.0007252074,0.00002552414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001320855,"about_ca_system_score_gemma":0.0002821614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002473665,"about_ca_topic_score_gemma":0.000003676791,"domain_scores_codex":[0.9961941,0.0003121368,0.001220298,0.0004340117,0.001275112,0.0005643888],"domain_scores_gemma":[0.9942394,0.001834782,0.001542662,0.0002734757,0.001843671,0.0002659801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007427578,0.0002538802,0.007924925,0.00007120397,0.001646477,0.0008181699,0.001305347,0.871994,0.09306765,0.001150787,0.0006485199,0.02104479],"study_design_scores_gemma":[0.002979056,0.0002979379,0.001076294,0.0003175282,0.0001052281,0.0005115019,0.000315492,0.9897187,0.001995116,0.00008038312,0.002511136,0.00009160081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4185947,0.0008367613,0.5785225,0.0002270913,0.001334533,0.0002444866,0.00003768768,0.0001113234,0.00009090869],"genre_scores_gemma":[0.9773732,0.0001948685,0.02053696,0.0001139645,0.001492861,0.000006428266,0.00001732093,0.0000586855,0.0002056771],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5587785,"threshold_uncertainty_score":0.9999117,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03561845750667487,"gpt":0.2763211445067575,"spread":0.2407026870000826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001409433,0.000338848,0.0003162342,0.00008561562,0.0003900765,0.000275139,0.00115157,0.00006310197,0.000003579311],"category_scores_gemma":[0.0007363024,0.000201637,0.0001070993,0.0003410806,0.0002579419,0.0003281816,0.0003751594,0.0004896688,0.00007239239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000148484,"about_ca_system_score_gemma":0.0001698974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009848466,"about_ca_topic_score_gemma":0.00005444892,"domain_scores_codex":[0.997403,0.0003122619,0.0004184855,0.0006721623,0.0006362314,0.0005579214],"domain_scores_gemma":[0.9971679,0.001106539,0.0002619409,0.001083099,0.0001621269,0.0002183275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002869436,0.000961118,0.01015402,0.00009919753,0.0007542858,0.0002515993,0.01152703,0.001816132,0.000883927,0.1157874,0.000170052,0.8573083],"study_design_scores_gemma":[0.001243796,0.0007182077,0.006143203,0.00005587774,0.00007220056,0.00005527949,0.0002415521,0.9766934,0.00007527716,0.005403686,0.00884328,0.0004542543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5717051,0.000352284,0.412459,0.01334116,0.0002505332,0.001357027,0.00002413258,0.0003425862,0.0001681109],"genre_scores_gemma":[0.8480538,0.000006812563,0.150649,0.0005648655,0.0001712814,0.00009980967,0.00004508516,0.00003289462,0.0003765083],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9748772,"threshold_uncertainty_score":0.8222517,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008015808123454937,"gpt":0.2475236819889693,"spread":0.2395078738655144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009477152,0.0002785206,0.0004537036,0.0001185298,0.0003798158,0.0001346803,0.001162205,0.00006834973,5.668239e-7],"category_scores_gemma":[0.0002275831,0.0001845789,0.0002182451,0.0008063474,0.0001657785,0.0001018146,0.0003771936,0.0002696801,0.000002035635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007459192,"about_ca_system_score_gemma":0.0001599859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002051263,"about_ca_topic_score_gemma":0.00004564165,"domain_scores_codex":[0.9974355,0.0003768728,0.0006376191,0.0005513522,0.0003283063,0.0006703319],"domain_scores_gemma":[0.9962367,0.002327153,0.0004703568,0.0006235531,0.0002498406,0.00009238121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001818012,0.0003611387,0.001510713,0.0004560909,0.0004566722,0.00005082188,0.002963756,0.04357286,0.01076536,0.003615073,0.00008457527,0.9359812],"study_design_scores_gemma":[0.004586334,0.0001198155,0.002749588,0.0001465505,0.00004931484,0.00001487474,0.0002953513,0.9913596,0.0001897135,0.0001570134,0.0001612541,0.0001706209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1028104,0.00008122071,0.8928603,0.001399389,0.0005403451,0.001680788,0.0001504938,0.0004750294,0.000002084914],"genre_scores_gemma":[0.9693177,0.000003298112,0.03010708,0.0004217416,0.00002857996,0.00005959663,0.00001242759,0.00003129969,0.00001826179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9477867,"threshold_uncertainty_score":0.7526908,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01959364087753272,"gpt":0.2270879000056234,"spread":0.2074942591280907,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001640665,0.0001376913,0.0001393198,0.00008335372,0.0001361194,0.0001652672,0.0006409397,0.00004492863,0.0001226042],"category_scores_gemma":[0.00006329962,0.000125036,0.00006793965,0.0002210601,0.00003557475,0.0004100074,0.0002149213,0.0001907146,0.0003029177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007627976,"about_ca_system_score_gemma":0.00001156374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003510169,"about_ca_topic_score_gemma":0.000001406284,"domain_scores_codex":[0.9987355,0.00004887511,0.0001939867,0.0003226894,0.0002975038,0.0004013836],"domain_scores_gemma":[0.9992914,0.00008126002,0.00005071715,0.0003935398,0.00007167557,0.0001114172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001118075,0.00005060634,0.00002856022,0.00000438612,0.00003076312,0.0000328945,0.0005350682,0.004021794,0.0001559018,0.1202942,0.0004906758,0.874354],"study_design_scores_gemma":[0.0003929663,0.0001057867,0.00003843375,0.000005831274,0.000003656229,0.00001045382,0.00002103068,0.9926615,0.00004804506,0.0005693585,0.005979246,0.0001637401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001625509,0.00007519979,0.978272,0.0006196293,0.0001505511,0.0001589181,1.442405e-7,0.0005192202,0.02004174],"genre_scores_gemma":[0.8744354,0.000006914153,0.1127972,0.0003583977,0.00004524921,0.00002641509,0.000001136074,0.000008618325,0.01232064],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9886397,"threshold_uncertainty_score":0.5098822,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Control (management); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.006745649804198587,"gpt":0.2209946881010428,"spread":0.2142490382968442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004072026,0.0001991359,0.0002958748,0.00008464369,0.0001283528,0.0001447348,0.000810895,0.00006704008,0.0000333528],"category_scores_gemma":[0.0001027139,0.000171319,0.0001374546,0.0001505625,0.00003638899,0.0005287509,0.0001860398,0.0002134046,0.0001587722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007211952,"about_ca_system_score_gemma":0.00006571949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004940523,"about_ca_topic_score_gemma":4.046546e-7,"domain_scores_codex":[0.99837,0.00004878241,0.0003041371,0.0004756954,0.0002793217,0.0005220909],"domain_scores_gemma":[0.9988598,0.0002790796,0.0001290924,0.0004855744,0.0001459756,0.0001004783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006478662,0.0001376244,0.008133989,0.0001202413,0.0002386463,0.000006102074,0.0002405628,0.3664513,0.004323138,0.4202196,0.000235969,0.1992449],"study_design_scores_gemma":[0.004013076,0.0004824118,0.0003056653,0.00001162364,0.00000920901,0.000004408723,0.000009837573,0.9855521,0.0001132983,0.0001035317,0.00917258,0.0002222044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02068268,0.00002010287,0.9740005,0.0006497081,0.0003059805,0.001058922,4.399458e-7,0.0004029039,0.002878772],"genre_scores_gemma":[0.8814889,0.000003441588,0.1121369,0.0005330527,0.00003212698,0.0001205614,0.000004927515,0.00001574731,0.005664344],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8618636,"threshold_uncertainty_score":0.6986186,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007856394716716102,"gpt":0.3001037041050311,"spread":0.2922473093883149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002167345,0.0006352246,0.0007577186,0.0008991049,0.0002538191,0.0004646676,0.001253827,0.0001863948,0.0000195616],"category_scores_gemma":[0.009602523,0.0006252569,0.0002846459,0.001213564,0.00005439899,0.001122676,0.0001697966,0.001344502,0.00005026705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006153692,"about_ca_system_score_gemma":0.0006580913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004858302,"about_ca_topic_score_gemma":0.00002152874,"domain_scores_codex":[0.9961879,0.0005219848,0.0007497593,0.0009300124,0.0006067728,0.001003572],"domain_scores_gemma":[0.9924888,0.00515242,0.0004294268,0.001193519,0.0004671273,0.0002687005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006528943,0.0001876975,0.00003791429,0.00003965236,0.0003827508,0.00009130243,0.00009275327,0.8923984,0.004372623,0.05910388,0.00008799217,0.04255211],"study_design_scores_gemma":[0.01729109,0.0005568523,0.00007929376,0.0001211775,0.0001728598,0.00001197637,0.00002568869,0.9321932,0.0002361599,0.00005976098,0.04874714,0.0005048037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00008961503,0.0001947791,0.9898553,0.004170328,0.0008670421,0.0012824,0.00001027525,0.00108311,0.00244708],"genre_scores_gemma":[0.9317844,0.000004748754,0.05946827,0.007457825,0.0002443382,0.0004112701,0.00001532092,0.00005732095,0.0005565415],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9316947,"threshold_uncertainty_score":0.9996199,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Adaptive learning; Adaptive control; Artificial intelligence; Control (management); Machine learning; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.006952249410241171,"gpt":0.2509708647991017,"spread":0.2440186153888605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001544867,0.0002106647,0.0003298773,0.0001670934,0.0002507587,0.0003644135,0.0007295632,0.00008626159,0.000009757852],"category_scores_gemma":[0.0002033864,0.0001447819,0.000140866,0.0000906351,0.0001779879,0.0005314167,0.00005621279,0.0004579285,0.000004493725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008433314,"about_ca_system_score_gemma":0.0002432341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003406304,"about_ca_topic_score_gemma":0.000001371753,"domain_scores_codex":[0.9981623,0.0002122235,0.0004186069,0.0003059122,0.0006694171,0.0002314943],"domain_scores_gemma":[0.9950528,0.002595626,0.0006588812,0.0001015935,0.001488934,0.0001021468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008093374,0.000161871,0.0002100004,0.00001325662,0.0006361953,0.0000104163,0.0004914478,0.01204537,0.0009069119,0.0985402,0.001011886,0.8778791],"study_design_scores_gemma":[0.01302832,0.002401112,0.0007698152,0.000175197,0.0001521522,0.00004545094,0.0004444605,0.8316746,0.00005120293,0.02249259,0.1284275,0.0003375473],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001488829,0.0007082371,0.9920105,0.001743722,0.004436215,0.0006289703,0.00001652448,0.00002293247,0.0002839939],"genre_scores_gemma":[0.9403678,0.00001129154,0.002575867,0.000747532,0.056111,0.00005345797,0.000001041088,0.00001546636,0.0001165873],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9894347,"threshold_uncertainty_score":0.5904033,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03195951659220993,"gpt":0.2699029278227233,"spread":0.2379434112305134,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003203372,0.0002984486,0.0004351363,0.0001242518,0.0001158324,0.0001762675,0.0009796132,0.0001926469,6.159664e-7],"category_scores_gemma":[0.00008951427,0.0002882839,0.0001804186,0.0001874511,0.00003291677,0.0004169315,0.0002856543,0.0003169862,0.00003548279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003925877,"about_ca_system_score_gemma":0.0001645455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003370939,"about_ca_topic_score_gemma":0.00005048549,"domain_scores_codex":[0.9977636,0.00007930408,0.0003864734,0.0007296941,0.0004332998,0.0006076122],"domain_scores_gemma":[0.9982097,0.0002473533,0.0002205485,0.0006633897,0.0005137853,0.0001452124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001627523,0.0001950707,0.00003215162,0.00001734614,0.00006102429,0.000005410896,0.0002174273,0.4976751,0.000372983,0.4993964,0.000003130931,0.002007762],"study_design_scores_gemma":[0.001361246,0.0002786614,0.0001033891,0.00005159693,0.00003227558,0.00001617235,0.0001934454,0.989799,0.00005493565,0.007759933,0.000005819174,0.0003435421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002189066,0.00005425072,0.9945962,0.0001992086,0.0009985924,0.001566954,0.00004861928,0.0002965759,0.00005053421],"genre_scores_gemma":[0.6019853,0.000001561286,0.3973613,0.00008175334,0.00005028169,0.00004155523,0.00001067214,0.00002788982,0.0004396235],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5997963,"threshold_uncertainty_score":0.9999569,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02542890790449781,"gpt":0.277794600672952,"spread":0.2523656927684542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005508497,0.0002118125,0.0002450164,0.0001333838,0.0002055787,0.0002786832,0.0009453956,0.00007909771,0.00002521944],"category_scores_gemma":[0.00008126198,0.0002023145,0.0001130188,0.0002091006,0.00001630364,0.001135086,0.000222141,0.0002201385,0.00005816954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001105061,"about_ca_system_score_gemma":0.00007929873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005720738,"about_ca_topic_score_gemma":0.00001505613,"domain_scores_codex":[0.9981378,0.00004564793,0.0003199239,0.0005859048,0.0003298886,0.0005808061],"domain_scores_gemma":[0.9987524,0.000135311,0.000144139,0.0006203568,0.0002232685,0.0001245475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002441192,0.0001014643,0.0007371738,0.00003766814,0.00006186814,0.000004958675,0.0007657286,0.0646585,0.04797028,0.7839425,0.00002119541,0.1016742],"study_design_scores_gemma":[0.0008218722,0.0006001007,0.0002031858,0.0000374885,0.000009273544,0.000005249008,0.00020246,0.9884081,0.003154639,0.004820224,0.001446156,0.0002912202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02624137,0.00001176585,0.9705898,0.0004045528,0.0003856735,0.0006684582,6.633965e-7,0.0009459436,0.0007518342],"genre_scores_gemma":[0.7494434,0.000001114122,0.2465283,0.0005852878,0.00008537085,0.00002637863,0.00001528467,0.00002188045,0.003292938],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9237496,"threshold_uncertainty_score":0.8250145,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}